feat(agent): sandbox conversation analysis

tests/runtime/opencodeConfig.test.ts

@@ -1,10 +1,29 @@
 import { describe, expect, it } from "bun:test";
 import { readFile } from "node:fs/promises";
+import sandboxBash from "../../.opencode/tools/bash.js";
+import tjwaterCli from "../../.opencode/tools/tjwater_cli.js";
 import storeRenderRef, {
   resolveStoreRenderFilePath,
 } from "../../.opencode/tools/store_render_ref.js";
 
 describe("internal OpenCode permissions", () => {
+  it("pins the runtime, SDK, plugin, and image to OpenCode 1.18.13", async () => {
+    const [rootPackageText, toolPackageText, dockerfile] = await Promise.all([
+      readFile("package.json", "utf8"),
+      readFile(".opencode/package.json", "utf8"),
+      readFile("Dockerfile", "utf8"),
+    ]);
+    const rootPackage = JSON.parse(rootPackageText) as {
+      dependencies?: Record<string, string>;
+    };
+    const toolPackage = JSON.parse(toolPackageText) as {
+      dependencies?: Record<string, string>;
+    };
+    expect(rootPackage.dependencies?.["@opencode-ai/sdk"]).toBe("1.18.13");
+    expect(toolPackage.dependencies?.["@opencode-ai/plugin"]).toBe("1.18.13");
+    expect(dockerfile.startsWith("FROM smanx/opencode:1.18.13@")).toBe(true);
+  });
+
   it("keeps protected paths denied in every approval mode", async () => {
     const config = JSON.parse(await readFile("opencode.json", "utf8")) as {
       permission?: Record<string, string | Record<string, string>>;
@@ -89,3 +108,77 @@ describe("store_render_ref arguments", () => {
     });
   });
 });
+
+describe("sandbox bash tool", () => {
+  it("forwards commands to the authenticated sandbox endpoint", async () => {
+    const originalFetch = globalThis.fetch;
+    const permissionRequests: unknown[] = [];
+    let requestUrl = "";
+    let requestBody: unknown;
+    globalThis.fetch = (async (input: RequestInfo | URL, init?: RequestInit) => {
+      requestUrl = String(input);
+      requestBody = JSON.parse(String(init?.body));
+      return new Response('{"ok":true,"stdout":"done"}');
+    }) as unknown as typeof fetch;
+    try {
+      const definition = sandboxBash as unknown as {
+        execute: (args: unknown, context: unknown) => Promise<unknown>;
+      };
+      await definition.execute(
+        { command: "python3 analysis.py", timeout: 300 },
+        {
+          sessionID: "session-test",
+          ask: async (input: unknown) => permissionRequests.push(input),
+        } as never,
+      );
+    } finally {
+      globalThis.fetch = originalFetch;
+    }
+    expect(requestUrl).toEndWith("/internal/tools/sandbox-shell");
+    expect(permissionRequests).toEqual([
+      {
+        permission: "bash",
+        patterns: ["python3 analysis.py"],
+        always: ["python3 analysis.py"],
+        metadata: {
+          command: "python3 analysis.py",
+        },
+      },
+    ]);
+    expect(requestBody).toEqual({
+      session_id: "session-test",
+      command: "python3 analysis.py",
+      timeout: 300,
+    });
+  });
+});
+
+describe("tjwater_cli storage request", () => {
+  it("forwards store_result so small workflow inputs can be staged", async () => {
+    const originalFetch = globalThis.fetch;
+    let requestBody: unknown;
+    globalThis.fetch = (async (_input: RequestInfo | URL, init?: RequestInit) => {
+      requestBody = JSON.parse(String(init?.body));
+      return new Response('{"ok":true,"data_file":{"file_path":"/tmp/test"}}');
+    }) as unknown as typeof fetch;
+    try {
+      const definition = tjwaterCli as unknown as {
+        execute: (args: unknown, context: unknown) => Promise<unknown>;
+      };
+      await definition.execute(
+        {
+          command: "network get-all-reservoirs-properties",
+          reason: "prepare workflow input",
+          store_result: true,
+        },
+        { sessionID: "session-test" } as never,
+      );
+    } finally {
+      globalThis.fetch = originalFetch;
+    }
+    expect(requestBody).toMatchObject({
+      session_id: "session-test",
+      store_result: true,
+    });
+  });
+});

