feat: support litellm-sdk for reranker endpoint

.github/workflows/test.yml

@@ -941,11 +941,30 @@ jobs:
           sleep 1
         done
 
+    - name: Run Python doc examples
+      working-directory: ./hindsight-clients/python
+      run: |
+        for f in ../../hindsight-docs/examples/api/*.py; do
+          echo "Running $f..."
+          uv run python "$f"
+        done
+
+    - name: Run Node.js doc examples
+      run: |
+        for f in hindsight-docs/examples/api/*.mjs; do
+          echo "Running $f..."
+          node "$f"
+        done
+
     - name: Configure CLI
       run: hindsight configure --api-url http://localhost:8888
 
-    - name: Run all doc examples
-      run: ./scripts/test-doc-examples.sh
+    - name: Run CLI doc examples
+      run: |
+        for f in hindsight-docs/examples/api/*.sh; do
+          echo "Running $f..."
+          bash "$f"
+        done
 
     - name: Show API server logs
       if: always()

.gitignore

@@ -46,7 +46,6 @@ hindsight-docs/static/llms-full.txt
 hindsight-dev/benchmarks/locomo/results/
 hindsight-dev/benchmarks/longmemeval/results/
 hindsight-dev/benchmarks/consolidation/results/
-hindsight-dev/benchmarks/perf/results/
 benchmarks/results/
 hindsight-cli/target
 hindsight-clients/rust/target

CLAUDE.md

@@ -57,15 +57,8 @@ cd hindsight-control-plane && npm run dev
 
 ### Benchmarks
 ```bash
-# Accuracy benchmarks
 ./scripts/benchmarks/run-longmemeval.sh
 ./scripts/benchmarks/run-locomo.sh
-
-# Performance benchmarks
-./scripts/benchmarks/run-consolidation.sh
-./scripts/benchmarks/run-retain-perf.sh --document <path>  # Requires API server running
-
-# Results viewer
 ./scripts/benchmarks/start-visualizer.sh  # View results at localhost:8001
 ```
 

docker/docker-compose/pg_textsearch/Dockerfile

@@ -1,32 +0,0 @@
-# PostgreSQL with pgvector and pg_textsearch extensions
-# Note: pg_textsearch requires PostgreSQL 17+
-FROM postgres:17
-
-# Install build dependencies
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    git \
-    postgresql-server-dev-17 \
-    libpq-dev \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install pgvector
-RUN cd /tmp && \
-    git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git && \
-    cd pgvector && \
-    make && \
-    make install
-
-# Install pg_textsearch
-RUN cd /tmp && \
-    git clone https://github.com/timescale/pg_textsearch.git && \
-    cd pg_textsearch && \
-    make && \
-    make install
-
-# Clean up source files and build dependencies
-RUN rm -rf /tmp/pgvector /tmp/pg_textsearch && \
-    apt-get purge -y --auto-remove build-essential git postgresql-server-dev-17
-
-# Ensure extensions are preloaded
-RUN echo "shared_preload_libraries = 'pg_textsearch'" >> /usr/share/postgresql/postgresql.conf.sample

