7 files changed, 499 insertions(+), 6 deletions(-)

M CHANGELOG.md
M VERSION
M package.json
A test/gemini-e2e.test.ts
A test/helpers/gemini-session-runner.test.ts
A test/helpers/gemini-session-runner.ts
M test/helpers/touchfiles.ts

@@ 1,5 1,13 @@
 # Changelog
 
+## [0.9.2.0] - 2026-03-20 — Gemini CLI E2E Tests
+
+### Added
+
+- **Gemini CLI is now tested end-to-end.** Two E2E tests verify that gstack skills work when invoked by Google's Gemini CLI (`gemini -p`). The `gemini-discover-skill` test confirms skill discovery from `.agents/skills/`, and `gemini-review-findings` runs a full code review via gstack-review. Both parse Gemini's stream-json NDJSON output and track token usage.
+- **Gemini JSONL parser with 10 unit tests.** `parseGeminiJSONL` handles all Gemini event types (init, message, tool_use, tool_result, result) with defensive parsing for malformed input. The parser is a pure function, independently testable without spawning the CLI.
+- **`bun run test:gemini`** and **`bun run test:gemini:all`** scripts for running Gemini E2E tests independently. Gemini tests are also included in `test:evals` and `test:e2e` aggregate scripts.
+
 ## [0.9.1.0] - 2026-03-20 — Adversarial Spec Review + Skill Chaining
 
 ### Added

@@ 1,1 1,1 @@
-0.9.1.0
+0.9.2.0

@@ 12,13 12,15 @@
     "gen:skill-docs": "bun run scripts/gen-skill-docs.ts",
     "dev": "bun run browse/src/cli.ts",
     "server": "bun run browse/src/server.ts",
-    "test": "bun test browse/test/ test/ --ignore test/skill-e2e.test.ts --ignore test/skill-llm-eval.test.ts --ignore test/skill-routing-e2e.test.ts --ignore test/codex-e2e.test.ts",
-    "test:evals": "EVALS=1 bun test test/skill-llm-eval.test.ts test/skill-e2e.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts",
-    "test:evals:all": "EVALS=1 EVALS_ALL=1 bun test test/skill-llm-eval.test.ts test/skill-e2e.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts",
-    "test:e2e": "EVALS=1 bun test test/skill-e2e.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts",
-    "test:e2e:all": "EVALS=1 EVALS_ALL=1 bun test test/skill-e2e.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts",
+    "test": "bun test browse/test/ test/ --ignore test/skill-e2e.test.ts --ignore test/skill-llm-eval.test.ts --ignore test/skill-routing-e2e.test.ts --ignore test/codex-e2e.test.ts --ignore test/gemini-e2e.test.ts",
+    "test:evals": "EVALS=1 bun test test/skill-llm-eval.test.ts test/skill-e2e.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
+    "test:evals:all": "EVALS=1 EVALS_ALL=1 bun test test/skill-llm-eval.test.ts test/skill-e2e.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
+    "test:e2e": "EVALS=1 bun test test/skill-e2e.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
+    "test:e2e:all": "EVALS=1 EVALS_ALL=1 bun test test/skill-e2e.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
     "test:codex": "EVALS=1 bun test test/codex-e2e.test.ts",
     "test:codex:all": "EVALS=1 EVALS_ALL=1 bun test test/codex-e2e.test.ts",
+    "test:gemini": "EVALS=1 bun test test/gemini-e2e.test.ts",
+    "test:gemini:all": "EVALS=1 EVALS_ALL=1 bun test test/gemini-e2e.test.ts",
     "skill:check": "bun run scripts/skill-check.ts",
     "dev:skill": "bun run scripts/dev-skill.ts",
     "start": "bun run browse/src/server.ts",

