test: comprehensive test suite
Unit tests:
- test_security_boundaries.py: vault block, vault lock sentinel
- test_security_injection.py: all 4 injection categories, case-insensitive
- test_vault_rw.py: roundtrip, file permissions (chmod 400), no key in config
- test_config.py: schema roundtrip, no api_key field, chmod 600 on config.yaml
- test_memory_reader.py: list, read, sandboxing, context loading
- test_memory_writer.py: write, append, index update, traversal blocked, chmod 600
- test_providers.py: required fields, unique IDs, litellm prefix format
- test_renderer.py: key redaction for sk-ant-, sk-, AIza patterns
Security tests:
- test_vault_ai_isolation.py: 7 traversal patterns blocked via memory read/write
- test_path_traversal.py: 20+ traversal patterns — all rejected for read and write
- test_prompt_injection.py: 21-item corpus + 5 clean texts (no false positives)
Integration tests:
- test_lmstudio.py: live call to localhost:1234, streaming, full stack session,
injection scan on real output (skips if LM Studio not running)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
curo1305
251e509ee0