docker/docker-compose/pg_textsearch/docker-compose.yaml

@@ -1,91 +0,0 @@
-name: hindsight
-# Docker Compose file for Hindsight with PostgreSQL and Timescale pg_textsearch
-# docker compose -f docker/docker-compose/pg_textsearch/docker-compose.yaml down && sleep 2 && docker compose -f docker/docker-compose/pg_textsearch/docker-compose.yaml up -d
-# Make sure to set the required environment variables before running:
-# - HINDSIGHT_DB_PASSWORD: Password for the PostgreSQL user
-# - Configure LLM provider variables as needed (see below in the hindsight service)
-#
-# Usage:
-# docker compose up -d
-#
-# Optional environment variables with defaults:
-# - HINDSIGHT_VERSION: Hindsight application version (default: latest)
-# - HINDSIGHT_DB_USER: PostgreSQL user (default: hindsight_user)
-# - HINDSIGHT_DB_NAME: PostgreSQL database name (default: hindsight_db)
-
-services:
-  db:
-    # Use custom PostgreSQL image with pgvector and pg_textsearch extensions
-    build:
-      context: .
-      dockerfile: Dockerfile
-    container_name: hindsight-db
-    restart: always
-    # Expose PostgreSQL port
-    ports:
-      - "5437:5432"
-    environment:
-      POSTGRES_USER: ${HINDSIGHT_DB_USER:-hindsight_user}
-      POSTGRES_PASSWORD: ${HINDSIGHT_DB_PASSWORD:-hindsight_password}
-      POSTGRES_DB: ${HINDSIGHT_DB_NAME:-hindsight_db}
-    volumes:
-      - pg_data:/var/lib/postgresql/data
-    networks:
-      - hindsight-net
-
-  pg-textsearch-init:
-    build:
-      context: .
-      dockerfile: Dockerfile
-    depends_on:
-      - db
-    environment:
-      - PGPASSWORD=${HINDSIGHT_DB_PASSWORD:-hindsight_password}
-    command: >
-      bash -c "
-        echo 'Waiting for PostgreSQL to be ready...';
-        until pg_isready -h hindsight-db -p 5432 -U hindsight_user; do
-          echo 'PostgreSQL is unavailable - sleeping';
-          sleep 2;
-        done;
-        echo 'PostgreSQL is ready - creating hindsight_db database';
-        psql -h hindsight-db -p 5432 -U hindsight_user -c 'CREATE DATABASE hindsight_db;' 2>/dev/null || echo 'Database already exists';
-        echo 'Creating extensions in hindsight_db database';
-        psql -h hindsight-db -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS vector CASCADE;';
-        psql -h hindsight-db -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS pg_textsearch CASCADE;';
-        echo 'Database and extensions created successfully';
-      "
-    restart: "no"
-    networks:
-      - hindsight-net
-
-  hindsight:
-    image: ghcr.io/vectorize-io/hindsight:${HINDSIGHT_VERSION:-latest}
-    container_name: hindsight-app
-    ports:
-      - "8888:8888"
-      - "9999:9999"
-    environment:
-      # LLM Configuration
-      HINDSIGHT_API_LLM_PROVIDER: ${HINDSIGHT_API_LLM_PROVIDER:-openai}
-      HINDSIGHT_API_LLM_API_KEY: ${OPENAI_API_KEY:-your-api-key}
-
-      # Database Configuration
-      HINDSIGHT_API_DATABASE_URL: postgresql://${HINDSIGHT_DB_USER:-hindsight_user}:${HINDSIGHT_DB_PASSWORD:-hindsight_password}@db:5432/${HINDSIGHT_DB_NAME:-hindsight_db}
-
-      # Vector and Text Search Extensions
-      HINDSIGHT_API_VECTOR_EXTENSION: pgvector
-      HINDSIGHT_API_TEXT_SEARCH_EXTENSION: pg_textsearch
-
-    depends_on:
-      - db
-    networks:
-      - hindsight-net
-
-
-networks:
-  hindsight-net:
-    driver: bridge
-
-volumes:
-  pg_data:

helm/hindsight/Chart.yaml

@@ -2,8 +2,8 @@ apiVersion: v2
 name: hindsight
 description: Hindsight helm chart
 type: application
-version: 0.4.11
-appVersion: "0.4.11"
+version: 0.4.10
+appVersion: "0.4.10"
 keywords:
   - ai
   - memory

hindsight-api/hindsight_api/__init__.py

@@ -46,4 +46,4 @@ __all__ = [
     "RemoteTEICrossEncoder",
     "LLMConfig",
 ]
-__version__ = "0.4.11"
+__version__ = "0.4.10"

hindsight-api/hindsight_api/alembic/versions/5a366d414dce_initial_schema.py

@@ -51,7 +51,7 @@ def _detect_vector_extension() -> str:
 
 def _detect_text_search_extension() -> str:
     """
-    Detect or validate text search extension: 'native', 'vchord', or 'pg_textsearch'.
+    Detect or validate text search extension: 'native' or 'vchord'.
     Respects HINDSIGHT_API_TEXT_SEARCH_EXTENSION env var.
     Creates the extension if needed.
     """
@@ -69,23 +69,11 @@ def _detect_text_search_extension() -> str:
                 # Extension truly doesn't exist - re-raise the error
                 raise
         return "vchord"
-    elif text_search_extension == "pg_textsearch":
-        # Create pg_textsearch extension if not exists
-        try:
-            op.execute("CREATE EXTENSION IF NOT EXISTS pg_textsearch CASCADE")
-        except Exception:
-            # Extension might already exist or user lacks permissions - verify it exists
-            conn = op.get_bind()
-            result = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'pg_textsearch'")).fetchone()
-            if not result:
-                # Extension truly doesn't exist - re-raise the error
-                raise
-        return "pg_textsearch"
     elif text_search_extension == "native":
         return "native"
     else:
         raise ValueError(
-            f"Invalid HINDSIGHT_API_TEXT_SEARCH_EXTENSION: {text_search_extension}. Must be 'native', 'vchord', or 'pg_textsearch'"
+            f"Invalid HINDSIGHT_API_TEXT_SEARCH_EXTENSION: {text_search_extension}. Must be 'native' or 'vchord'"
         )
 