tests/runtime/toolOutputStaging.test.ts

@@ -0,0 +1,98 @@
+import { afterEach, describe, expect, it } from "bun:test";
+import { mkdir, readFile, rm, stat } from "node:fs/promises";
+import { resolve } from "node:path";
+
+import { config } from "../../src/config.js";
+import { type RuntimeSessionContext } from "../../src/runtime/sessionContext.js";
+import {
+  buildLargeCliResult,
+  stageLargeToolOutput,
+} from "../../src/runtime/toolOutputStaging.js";
+
+const createdPaths: string[] = [];
+
+afterEach(async () => {
+  await Promise.all(
+    createdPaths.splice(0).map((path) => rm(path, { force: true, recursive: true })),
+  );
+});
+
+const createContext = async (): Promise<RuntimeSessionContext> => {
+  const importRoot = resolve(config.RESULT_REF_IMPORT_DIR);
+  await mkdir(importRoot, { recursive: true });
+  const workspaceDirectory = resolve(
+    importRoot,
+    `conversation-staging-${crypto.randomUUID()}`,
+  );
+  await mkdir(workspaceDirectory, { mode: 0o700 });
+  createdPaths.push(workspaceDirectory);
+  return {
+    actorKey: "actor-1",
+    clientSessionId: "client-1",
+    projectKey: "project-1",
+    sessionId: "runtime-1",
+    traceId: "trace-1",
+    workspaceDirectory,
+  };
+};
+
+describe("tool output staging", () => {
+  it("keeps small output inline unless storage is forced", async () => {
+    const context = await createContext();
+    await expect(
+      stageLargeToolOutput(context, '{"ok":true}', {
+        contentType: "application/json",
+        extension: "json",
+        prefix: "cli",
+      }),
+    ).resolves.toBeNull();
+
+    const stored = await stageLargeToolOutput(context, '{"ok":true}', {
+      contentType: "application/json",
+      extension: "json",
+      force: true,
+      prefix: "cli",
+    });
+    expect(stored?.file_path).toContain("/tool-data/cli-");
+    expect(await readFile(stored!.file_path, "utf8")).toBe('{"ok":true}');
+    expect((await stat(stored!.file_path)).mode & 0o777).toBe(0o600);
+  });
+
+  it("stages output above the inline threshold and returns a compact descriptor", async () => {
+    const context = await createContext();
+    const content = JSON.stringify({
+      ok: true,
+      schema_version: "tjwater-cli/v1",
+      data: "x".repeat(config.MAX_INLINE_RESULT_BYTES),
+    });
+    const dataFile = await stageLargeToolOutput(context, content, {
+      contentType: "application/json",
+      extension: "json",
+      prefix: "cli",
+    });
+    expect(dataFile?.bytes).toBe(Buffer.byteLength(content));
+    const stored = dataFile!;
+    expect(buildLargeCliResult(stored)).toEqual({
+      ok: true,
+      schema_version: "tjwater-cli/v1",
+      summary: "CLI 结果已保存到当前对话工作区",
+      data_file: stored,
+    });
+  });
+
+  it("does not stage large output for legacy sessions without a workspace", async () => {
+    await expect(
+      stageLargeToolOutput(
+        {
+          actorKey: "actor-1",
+          clientSessionId: "client-1",
+          projectKey: "project-1",
+          sessionId: "runtime-1",
+          traceId: "trace-1",
+        },
+        "x".repeat(config.MAX_INLINE_RESULT_BYTES + 1),
+        { contentType: "text/plain", extension: "txt", prefix: "shell" },
+      ),
+    ).rejects.toThrow("requires a conversation workspace");
+  });
+});