@@ 0,0 1,173 @@
+/**
+ * Gemini CLI E2E tests — verify skills work when invoked by Gemini CLI.
+ *
+ * Spawns `gemini -p` with stream-json output in the repo root (where
+ * .agents/skills/ already exists), parses JSONL events, and validates
+ * structured results. Follows the same pattern as codex-e2e.test.ts.
+ *
+ * Prerequisites:
+ * - `gemini` binary installed (npm install -g @google/gemini-cli)
+ * - Gemini authenticated via ~/.gemini/ config or GEMINI_API_KEY env var
+ * - EVALS=1 env var set (same gate as Claude E2E tests)
+ *
+ * Skips gracefully when prerequisites are not met.
+ */
+
+import { describe, test, expect, afterAll } from 'bun:test';
+import { runGeminiSkill } from './helpers/gemini-session-runner';
+import type { GeminiResult } from './helpers/gemini-session-runner';
+import { EvalCollector } from './helpers/eval-store';
+import { selectTests, detectBaseBranch, getChangedFiles, GLOBAL_TOUCHFILES } from './helpers/touchfiles';
+import * as path from 'path';
+
+const ROOT = path.resolve(import.meta.dir, '..');
+
+// --- Prerequisites check ---
+
+const GEMINI_AVAILABLE = (() => {
+  try {
+    const result = Bun.spawnSync(['which', 'gemini']);
+    return result.exitCode === 0;
+  } catch { return false; }
+})();
+
+const evalsEnabled = !!process.env.EVALS;
+
+// Skip all tests if gemini is not available or EVALS is not set.
+const SKIP = !GEMINI_AVAILABLE || !evalsEnabled;
+
+const describeGemini = SKIP ? describe.skip : describe;
+
+// Log why we're skipping (helpful for debugging CI)
+if (!evalsEnabled) {
+  // Silent — same as Claude E2E tests, EVALS=1 required
+} else if (!GEMINI_AVAILABLE) {
+  process.stderr.write('\nGemini E2E: SKIPPED — gemini binary not found (install: npm i -g @google/gemini-cli)\n');
+}
+
+// --- Diff-based test selection ---
+
+// Gemini E2E touchfiles — keyed by test name, same pattern as Codex E2E
+const GEMINI_E2E_TOUCHFILES: Record<string, string[]> = {
+  'gemini-discover-skill':  ['.agents/skills/**', 'test/helpers/gemini-session-runner.ts'],
+  'gemini-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'test/helpers/gemini-session-runner.ts'],
+};
+
+let selectedTests: string[] | null = null; // null = run all
+
+if (evalsEnabled && !process.env.EVALS_ALL) {
+  const baseBranch = process.env.EVALS_BASE
+    || detectBaseBranch(ROOT)
+    || 'main';
+  const changedFiles = getChangedFiles(baseBranch, ROOT);
+
+  if (changedFiles.length > 0) {
+    const selection = selectTests(changedFiles, GEMINI_E2E_TOUCHFILES, GLOBAL_TOUCHFILES);
+    selectedTests = selection.selected;
+    process.stderr.write(`\nGemini E2E selection (${selection.reason}): ${selection.selected.length}/${Object.keys(GEMINI_E2E_TOUCHFILES).length} tests\n`);
+    if (selection.skipped.length > 0) {
+      process.stderr.write(`  Skipped: ${selection.skipped.join(', ')}\n`);
+    }
+    process.stderr.write('\n');
+  }
+  // If changedFiles is empty (e.g., on main branch), selectedTests stays null -> run all
+}
+
+/** Skip an individual test if not selected by diff-based selection. */
+function testIfSelected(testName: string, fn: () => Promise<void>, timeout: number) {
+  const shouldRun = selectedTests === null || selectedTests.includes(testName);
+  (shouldRun ? test : test.skip)(testName, fn, timeout);
+}
+
+// --- Eval result collector ---
