fix(discover): parse Codex sessions with large session_meta (>4KB) (#798)

Merged via PR triage plan. Fixes Codex session discovery for v0.117+ with 15KB+ session_meta. Follow-up: add >128KB regression test.

bin/gstack-global-discover.ts

@@ -291,7 +291,7 @@ function extractCwdFromJsonl(filePath: string): string | null {
 }
 
 function scanCodex(since: Date): Session[] {
-  const sessionsDir = join(homedir(), ".codex", "sessions");
+  const sessionsDir = process.env.CODEX_SESSIONS_DIR || join(homedir(), ".codex", "sessions");
   if (!existsSync(sessionsDir)) return [];
 
   const sessions: Session[] = [];
@@ -326,11 +326,14 @@ function scanCodex(since: Date): Session[] {
               continue;
             }
 
-            // Read first line for session_meta (only first 4KB)
+            // Codex session_meta lines embed the full system prompt in
+            // base_instructions (~15KB as of CLI v0.117+). A 4KB buffer
+            // truncates the line and JSON.parse fails. 128KB covers current
+            // sizes with room for growth.
             try {
               const fd = openSync(filePath, "r");
-              const buf = Buffer.alloc(4096);
+              const buf = Buffer.alloc(131072);
-              const bytesRead = readSync(fd, buf, 0, 4096, 0);
+              const bytesRead = readSync(fd, buf, 0, 131072, 0);
               closeSync(fd);
               const firstLine = buf.toString("utf-8", 0, bytesRead).split("\n")[0];
               if (!firstLine) continue;

test/global-discover.test.ts

@@ -131,6 +131,127 @@ describe("gstack-global-discover", () => {
     });
   });
 
+  describe("codex large session_meta parsing", () => {
+    let codexDir: string;
+    let tmpDir: string;
+
+    beforeEach(() => {
+      tmpDir = mkdtempSync(join(tmpdir(), "gstack-codex-test-"));
+      // Build a realistic ~/.codex/sessions/YYYY/MM/DD structure
+      const now = new Date();
+      const y = now.getFullYear().toString();
+      const m = String(now.getMonth() + 1).padStart(2, "0");
+      const d = String(now.getDate()).padStart(2, "0");
+      codexDir = join(tmpDir, "codex-home", "sessions", y, m, d);
+      mkdirSync(codexDir, { recursive: true });
+    });
+
+    afterEach(() => {
+      rmSync(tmpDir, { recursive: true, force: true });
+    });
+
+    function writeCodexSession(
+      dir: string,
+      cwd: string,
+      baseInstructionsSize: number
+    ): string {
+      const padding = "x".repeat(baseInstructionsSize);
+      const line = JSON.stringify({
+        timestamp: new Date().toISOString(),
+        type: "session_meta",
+        payload: {
+          id: `test-${Date.now()}`,
+          timestamp: new Date().toISOString(),
+          cwd,
+          originator: "codex_exec",
+          cli_version: "0.118.0",
+          source: "exec",
+          model_provider: "openai",
+          base_instructions: { text: padding },
+        },
+      });
+      const name = `rollout-${new Date().toISOString().replace(/[:.]/g, "-")}-${Math.random().toString(36).slice(2)}.jsonl`;
+      const filePath = join(dir, name);
+      writeFileSync(filePath, line + "\n");
+      return filePath;
+    }
+
+    test("discovers codex sessions with >4KB session_meta via CLI", () => {
+      // Create a git repo as the session target
+      const repoDir = join(tmpDir, "fake-repo");
+      mkdirSync(repoDir);
+      spawnSync("git", ["init"], { cwd: repoDir, stdio: "pipe" });
+      spawnSync("git", ["commit", "--allow-empty", "-m", "init"], {
+        cwd: repoDir,
+        stdio: "pipe",
+      });
+
+      // Write a session with a 20KB first line (simulates Codex v0.117+)
+      writeCodexSession(codexDir, repoDir, 20000);
+
+      // Run discovery with CODEX_SESSIONS_DIR override
+      const result = spawnSync(
+        "bun",
+        ["run", scriptPath, "--since", "1h", "--format", "json"],
+        {
+          encoding: "utf-8",
+          timeout: 30000,
+          env: {
+            ...process.env,
+            CODEX_SESSIONS_DIR: join(tmpDir, "codex-home", "sessions"),
+          },
+        }
+      );
+
+      expect(result.status).toBe(0);
+      const json = JSON.parse(result.stdout);
+      expect(json.tools.codex.total_sessions).toBeGreaterThanOrEqual(1);
+    });
+
+    test("4KB buffer truncates session_meta, 128KB buffer parses it", () => {
+      const padding = "x".repeat(20000);
+      const sessionMeta = JSON.stringify({
+        timestamp: new Date().toISOString(),
+        type: "session_meta",
+        payload: {
+          id: "test-id",
+          timestamp: new Date().toISOString(),
+          cwd: "/tmp/test-repo",
+          originator: "codex_exec",
+          cli_version: "0.118.0",
+          source: "exec",
+          model_provider: "openai",
+          base_instructions: { text: padding },
+        },
+      });
+
+      expect(sessionMeta.length).toBeGreaterThan(4096);
+
+      const filePath = join(codexDir, "test.jsonl");
+      writeFileSync(filePath, sessionMeta + "\n");
+
+      // 4KB buffer: JSON.parse fails (the old bug)
+      const { openSync, readSync, closeSync } = require("fs");
+      const fd4k = openSync(filePath, "r");
+      const buf4k = Buffer.alloc(4096);
+      readSync(fd4k, buf4k, 0, 4096, 0);
+      closeSync(fd4k);
+      expect(() =>
+        JSON.parse(buf4k.toString("utf-8").split("\n")[0])
+      ).toThrow();
+
+      // 128KB buffer: JSON.parse succeeds (the fix)
+      const fd128k = openSync(filePath, "r");
+      const buf128k = Buffer.alloc(131072);
+      const bytesRead = readSync(fd128k, buf128k, 0, 131072, 0);
+      closeSync(fd128k);
+      const firstLine = buf128k.toString("utf-8", 0, bytesRead).split("\n")[0];
+      const meta = JSON.parse(firstLine);
+      expect(meta.type).toBe("session_meta");
+      expect(meta.payload.cwd).toBe("/tmp/test-repo");
+    });
+  });
+
   describe("discovery output structure", () => {
     test("repos have required fields", () => {
       const result = spawnSync(