Files
life-helper/app/test/data/ai/gemma_llm_service_test.dart
joungmin 9a9eb2abd5 [Developer] #218 Real Gemma 4 E2B integration via flutter_gemma 0.16.5
Implements the OQ-1 follow-up to #215 v0.2.0: replace the placeholder
GemmaLlmService stub with a real flutter_gemma 0.16.5 backend driving
Gemma 4 E2B (litert-community/gemma-4-E2B-it-litert-lm, 2.41GB).

Highlights:
- GemmaLlmService.load → FlutterGemma.initialize + installModel.fromFile +
  getActiveModel; idempotent + FileSystemException on missing file.
- generateStructured uses Gemma 4 native function calling via
  createChat(tools: [Tool(...)], toolChoice: required). Stream parsed by
  collectFunctionCall — first FCR wins, ParallelFCR first-call wins,
  TextResponse/ThinkingResponse skipped, errors sanitized to prevent
  prompt leakage.
- main.dart wires _LazyLlmService adapter that resolves to GemmaLlmService
  when ModelLifecycle reports ready, MockLlmService otherwise.
- ai_providers.dart pins real model URL + SHA-256 (181938...39a63c).
- F2 hardening: ModelLifecycle.purge wraps each delete + meta remove in
  try/catch so a single OS-level flake cannot block opt-out.
- Android: INTERNET / FOREGROUND_SERVICE / POST_NOTIFICATIONS permissions
  + R8 proguard-rules.pro keeping MediaPipe / LiteRT / TFLite / protobuf
  JNI entry points (release builds otherwise crash on first inference).

Design-First: fn-gemma_llm_service.md updated to v2 — §C
(_appendSchemaInstruction) deprecated after reading flutter_gemma
0.16.5 source (Gemma 4 SDK injects tool declarations via template;
prompt-side append would double-wrap).

Tests:
- 10 new unit tests for collectFunctionCall covering all 8 fn-spec
  cases + 2 ParallelFunctionCallResponse paths.
- All 81 existing tests still pass.
- flutter analyze: 0 issues.

Refs #218

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-06-12 15:18:08 +09:00

151 lines
4.6 KiB
Dart

import 'dart:async';
import 'package:flutter_gemma/flutter_gemma.dart';
import 'package:flutter_test/flutter_test.dart';
import 'package:life_helper/data/ai/gemma_llm_service.dart';
/// Unit tests for `collectFunctionCall` (fn-spec §D, 8 cases).
///
/// `GemmaLlmService.load` / `.generateStructured` themselves require the
/// flutter_gemma native runtime and are covered by AC-7 (on-device E2E),
/// not by host tests. The pure stream-parsing helper is unit-testable in
/// isolation because we can feed a synthetic `Stream<ModelResponse>`.
void main() {
const fn = 'emit_frame_candidates';
test('1. single FCR with expected name returns args', () async {
final stream = Stream<ModelResponse>.fromIterable([
const FunctionCallResponse(
name: fn,
args: {
'candidates': [
{'text': 'a', 'level': 'L2'},
{'text': 'b', 'level': 'L2'},
{'text': 'c', 'level': 'L3'},
],
},
),
]);
final args = await collectFunctionCall(stream, fn);
expect(args['candidates'], hasLength(3));
});
test('2. TextResponse before FCR is skipped', () async {
final stream = Stream<ModelResponse>.fromIterable([
const TextResponse('hello'),
const FunctionCallResponse(name: fn, args: {'candidates': []}),
]);
final args = await collectFunctionCall(stream, fn);
expect(args['candidates'], isEmpty);
});
test('3. ThinkingResponse + TextResponse before empty-args FCR', () async {
final stream = Stream<ModelResponse>.fromIterable([
const ThinkingResponse('reasoning...'),
const TextResponse('preamble'),
const FunctionCallResponse(name: fn, args: {}),
]);
final args = await collectFunctionCall(stream, fn);
expect(args, isEmpty);
});
test('4. wrong function name throws FormatException', () async {
final stream = Stream<ModelResponse>.fromIterable([
const FunctionCallResponse(name: 'wrong_name', args: {}),
]);
expect(
() => collectFunctionCall(stream, fn),
throwsA(
isA<FormatException>().having(
(e) => e.message,
'message',
contains('wrong_name'),
),
),
);
});
test('5. text-only stream throws "no function call emitted"', () async {
final stream = Stream<ModelResponse>.fromIterable([
const TextResponse('only text, no call'),
]);
expect(
() => collectFunctionCall(stream, fn),
throwsA(
isA<FormatException>().having(
(e) => e.message,
'message',
contains('no function call emitted'),
),
),
);
});
test('6. stream error throws sanitized FormatException (no leak)', () async {
final stream = Stream<ModelResponse>.error(
Exception('SENSITIVE: user_prompt_leaked_in_error'),
);
expect(
() => collectFunctionCall(stream, fn),
throwsA(
isA<FormatException>().having(
(e) => e.message,
'message',
allOf(
equals('stream error'),
isNot(contains('SENSITIVE')),
isNot(contains('user_prompt_leaked_in_error')),
),
),
),
);
});
test('7. FCR with empty args map returns empty map (no throw)', () async {
final stream = Stream<ModelResponse>.fromIterable([
const FunctionCallResponse(name: fn, args: {}),
]);
final args = await collectFunctionCall(stream, fn);
expect(args, isEmpty);
});
test('8. empty stream throws "no function call emitted"', () async {
final stream = const Stream<ModelResponse>.empty();
expect(
() => collectFunctionCall(stream, fn),
throwsA(
isA<FormatException>().having(
(e) => e.message,
'message',
contains('no function call emitted'),
),
),
);
});
group('ParallelFunctionCallResponse', () {
test('first call with expected name returns its args', () async {
final stream = Stream<ModelResponse>.fromIterable([
ParallelFunctionCallResponse(calls: [
const FunctionCallResponse(name: fn, args: {'x': 1}),
const FunctionCallResponse(name: 'other', args: {'y': 2}),
]),
]);
final args = await collectFunctionCall(stream, fn);
expect(args['x'], 1);
});
test('first call with wrong name throws', () async {
final stream = Stream<ModelResponse>.fromIterable([
ParallelFunctionCallResponse(calls: [
const FunctionCallResponse(name: 'wrong_first', args: {}),
]),
]);
expect(
() => collectFunctionCall(stream, fn),
throwsA(isA<FormatException>()),
);
});
});
}