 
@@ -244,12 +232,6 @@ def upgrade() -> None:
             ALTER TABLE memory_units
             ADD COLUMN search_vector bm25_catalog.bm25vector
         """)
-    elif text_search_ext == "pg_textsearch":
-        # Timescale pg_textsearch: dummy TEXT column for consistency (indexes operate on base columns directly)
-        op.execute("""
-            ALTER TABLE memory_units
-            ADD COLUMN search_vector TEXT
-        """)
     else:  # native
         # Native PostgreSQL: tsvector with automatic generation
         op.execute("""
@@ -313,14 +295,6 @@ def upgrade() -> None:
             CREATE INDEX idx_memory_units_text_search ON memory_units
             USING bm25 (search_vector bm25_catalog.bm25_ops)
         """)
-    elif text_search_ext == "pg_textsearch":
-        # Timescale pg_textsearch BM25 index on text column
-        # Note: pg_textsearch doesn't support expressions, so we index the main text column
-        op.execute("""
-            CREATE INDEX idx_memory_units_text_search ON memory_units
-            USING bm25(text)
-            WITH (text_config='english')
-        """)
     else:  # native
         # Native PostgreSQL GIN index
         op.execute("""

hindsight-api/hindsight_api/alembic/versions/n9i0j1k2l3m4_learnings_and_pinned_reflections.py

@@ -58,7 +58,7 @@ def _detect_vector_extension() -> str:
 
 def _detect_text_search_extension() -> str:
     """
-    Detect or validate text search extension: 'native', 'vchord', or 'pg_textsearch'.
+    Detect or validate text search extension: 'native' or 'vchord'.
     Respects HINDSIGHT_API_TEXT_SEARCH_EXTENSION env var.
     Creates the extension if needed.
     """
@@ -76,23 +76,11 @@ def _detect_text_search_extension() -> str:
                 # Extension truly doesn't exist - re-raise the error
                 raise
         return "vchord"
-    elif text_search_extension == "pg_textsearch":
-        # Create pg_textsearch extension if not exists
-        try:
-            op.execute("CREATE EXTENSION IF NOT EXISTS pg_textsearch CASCADE")
-        except Exception:
-            # Extension might already exist or user lacks permissions - verify it exists
-            conn = op.get_bind()
-            result = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'pg_textsearch'")).fetchone()
-            if not result:
-                # Extension truly doesn't exist - re-raise the error
-                raise
-        return "pg_textsearch"
     elif text_search_extension == "native":
         return "native"
     else:
         raise ValueError(
-            f"Invalid HINDSIGHT_API_TEXT_SEARCH_EXTENSION: {text_search_extension}. Must be 'native', 'vchord', or 'pg_textsearch'"
+            f"Invalid HINDSIGHT_API_TEXT_SEARCH_EXTENSION: {text_search_extension}. Must be 'native' or 'vchord'"
         )
 
 
@@ -158,15 +146,6 @@ def upgrade() -> None:
             CREATE INDEX idx_learnings_text_search ON {schema}learnings
             USING bm25 (search_vector bm25_catalog.bm25_ops)
         """)
-    elif text_search_ext == "pg_textsearch":
-        # Timescale pg_textsearch: dummy TEXT column for consistency (indexes operate on base columns directly)
-        op.execute(f"""
-            ALTER TABLE {schema}learnings ADD COLUMN search_vector TEXT
-        """)
-        op.execute(f"""
-            CREATE INDEX idx_learnings_text_search ON {schema}learnings
-            USING bm25(text) WITH (text_config='english')
-        """)
     else:  # native
         # Native PostgreSQL: tsvector with automatic generation
         op.execute(f"""
@@ -225,16 +204,6 @@ def upgrade() -> None:
             CREATE INDEX idx_pinned_reflections_text_search ON {schema}pinned_reflections
             USING bm25 (search_vector bm25_catalog.bm25_ops)
         """)
-    elif text_search_ext == "pg_textsearch":
-        # Timescale pg_textsearch: dummy TEXT column for consistency (indexes operate on base columns directly)
-        op.execute(f"""
-            ALTER TABLE {schema}pinned_reflections ADD COLUMN search_vector TEXT
-        """)
-        op.execute(f"""
-            CREATE INDEX idx_pinned_reflections_text_search ON {schema}pinned_reflections
-            USING bm25(content)
-            WITH (text_config='english')
-        """)
     else:  # native
         # Native PostgreSQL: tsvector with automatic generation
         op.execute(f"""

hindsight-api/hindsight_api/alembic/versions/y0t1u2v3w4x5_add_result_metadata_gin_index.py

