holetron-lab/fleet-memory
1
0
Fork 0
Code Releases Packages Activity Actions
fleet-memory/hindsight-api/tests
History
Chris Bartholomew 49ae55af03
Switch Vertex AI provider to native genai SDK (#242) 
Replace the OpenAI-compatible endpoint approach with the native
google-genai SDK for Vertex AI. This eliminates the custom token
refresher, TokenInjectingTransport, and async lifecycle complexity
while also removing the 8192 output token cap that the OpenAI
endpoint enforced.

Changes:
- vertexai provider now uses genai.Client(vertexai=True) instead of
  AsyncOpenAI with token-injecting transport
- Routes through existing _call_gemini/_call_with_tools_gemini paths
- Strips google/ prefix from model names (native SDK uses bare names)
- Preserves service account key auth via credentials parameter
- Delete vertexai_token_refresher.py (no longer needed)
- Strip markdown code fences in consolidator JSON parsing
- Rewrite vertexai tests for native SDK integration
2026-01-30 08:35:59 +01:00
..
fixtures rename to hindsight (#2) 2025-11-25 19:28:26 +01:00
__init__.py rename to hindsight (#2) 2025-11-25 19:28:26 +01:00
conftest.py fix: improve pytorch model initialization to prevent meta tensor issues (#180) 2026-01-20 14:15:51 +01:00
test_admin_backup_restore.py feat: run db migrations offline (optionally) (#114) 2026-01-07 15:49:51 +01:00
test_agents_api.py feat: introduce mental models (#132) 2026-01-16 11:16:41 +01:00
test_batch_chunking.py feat: extensions (#54) 2025-12-22 11:05:23 +01:00
test_causal_relations.py fix: duplicated causal relationships and token optimization (#126) 2026-01-08 14:43:48 +01:00
test_causal_relationships.py fix: duplicated causal relationships and token optimization (#126) 2026-01-08 14:43:48 +01:00
test_chunking.py improve retain performances, caching and tests 2025-12-08 18:21:56 +01:00
test_combined_scoring.py feat: extensions (#54) 2025-12-22 11:05:23 +01:00
test_consolidation.py fix: graph endpoint not showing links for observations (#214) 2026-01-28 14:51:25 +01:00
test_custom_embedding_dimension.py fix: improve mental model consolidation (#197) 2026-01-26 09:54:25 +01:00
test_document_tracking.py feat: extensions (#54) 2025-12-22 11:05:23 +01:00
test_extensions.py fix: improve mental model consolidation (#197) 2026-01-26 09:54:25 +01:00
test_fact_extraction_analysis.py fix: misc perf improvements (#133) 2026-01-08 22:49:04 +01:00
test_fact_extraction_output_ratio.py fix: misc perf improvements (#133) 2026-01-08 22:49:04 +01:00
test_fact_extraction_quality.py feat: introduce mental models (#132) 2026-01-16 11:16:41 +01:00
test_fact_ordering.py feat: introduce mental models (#132) 2026-01-16 11:16:41 +01:00
test_http_api_integration.py fix: /version endpoint return wrong version (#224) 2026-01-29 08:40:01 +01:00
test_link_expansion_retrieval.py fix: misc fixes for observations and mental models (#209) 2026-01-27 15:37:57 +01:00
test_link_utils.py prepare for release 2025-12-03 11:52:25 +01:00
test_llm_provider.py fix: ollama structured support (#63) 2025-12-22 16:35:24 +01:00
test_llm_token_metrics.py feat: add metrics for llm call latency (#120) 2026-01-08 11:40:34 +01:00
test_llm_tools.py chore: internal renames (#204) 2026-01-27 09:53:28 +01:00
test_load_large_batch.py feat: new 'worker' service (#176) 2026-01-20 10:17:56 +01:00
test_main_module.py fix: improve mental model consolidation (#197) 2026-01-26 09:54:25 +01:00
test_mcp_local.py feat(mcp): add timestamp to retain (#190) 2026-01-23 16:00:43 +01:00
test_mcp_routing.py fix(mcp): add back bank list and create_bank tools (#123) 2026-01-08 14:02:28 +01:00
test_mcp_tools.py feat(mcp): add timestamp to retain (#190) 2026-01-23 16:00:43 +01:00
test_mental_models.py feat: revisit mental models, directives and reflections (#179) 2026-01-22 17:13:16 +01:00
test_metrics.py misc: performance improvements (#140) 2026-01-09 14:47:20 +01:00
test_mpfp_retrieval.py fix: improve mpfp retrieval (#146) 2026-01-12 18:58:05 +01:00
test_multilingual.py fix: sometimes memories gets extracted in the wrong language (#184) 2026-01-22 14:21:59 +01:00
test_observations.py chore: cleanup benchmarks runner with old flags (#212) 2026-01-28 13:22:48 +01:00
test_per_operation_llm_config.py feat: add more config options for llm retries (#234) 2026-01-29 17:50:43 +01:00
test_query_analyzer.py fix: ci and ui build (#9) 2025-12-03 15:47:53 +01:00
test_reflect_agent.py fix: graph endpoint not showing links for observations (#214) 2026-01-28 14:51:25 +01:00
test_reflections.py fix: misc fixes for observations and mental models (#209) 2026-01-27 15:37:57 +01:00
test_retain.py feat: add custom extraction prompt (#213) 2026-01-28 13:54:52 +01:00
test_schema_isolation.py fix: improve mental model consolidation (#197) 2026-01-26 09:54:25 +01:00
test_search_trace.py feat: extensions (#54) 2025-12-22 11:05:23 +01:00
test_server_module.py fix: improve mental model consolidation (#197) 2026-01-26 09:54:25 +01:00
test_sql_schema_safety.py chore: internal renames (#204) 2026-01-27 09:53:28 +01:00
test_tags_visibility.py chore: cleanup benchmarks runner with old flags (#212) 2026-01-28 13:22:48 +01:00
test_tei_cross_encoder.py fix: add defensive error handling to PyTorch device detection (#221) 2026-01-28 18:14:54 +01:00
test_temporal_ranges.py feat(mcp): add timestamp to retain (#190) 2026-01-23 16:00:43 +01:00
test_think.py feat: extensions (#54) 2025-12-22 11:05:23 +01:00
test_vertexai_provider.py Switch Vertex AI provider to native genai SDK (#242) 2026-01-30 08:35:59 +01:00
test_worker.py fix: improve mental model consolidation (#197) 2026-01-26 09:54:25 +01:00