+
+const evalCollector = evalsEnabled && !SKIP ? new EvalCollector('e2e-gemini') : null;
+
+/** DRY helper to record a Gemini E2E test result into the eval collector. */
+function recordGeminiE2E(name: string, result: GeminiResult, passed: boolean) {
+  evalCollector?.addTest({
+    name,
+    suite: 'gemini-e2e',
+    tier: 'e2e',
+    passed,
+    duration_ms: result.durationMs,
+    cost_usd: 0, // Gemini doesn't report cost in USD; tokens are tracked
+    output: result.output?.slice(0, 2000),
+    turns_used: result.toolCalls.length, // approximate: tool calls as turns
+    exit_reason: result.exitCode === 0 ? 'success' : `exit_code_${result.exitCode}`,
+  });
+}
+
+/** Print cost summary after a Gemini E2E test. */
+function logGeminiCost(label: string, result: GeminiResult) {
+  const durationSec = Math.round(result.durationMs / 1000);
+  console.log(`${label}: ${result.tokens} tokens, ${result.toolCalls.length} tool calls, ${durationSec}s`);
+}
+
+// Finalize eval results on exit
+afterAll(async () => {
+  if (evalCollector) {
+    await evalCollector.finalize();
+  }
+});
+
+// --- Tests ---
+
+describeGemini('Gemini E2E', () => {
+
+  testIfSelected('gemini-discover-skill', async () => {
+    // Run Gemini in the repo root where .agents/skills/ exists
+    const result = await runGeminiSkill({
+      prompt: 'List any skills or instructions you have available. Just list the names.',
+      timeoutMs: 60_000,
+      cwd: ROOT,
+    });
+
+    logGeminiCost('gemini-discover-skill', result);
+
+    // Gemini should have produced some output
+    const passed = result.exitCode === 0 && result.output.length > 0;
+    recordGeminiE2E('gemini-discover-skill', result, passed);
+
+    expect(result.exitCode).toBe(0);
+    expect(result.output.length).toBeGreaterThan(0);
+    // The output should reference skills in some form
+    const outputLower = result.output.toLowerCase();
+    expect(
+      outputLower.includes('review') || outputLower.includes('gstack') || outputLower.includes('skill'),
+    ).toBe(true);
+  }, 120_000);
+
+  testIfSelected('gemini-review-findings', async () => {
+    // Run gstack-review skill via Gemini on this repo
+    const result = await runGeminiSkill({
+      prompt: 'Run the gstack-review skill on this repository. Review the current branch diff and report your findings.',
+      timeoutMs: 540_000,
+      cwd: ROOT,
+    });
+
+    logGeminiCost('gemini-review-findings', result);
+
+    // Should produce structured review-like output
+    const output = result.output;
+    const passed = result.exitCode === 0 && output.length > 50;
+    recordGeminiE2E('gemini-review-findings', result, passed);
+
+    expect(result.exitCode).toBe(0);
+    expect(output.length).toBeGreaterThan(50);
+
+    // Review output should contain some review-like content
+    const outputLower = output.toLowerCase();
+    const hasReviewContent =
+      outputLower.includes('finding') ||
+      outputLower.includes('issue') ||
+      outputLower.includes('review') ||
+      outputLower.includes('change') ||
+      outputLower.includes('diff') ||
+      outputLower.includes('clean') ||
+      outputLower.includes('no issues') ||
+      outputLower.includes('p1') ||
+      outputLower.includes('p2');
+    expect(hasReviewContent).toBe(true);
+  }, 600_000);
+});

