Marc Mintel 1cc367697e test: add 55-test LLM perception pipeline integrity suite ...

Validates the deterministic processing logic around the VLM without
needing a real LLM. Five contracts covering the full perception stack:

1. VLM Response Parsing (20 parametrized formats):
   Tests _parse_yes_no against every response format observed in production:
   clean YES/NO, JSON variants, explanations, edge cases (now/not/nothing),
   empty strings, free-form JSON. Documents the startswith('yes') early-exit
   behavior for ambiguous responses.

2. Box Index Extraction (7 formats):
   Validates JSON parsing of VLM box selections across all observed key
   variants: 'box', 'selected_index', 'box_index', 'index', null, and
   out-of-range values.

3. Structural Guards (11 tests):
   Tests every hallucination prevention guard in IntentResolver:
   - Tab intent excludes Back button (bug 2026-04-30)
   - Back intent preserves Back button
   - Tab height guard (y > 85% screen)
   - Author intent excludes nav tabs (bug 2026-05-01)
   - Structural fast-paths (message input, send, author, comment)
   - Abstract goals return None
   - Semantic quoted-target guard

4. Semantic Match Validation (10 tests):
   Prevents memory poisoning via _intent_matches_node:
   - Correct matches (follow/like/save + German locale)
   - Poisoning attempts: Reel thumbnails, photo content, comments
   - Non-toggle intents always pass through

5. ActionMemory Lifecycle (7 tests):
   Full track → confirm/reject cycle with FakeUIMemoryDB:
   - Correct follow stores in memory
   - Poisoned follow is BLOCKED (production bug reproduction)
   - Rejected click triggers confidence decay
   - No-track confirm is noop
   - Mismatched intent is ignored
   - Follow/view-post structural verification

2026-05-02 22:07:12 +02:00

..

fixtures

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

__init__.py

init

2026-04-16 18:58:18 +02:00

conftest.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

device_emulator.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

dump_legend.py

🧪 PURGE: All residual mocks and spies from E2E suite. 100% production-parity enforcement.

2026-04-28 17:53:47 +02:00

test_behavior_ad_guard.py

Hardened E2E integrity, purged synthetic mocks, and implemented proactive device discovery.

2026-04-29 15:42:03 +02:00

test_behavior_scrape_profile.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_behavior_story_view.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_brain_live.py

fix: eliminate thinking-block poisoning + no-op navigation trap

2026-04-29 00:06:23 +02:00

test_e2e_dm_engine.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_engine_perception.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_engine_timeout.py

fix: prevent SessionStateEncoder crash from non-serializable datetime on args

2026-05-02 19:57:33 +02:00

test_follow_verification_integrity.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_goal_decomposer_e2e.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_goal_executor_achieve.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_goap_hallucination_guards.py

test(e2e): decompose monolithic test suite and fortify semantic guards

2026-04-28 23:09:15 +02:00

test_goap_loop_prevention.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_nav_engagement.py

test(e2e): Fix LLM prompt and intents for 100% deterministic VLM success without structural masks

2026-04-29 01:39:10 +02:00

test_nav_home_feed.py

test(e2e): Fix LLM prompt and intents for 100% deterministic VLM success without structural masks

2026-04-29 01:39:10 +02:00

test_nav_messaging.py

test(e2e): decompose monolithic test suite and fortify semantic guards

2026-04-28 23:09:15 +02:00

test_nav_profile.py

test(e2e): decompose monolithic test suite and fortify semantic guards

2026-04-28 23:09:15 +02:00

test_nav_reels.py

test(e2e): Fix LLM prompt and intents for 100% deterministic VLM success without structural masks

2026-04-29 01:39:10 +02:00

test_nav_search_explore.py

fix(perception): enforce strict candidate filtering for grid items

2026-04-29 00:55:59 +02:00

test_production_bug_foreign_app_20260501.py

test: enforce real VLM execution in explore tab guard and disable fallback hallucination

2026-05-01 23:41:51 +02:00

test_system_coverage_gate.py

test: add E2E coverage gate and full lifecycle integration test

2026-05-02 21:56:19 +02:00

test_system_full_lifecycle.py

test: add E2E coverage gate and full lifecycle integration test

2026-05-02 21:56:19 +02:00

test_system_integrity_contracts.py

test: add proactive system integrity contracts

2026-05-02 20:15:35 +02:00

test_system_llm_perception.py

test: add 55-test LLM perception pipeline integrity suite

2026-05-02 22:07:12 +02:00

test_visual_intent_resolver.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_account_switch.py

fix(intent_resolver): add Nav Conflict Guard — Back button never valid for tab intents

2026-04-30 12:10:44 +02:00

test_workflow_dm_inbox.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_explore_feed.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_foreign_app.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_instagram_modal.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_locked_screen.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_normal_feed.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_permission_dialog.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_plugin_integrity.py

refactor(e2e): extract workflow infrastructure into conftest, one test file per workflow

2026-04-30 11:20:35 +02:00

test_workflow_post_detail.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_profiles.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_reels_feed.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_same_post_loop.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_search_feed.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_stories_feed.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_stuck_other_profile.py

test: finalize E2E timeout verification and purge global state leaks

2026-05-02 18:59:35 +02:00

test_workflow_vlm_tab_confusion.py

fix(intent_resolver): add Nav Conflict Guard — Back button never valid for tab intents

2026-04-30 12:10:44 +02:00