ContractorAgent/plugin/core/gemini/sdk-adapter.ts

import fs from "node:fs";
import path from "node:path";
import os from "node:os";
import { spawn } from "node:child_process";
import { createInterface } from "node:readline";
import { fileURLToPath } from "node:url";
import type { ClaudeMessage, OpenAITool } from "../claude/sdk-adapter.js";

// Resolve the MCP server script path relative to this file.
// Installed layout: plugin root / core / gemini / sdk-adapter.ts
//                   plugin root / services / openclaw-mcp-server.mjs
const __dirname = path.dirname(fileURLToPath(import.meta.url));
const MCP_SERVER_SCRIPT = path.resolve(__dirname, "../../services/openclaw-mcp-server.mjs");

export type GeminiDispatchOptions = {
  prompt: string;
  /**
   * System-level instructions written to workspace/GEMINI.md before each invocation.
   * Gemini CLI reads GEMINI.md from cwd on every turn (including resumes) — it is NOT
   * stored in the session file — so updating it takes effect immediately.
   */
  systemPrompt?: string;
  workspace: string;
  agentId?: string;
  resumeSessionId?: string;
  /** Gemini model override (e.g. "gemini-2.5-flash"). Defaults to gemini-cli's configured default. */
  model?: string;
  /** OpenClaw tool definitions to expose via MCP */
  openclawTools?: OpenAITool[];
  bridgePort?: number;
  bridgeApiKey?: string;
};

/**
 * Write the OpenClaw MCP server config to the workspace's .gemini/settings.json.
 *
 * Unlike Claude's --mcp-config flag, Gemini CLI reads MCP configuration from the
 * project settings file (.gemini/settings.json in the cwd). We write it before
 * each invocation to keep the tool list in sync with the current turn's tools.
 *
 * The file is merged with any existing settings to preserve user/project config.
 */
function setupGeminiMcpSettings(
  tools: OpenAITool[],
  bridgePort: number,
  bridgeApiKey: string,
  workspace: string,
  agentId: string,
): void {
  const geminiDir = path.join(workspace, ".gemini");
  const settingsPath = path.join(geminiDir, "settings.json");

  fs.mkdirSync(geminiDir, { recursive: true });

  // Preserve existing non-MCP settings
  let existing: Record<string, unknown> = {};
  if (fs.existsSync(settingsPath)) {
    try {
      existing = JSON.parse(fs.readFileSync(settingsPath, "utf8")) as Record<string, unknown>;
    } catch {
      // corrupt settings — start fresh
    }
  }

  if (!tools.length || !fs.existsSync(MCP_SERVER_SCRIPT)) {
    delete existing.mcpServers;
  } else {
    const tmpDir = os.tmpdir();
    const sessionId = `oc-${Date.now()}`;
    const toolDefsPath = path.join(tmpDir, `${sessionId}-tools.json`);
    fs.writeFileSync(toolDefsPath, JSON.stringify(tools, null, 2), "utf8");

    // Gemini MCP server config — server alias must not contain underscores
    // (Gemini uses underscores as FQN separator: mcp_<alias>_<toolname>).
    // We use "openclaw" (no underscores) to keep names clean.
    existing.mcpServers = {
      openclaw: {
        command: process.execPath,
        args: [MCP_SERVER_SCRIPT],
        env: {
          TOOL_DEFS_FILE: toolDefsPath,
          BRIDGE_EXECUTE_URL: `http://127.0.0.1:${bridgePort}/mcp/execute`,
          BRIDGE_API_KEY: bridgeApiKey,
          WORKSPACE: workspace,
          AGENT_ID: agentId,
        },
        trust: true, // auto-approve MCP tool calls (equivalent to Claude's bypassPermissions)
      },
    };
  }