@@ 0,0 1,104 @@
+import { describe, test, expect } from 'bun:test';
+import { parseGeminiJSONL } from './gemini-session-runner';
+
+// Fixture: actual Gemini CLI stream-json output with tool use
+const FIXTURE_LINES = [
+  '{"type":"init","timestamp":"2026-03-20T15:14:46.455Z","session_id":"test-session-123","model":"auto-gemini-3"}',
+  '{"type":"message","timestamp":"2026-03-20T15:14:46.456Z","role":"user","content":"list the files"}',
+  '{"type":"message","timestamp":"2026-03-20T15:14:49.650Z","role":"assistant","content":"I will list the files.","delta":true}',
+  '{"type":"tool_use","timestamp":"2026-03-20T15:14:49.690Z","tool_name":"run_shell_command","tool_id":"cmd_1","parameters":{"command":"ls"}}',
+  '{"type":"tool_result","timestamp":"2026-03-20T15:14:49.931Z","tool_id":"cmd_1","status":"success","output":"file1.ts\\nfile2.ts"}',
+  '{"type":"message","timestamp":"2026-03-20T15:14:51.945Z","role":"assistant","content":"Here are the files.","delta":true}',
+  '{"type":"result","timestamp":"2026-03-20T15:14:52.030Z","status":"success","stats":{"total_tokens":27147,"input_tokens":26928,"output_tokens":87,"cached":0,"duration_ms":5575,"tool_calls":1}}',
+];
+
+describe('parseGeminiJSONL', () => {
+  test('extracts session ID from init event', () => {
+    const parsed = parseGeminiJSONL(FIXTURE_LINES);
+    expect(parsed.sessionId).toBe('test-session-123');
+  });
+
+  test('concatenates assistant message deltas into output', () => {
+    const parsed = parseGeminiJSONL(FIXTURE_LINES);
+    expect(parsed.output).toBe('I will list the files.Here are the files.');
+  });
+
+  test('ignores user messages', () => {
+    const lines = [
+      '{"type":"message","role":"user","content":"this should be ignored"}',
+      '{"type":"message","role":"assistant","content":"this should be kept","delta":true}',
+    ];
+    const parsed = parseGeminiJSONL(lines);
+    expect(parsed.output).toBe('this should be kept');
+  });
+
+  test('extracts tool names from tool_use events', () => {
+    const parsed = parseGeminiJSONL(FIXTURE_LINES);
+    expect(parsed.toolCalls).toHaveLength(1);
+    expect(parsed.toolCalls[0]).toBe('run_shell_command');
+  });
+
+  test('extracts total tokens from result stats', () => {
+    const parsed = parseGeminiJSONL(FIXTURE_LINES);
+    expect(parsed.tokens).toBe(27147);
+  });
+
+  test('skips malformed lines without throwing', () => {
+    const lines = [
+      '{"type":"init","session_id":"ok"}',
+      'this is not json',
+      '{"type":"message","role":"assistant","content":"hello","delta":true}',
+      '{incomplete json',
+      '{"type":"result","status":"success","stats":{"total_tokens":100}}',
+    ];
+    const parsed = parseGeminiJSONL(lines);
+    expect(parsed.sessionId).toBe('ok');
+    expect(parsed.output).toBe('hello');
+    expect(parsed.tokens).toBe(100);
+  });
+
+  test('skips empty and whitespace-only lines', () => {
+    const lines = [
+      '',
+      '  ',
+      '{"type":"init","session_id":"s1"}',
+      '\t',
+      '{"type":"result","status":"success","stats":{"total_tokens":50}}',
+    ];
+    const parsed = parseGeminiJSONL(lines);
+    expect(parsed.sessionId).toBe('s1');
+    expect(parsed.tokens).toBe(50);
+  });
+
+  test('handles empty input', () => {
+    const parsed = parseGeminiJSONL([]);
+    expect(parsed.output).toBe('');
+    expect(parsed.toolCalls).toHaveLength(0);
+    expect(parsed.tokens).toBe(0);
+    expect(parsed.sessionId).toBeNull();
+  });
+
+  test('handles missing fields gracefully', () => {
+    const lines = [
+      '{"type":"init"}',                              // no session_id
+      '{"type":"message","role":"assistant"}',         // no content
+      '{"type":"tool_use"}',                           // no tool_name
+      '{"type":"result","status":"success"}',          // no stats
+    ];
+    const parsed = parseGeminiJSONL(lines);
+    expect(parsed.sessionId).toBeNull();
+    expect(parsed.output).toBe('');
+    expect(parsed.toolCalls).toHaveLength(0);
+    expect(parsed.tokens).toBe(0);
+  });
+
+  test('handles multiple tool_use events', () => {
+    const lines = [
+      '{"type":"tool_use","tool_name":"run_shell_command","tool_id":"cmd_1","parameters":{"command":"ls"}}',
+      '{"type":"tool_use","tool_name":"read_file","tool_id":"cmd_2","parameters":{"path":"foo.ts"}}',
+      '{"type":"tool_use","tool_name":"run_shell_command","tool_id":"cmd_3","parameters":{"command":"cat bar.ts"}}',
+    ];
+    const parsed = parseGeminiJSONL(lines);
+    expect(parsed.toolCalls).toEqual(['run_shell_command', 'read_file', 'run_shell_command']);
+  });
+});

