fleet-memory/hindsight-api-slim/tests
Nicolò Boschi 28dac7c7f8
fix: prevent silent memory loss on consolidation LLM failure (#601)
* fix: prevent silent memory loss on consolidation LLM failure

When all LLM retries are exhausted during consolidation, memories were
being marked consolidated_at unconditionally, permanently excluding them
from future consolidation runs without producing any observations.

Fix with two complementary mechanisms:
- Adaptive batch splitting: on LLM failure, the batch is halved and
  retried recursively down to batch_size=1, recovering most transient
  failures (rate limits, Pydantic validation on long prompts) without
  operator intervention
- consolidation_failed_at column: only single-memory batches that still
  fail after all retries are marked here instead of consolidated_at, so
  they remain visible and retryable
- New API endpoint POST /v1/default/banks/{bank_id}/consolidation/retry-failed
  resets these memories for the next consolidation run

* chore: regenerate OpenAPI spec

* fix: rename consolidation endpoint from /retry-failed to /recover

* fix: add consolidation_failed_at column, adaptive batch splitting, and recovery API

- Migration a3b4c5d6e7f8: add consolidation_failed_at TIMESTAMPTZ column to
  memory_units with an index for efficient failure queries; properly chains off
  g7h8i9j0k1l2 (backsweep_orphan_observations)
- Consolidator: filter pending memories with consolidation_failed_at IS NULL
  so failed memories are not re-fetched in an infinite loop
- Consolidator: adaptive batch splitting — when a batch exhausts all 3 LLM
  retries, halve it and retry sub-batches recursively; only single-memory
  batches that also exhaust all retries get consolidation_failed_at set
- New tests (9 total) covering: adaptive splitting recovers all memories,
  larger batch splitting, single-memory permanent failure, exclusion from
  next run, partial batch failure, recover resets columns, recover returns
  0 when none failed, recover-then-consolidate succeeds, HTTP endpoint

* chore: regenerate Go, Python, TypeScript clients with recover consolidation endpoint

* feat: add Recover Consolidation action to bank Actions dropdown

* style: apply ruff formatting to http.py and config.py

* fix: handle consolidation scope in large batch test mock LLM

The mock LLM was returning {"facts": ...} for ALL calls including consolidation.
Consolidation doesn't use skip_validation=True so it expects a _ConsolidationBatchResponse
instance, not a raw dict. Before this PR consolidation silently swallowed the AttributeError
(failed=False was returned); now failed=True triggers adaptive splitting and timeouts.

Fix: return _ConsolidationBatchResponse() when scope=="consolidation".

* fix: restrict claude-agent-sdk to macOS platform only (no Linux wheel available)

Also fix pre-existing type errors: use setattr for XLM-RoBERTa monkey-patch
and add missing reranker_local_fp16/bucket_batching/batch_size fields to main.py config constructor.

* fix: add UV_INDEX_STRATEGY=unsafe-best-match to fix markupsafe cp314 wheel conflict

PyTorch CPU index serves markupsafe==3.0.3 with only cp314 wheels.
uv's default first-index strategy stops at the first index with any version
even if no compatible wheel exists. unsafe-best-match searches all indices
for the best compatible wheel, falling back to PyPI for markupsafe.

* fix: use explicit pytorch index to prevent markupsafe wheel conflict

Configure the pytorch CPU index as explicit=true in pyproject.toml so it is
ONLY used for torch (via [tool.uv.sources]). All other packages (including
markupsafe) are resolved exclusively from PyPI, preventing the pytorch index
from serving incompatible cp314-only wheels for non-pytorch packages.

Remove UV_INDEX and UV_INDEX_STRATEGY from CI workflow (no longer needed
since the index is now configured in pyproject.toml).

* ci: trigger CI run

* ci: retry trigger

* ci: trigger after remote URL fix

* ci: add workflow_dispatch to unblock manual trigger

* fix: remove empty env blocks left after UV_INDEX removal

* fix: add type: ignore for optional claude_agent_sdk imports (macOS-only)

* fix: correct type: ignore rules for claude_agent_sdk and fix utcnow deprecation
2026-03-17 20:15:33 +01:00
..
fixtures feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
__init__.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
conftest.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_admin_backup_restore.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_agents_api.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_async_batch_retain.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_async_retain_tags.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_base_path.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_batch_api.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_batch_api_integration.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_batch_api_validation.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_batch_chunking.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_causal_relations.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_causal_relationships.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_chunking.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_combined_scoring.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_config_validation.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_consolidation.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_consolidation_failure_recovery.py fix: prevent silent memory loss on consolidation LLM failure (#601) 2026-03-17 20:15:33 +01:00
test_custom_embedding_dimension.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_document_tracking.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_entity_labels.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_extensions.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_fact_extraction_analysis.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_fact_extraction_metadata.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_fact_extraction_output_ratio.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_fact_extraction_quality.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_fact_extraction_retry.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_fact_ordering.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_file_retain.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_file_storage_s3.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_gemini_safety_settings.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_graph_filtering.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_hierarchical_config.py feat(retain): verbatim, chunks modes and named retain strategies (#593) 2026-03-17 18:08:25 +01:00
test_hnsw_indexes.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_http_api_integration.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_iris_parser.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_link_expansion_retrieval.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_link_utils.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_list_documents.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_litellm_sdk_cross_encoder.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_litellm_sdk_embeddings.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_llm_provider.py fix: support gemini-3.1-flash-lite-preview by preserving thought_signature in tool calls (#568) 2026-03-13 16:43:01 +01:00
test_llm_token_metrics.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_llm_tools.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_llm_wrapper.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_lmstudio_tool_choice.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_load_large_batch.py fix: prevent silent memory loss on consolidation LLM failure (#601) 2026-03-17 20:15:33 +01:00
test_main_module.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_mcp_endpoint_routing.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_mcp_extension.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_mcp_routing.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_mcp_tools.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_mental_model_hooks.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_mental_models.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_metrics.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_migration_backsweep.py fix(migration): backsweep orphaned observation memory units (#584) 2026-03-16 14:06:33 +01:00
test_migrations_thread_safety.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_mpfp_retrieval.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_multilingual.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_observation_invalidation.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_observations.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_op_cancellation.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_per_operation_llm_config.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_provider_default_models.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_query_analyzer.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_recall_chunks_independence.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_reflect_agent.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_reflect_empty_based_on.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_reflect_tracing.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_reflections.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_reranker_error_handling.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_retain.py feat(retain): verbatim, chunks modes and named retain strategies (#593) 2026-03-17 18:08:25 +01:00
test_schema_isolation.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_search_trace.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_server_module.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_source_facts_tokens.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_sql_schema_safety.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_supabase_tenant.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_tags_visibility.py feat: compound tag filtering via tag_groups (#562) 2026-03-13 14:30:11 +01:00
test_tei_cross_encoder.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_temporal_ranges.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_think.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_tracing.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_tracing_integration.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_tracing_spans_verification.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_vertexai_provider.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_webhooks.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
test_worker.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00