  fs.writeFileSync(settingsPath, JSON.stringify(existing, null, 2), "utf8");
}

/**
 * Dispatch a turn to Gemini CLI using `gemini -p --output-format stream-json`.
 * Returns an async iterable of ClaudeMessage events (same interface as Claude adapter).
 *
 * Stream-json event types from Gemini CLI:
 *   init    → { session_id, model }
 *   message → { role: "assistant", content: string, delta: true }  (streaming text)
 *   tool_use    → informational (Gemini handles internally)
 *   tool_result → informational (Gemini handles internally)
 *   result  → { status, stats }
 */
export async function* dispatchToGemini(
  opts: GeminiDispatchOptions,
): AsyncIterable<ClaudeMessage> {
  const {
    prompt,
    systemPrompt,
    workspace,
    agentId = "",
    resumeSessionId,
    model,
    openclawTools,
    bridgePort = 18800,
    bridgeApiKey = "",
  } = opts;

  // Write system-level instructions to workspace/GEMINI.md every turn.
  // Gemini CLI reads GEMINI.md from cwd on every invocation (including resumes)
  // and does NOT store it in the session file, so this acts as a stateless system prompt.
  if (systemPrompt) {
    fs.writeFileSync(path.join(workspace, "GEMINI.md"), systemPrompt, "utf8");
  }

  // Write MCP config to workspace .gemini/settings.json every turn.
  // Gemini CLI restarts the MCP server process each invocation (like Claude),
  // so we must re-inject the config on every turn including resumes.
  if (openclawTools?.length) {
    setupGeminiMcpSettings(openclawTools, bridgePort, bridgeApiKey, workspace, agentId);
  }

  // NOTE: prompt goes right after -p before other flags to avoid ambiguity.
  const args: string[] = [
    "-p",
    prompt,
    "--output-format", "stream-json",
    "--approval-mode", "yolo",
  ];

  if (model) {
    args.push("-m", model);
  }

  if (resumeSessionId) {
    args.push("--resume", resumeSessionId);
  }

  const child = spawn("gemini", args, {
    cwd: workspace,
    stdio: ["ignore", "pipe", "pipe"],
    env: { ...process.env },
  });

  const stderrLines: string[] = [];
  child.stderr?.on("data", (chunk: Buffer) => {
    stderrLines.push(chunk.toString("utf8").trim());
  });

  const rl = createInterface({ input: child.stdout!, crlfDelay: Infinity });

  let capturedSessionId = "";
  const events: ClaudeMessage[] = [];
  let done = false;
  let resolveNext: (() => void) | null = null;

  rl.on("line", (line: string) => {
    if (!line.trim()) return;
    let event: Record<string, unknown>;
    try {
      event = JSON.parse(line);
    } catch {
      return; // ignore non-JSON lines (e.g. "YOLO mode is enabled." warning)
    }

    const type = event.type as string;

    // init event carries the session_id for future --resume
    if (type === "init") {
      const sid = event.session_id as string;
      if (sid) capturedSessionId = sid;
    }

    // Streaming assistant text: message events with delta:true
    if (type === "message" && event.role === "assistant" && event.delta) {
      const content = event.content as string;
      if (content) {
        events.push({ type: "text", text: content });
      }
    }

    if (resolveNext) {
      const r = resolveNext;
      resolveNext = null;
      r();
    }
  });

  rl.on("close", () => {
    done = true;
    if (resolveNext) {
      const r = resolveNext;
      resolveNext = null;
      r();
    }
  });

  while (true) {
    if (events.length > 0) {
      yield events.shift()!;
      continue;
    }
    if (done) break;
    await new Promise<void>((resolve) => {
      resolveNext = resolve;
    });
  }

  while (events.length > 0) {
    yield events.shift()!;
  }

  await new Promise<void>((resolve) => {
    child.on("close", resolve);
    if (child.exitCode !== null) resolve();
  });

  if (capturedSessionId) {
    yield { type: "done", sessionId: capturedSessionId };
  } else {
    const stderrSummary = stderrLines
      .join(" ")
      .replace(/YOLO mode is enabled\./g, "")
      .trim()
      .slice(0, 200);
    yield {
      type: "error",
      message: `gemini did not return a session_id${stderrSummary ? `: ${stderrSummary}` : ""}`,
    };
  }
}