@@ 0,0 1,201 @@
+/**
+ * Gemini CLI subprocess runner for skill E2E testing.
+ *
+ * Spawns `gemini -p` as an independent process, parses its stream-json
+ * output, and returns structured results. Follows the same pattern as
+ * codex-session-runner.ts but adapted for the Gemini CLI.
+ *
+ * Key differences from Codex session-runner:
+ * - Uses `gemini -p` instead of `codex exec`
+ * - Output is NDJSON with event types: init, message, tool_use, tool_result, result
+ * - Uses `--output-format stream-json --yolo` instead of `--json -s read-only`
+ * - No temp HOME needed — Gemini discovers skills from `.agents/skills/` in cwd
+ * - Message events are streamed with `delta: true` — must concatenate
+ */
+
+import * as path from 'path';
+
+// --- Interfaces ---
+
+export interface GeminiResult {
+  output: string;           // Full assistant message text (concatenated deltas)
+  toolCalls: string[];      // Tool names from tool_use events
+  tokens: number;           // Total tokens used
+  exitCode: number;         // Process exit code
+  durationMs: number;       // Wall clock time
+  sessionId: string | null; // Session ID from init event
+  rawLines: string[];       // Raw JSONL lines for debugging
+}
+
+// --- JSONL parser ---
+
+export interface ParsedGeminiJSONL {
+  output: string;
+  toolCalls: string[];
+  tokens: number;
+  sessionId: string | null;
+}
+
+/**
+ * Parse an array of JSONL lines from `gemini -p --output-format stream-json`.
+ * Pure function — no I/O, no side effects.
+ *
+ * Handles these Gemini event types:
+ * - init → extract session_id
+ * - message (role=assistant, delta=true) → concatenate content into output
+ * - tool_use → extract tool_name
+ * - tool_result → logged but not extracted
+ * - result → extract token usage from stats
+ */
+export function parseGeminiJSONL(lines: string[]): ParsedGeminiJSONL {
+  const outputParts: string[] = [];
+  const toolCalls: string[] = [];
+  let tokens = 0;
+  let sessionId: string | null = null;
+
+  for (const line of lines) {
+    if (!line.trim()) continue;
+    try {
+      const obj = JSON.parse(line);
+      const t = obj.type || '';
+
+      if (t === 'init') {
+        const sid = obj.session_id || '';
+        if (sid) sessionId = sid;
+      } else if (t === 'message') {
+        if (obj.role === 'assistant' && obj.content) {
+          outputParts.push(obj.content);
+        }
+      } else if (t === 'tool_use') {
+        const name = obj.tool_name || '';
+        if (name) toolCalls.push(name);
+      } else if (t === 'result') {
+        const stats = obj.stats || {};
+        tokens = (stats.total_tokens || 0);
+      }
+    } catch { /* skip malformed lines */ }
+  }
+
+  return {
+    output: outputParts.join(''),
+    toolCalls,
+    tokens,
+    sessionId,
+  };
+}
+
+// --- Main runner ---
+
+/**
+ * Run a prompt via `gemini -p` and return structured results.
+ *
+ * Spawns gemini with stream-json output, parses JSONL events,
+ * and returns a GeminiResult. Skips gracefully if gemini binary is not found.
+ */
+export async function runGeminiSkill(opts: {
+  prompt: string;           // What to ask Gemini
+  timeoutMs?: number;       // Default 300000 (5 min)
+  cwd?: string;             // Working directory (where .agents/skills/ lives)
+}): Promise<GeminiResult> {
+  const {
+    prompt,
+    timeoutMs = 300_000,
+    cwd,
+  } = opts;
+
+  const startTime = Date.now();
+
+  // Check if gemini binary exists
+  const whichResult = Bun.spawnSync(['which', 'gemini']);
+  if (whichResult.exitCode !== 0) {
+    return {
+      output: 'SKIP: gemini binary not found',
+      toolCalls: [],
+      tokens: 0,
+      exitCode: -1,
+      durationMs: Date.now() - startTime,
+      sessionId: null,
+      rawLines: [],
+    };
+  }
+
+  // Build gemini command
+  const args = ['-p', prompt, '--output-format', 'stream-json', '--yolo'];
+
+  // Spawn gemini — uses real HOME for auth, cwd for skill discovery
+  const proc = Bun.spawn(['gemini', ...args], {
+    cwd: cwd || process.cwd(),
+    stdout: 'pipe',
+    stderr: 'pipe',
+  });
+
+  // Race against timeout
+  let timedOut = false;
+  const timeoutId = setTimeout(() => {
+    timedOut = true;
+    proc.kill();
+  }, timeoutMs);
+
+  // Stream and collect JSONL from stdout
+  const collectedLines: string[] = [];
+  const stderrPromise = new Response(proc.stderr).text();
+
+  const reader = proc.stdout.getReader();
+  const decoder = new TextDecoder();
+  let buf = '';
+
+  try {
+    while (true) {
+      const { done, value } = await reader.read();
+      if (done) break;
+      buf += decoder.decode(value, { stream: true });
+      const lines = buf.split('\n');
+      buf = lines.pop() || '';
+      for (const line of lines) {
+        if (!line.trim()) continue;
+        collectedLines.push(line);
+
+        // Real-time progress to stderr
+        try {
+          const event = JSON.parse(line);
+          if (event.type === 'tool_use' && event.tool_name) {
+            const elapsed = Math.round((Date.now() - startTime) / 1000);
+            process.stderr.write(`  [gemini ${elapsed}s] tool: ${event.tool_name}\n`);
+          } else if (event.type === 'message' && event.role === 'assistant' && event.content) {
+            const elapsed = Math.round((Date.now() - startTime) / 1000);
+            process.stderr.write(`  [gemini ${elapsed}s] message: ${event.content.slice(0, 100)}\n`);
+          }
+        } catch { /* skip — parseGeminiJSONL will handle it later */ }
+      }
+    }
+  } catch { /* stream read error — fall through to exit code handling */ }
+
+  // Flush remaining buffer
+  if (buf.trim()) {
+    collectedLines.push(buf);
+  }
+
+  const stderr = await stderrPromise;
+  const exitCode = await proc.exited;
+  clearTimeout(timeoutId);
+
+  const durationMs = Date.now() - startTime;
+
+  // Parse all collected JSONL lines
+  const parsed = parseGeminiJSONL(collectedLines);
+
+  // Log stderr if non-empty (may contain auth errors, etc.)
+  if (stderr.trim()) {
+    process.stderr.write(`  [gemini stderr] ${stderr.trim().slice(0, 200)}\n`);
+  }
+
+  return {
+    output: parsed.output,
+    toolCalls: parsed.toolCalls,
+    tokens: parsed.tokens,
+    exitCode: timedOut ? 124 : exitCode,
+    durationMs,
+    sessionId: parsed.sessionId,
+    rawLines: collectedLines,
+  };
+}

@@ 84,6 84,10 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   'codex-discover-skill':  ['codex/**', '.agents/skills/**', 'test/helpers/codex-session-runner.ts'],
   'codex-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'codex/**', 'test/helpers/codex-session-runner.ts'],
 
+  // Gemini E2E (tests skills via Gemini CLI)
+  'gemini-discover-skill':  ['.agents/skills/**', 'test/helpers/gemini-session-runner.ts'],
+  'gemini-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'test/helpers/gemini-session-runner.ts'],
+
   // QA bootstrap
   'qa-bootstrap': ['qa/**', 'browse/src/**', 'ship/**'],
 


@@ 160,6 164,7 @@ export const LLM_JUDGE_TOUCHFILES: Record<string, string[]> = {
 export const GLOBAL_TOUCHFILES = [
   'test/helpers/session-runner.ts',
   'test/helpers/codex-session-runner.ts',
+  'test/helpers/gemini-session-runner.ts',
   'test/helpers/eval-store.ts',
   'test/helpers/llm-judge.ts',
   'scripts/gen-skill-docs.ts',