@@ -1,49 +0,0 @@
-"""Add GIN index on async_operations.result_metadata for parent_operation_id queries
-
-Revision ID: y0t1u2v3w4x5
-Revises: x9s0t1u2v3w4
-Create Date: 2026-02-13
-
-This migration adds a GIN index on the result_metadata JSONB column in the
-async_operations table to support efficient queries for child operations by
-parent_operation_id.
-
-The index enables fast lookups when querying for child operations:
-  SELECT * FROM async_operations
-  WHERE result_metadata::jsonb @> '{"parent_operation_id": "uuid"}'::jsonb
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "y0t1u2v3w4x5"
-down_revision: str | Sequence[str] | None = "x9s0t1u2v3w4"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    """Get schema prefix for table names (required for multi-tenant support)."""
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    """Add GIN index on result_metadata for efficient parent_operation_id queries."""
-    schema = _get_schema_prefix()
-
-    # Add GIN index for JSONB containment queries (@> operator)
-    op.execute(f"""
-        CREATE INDEX idx_async_operations_result_metadata
-        ON {schema}async_operations
-        USING gin(result_metadata)
-    """)
-
-
-def downgrade() -> None:
-    """Remove GIN index on result_metadata."""
-    schema = _get_schema_prefix()
-
-    # Drop index
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_async_operations_result_metadata")

hindsight-api/hindsight_api/api/http.py

@@ -1357,16 +1357,6 @@ class CancelOperationResponse(BaseModel):
     operation_id: str
 
 
-class ChildOperationStatus(BaseModel):
-    """Status of a child operation (for batch operations)."""
-
-    operation_id: str
-    status: str
-    sub_batch_index: int | None = None
-    items_count: int | None = None
-    error_message: str | None = None
-
-
 class OperationStatusResponse(BaseModel):
     """Response model for getting a single operation status."""
 
@@ -1391,13 +1381,6 @@ class OperationStatusResponse(BaseModel):
     updated_at: str | None = None
     completed_at: str | None = None
     error_message: str | None = None
-    result_metadata: dict[str, Any] | None = Field(
-        default=None,
-        description="Internal metadata for debugging. Structure may change without notice. Not for production use.",
-    )
-    child_operations: list[ChildOperationStatus] | None = Field(
-        default=None, description="Child operations for batch operations (if applicable)"
-    )
 
 
 class AsyncOperationSubmitResponse(BaseModel):

hindsight-api/hindsight_api/config.py

@@ -189,14 +189,6 @@ ENV_RERANKER_LITELLM_API_BASE = "HINDSIGHT_API_RERANKER_LITELLM_API_BASE"
 ENV_RERANKER_LITELLM_API_KEY = "HINDSIGHT_API_RERANKER_LITELLM_API_KEY"
 ENV_RERANKER_LITELLM_MODEL = "HINDSIGHT_API_RERANKER_LITELLM_MODEL"
 
-# LiteLLM SDK configuration (direct API access, no proxy needed)
-ENV_EMBEDDINGS_LITELLM_SDK_API_KEY = "HINDSIGHT_API_EMBEDDINGS_LITELLM_SDK_API_KEY"
-ENV_EMBEDDINGS_LITELLM_SDK_MODEL = "HINDSIGHT_API_EMBEDDINGS_LITELLM_SDK_MODEL"
-ENV_EMBEDDINGS_LITELLM_SDK_API_BASE = "HINDSIGHT_API_EMBEDDINGS_LITELLM_SDK_API_BASE"
-ENV_RERANKER_LITELLM_SDK_API_KEY = "HINDSIGHT_API_RERANKER_LITELLM_SDK_API_KEY"
-ENV_RERANKER_LITELLM_SDK_MODEL = "HINDSIGHT_API_RERANKER_LITELLM_SDK_MODEL"
-ENV_RERANKER_LITELLM_SDK_API_BASE = "HINDSIGHT_API_RERANKER_LITELLM_SDK_API_BASE"
-
 # Deprecated: Legacy shared LiteLLM config (for backward compatibility)
 ENV_LITELLM_API_BASE = "HINDSIGHT_API_LITELLM_API_BASE"
 ENV_LITELLM_API_KEY = "HINDSIGHT_API_LITELLM_API_KEY"
@@ -250,7 +242,6 @@ ENV_RETAIN_CHUNK_SIZE = "HINDSIGHT_API_RETAIN_CHUNK_SIZE"
 ENV_RETAIN_EXTRACT_CAUSAL_LINKS = "HINDSIGHT_API_RETAIN_EXTRACT_CAUSAL_LINKS"
 ENV_RETAIN_EXTRACTION_MODE = "HINDSIGHT_API_RETAIN_EXTRACTION_MODE"
 ENV_RETAIN_CUSTOM_INSTRUCTIONS = "HINDSIGHT_API_RETAIN_CUSTOM_INSTRUCTIONS"
-ENV_RETAIN_BATCH_TOKENS = "HINDSIGHT_API_RETAIN_BATCH_TOKENS"
 
 # Observations settings (consolidated knowledge from facts)
 ENV_ENABLE_OBSERVATIONS = "HINDSIGHT_API_ENABLE_OBSERVATIONS"
@@ -338,18 +329,14 @@ DEFAULT_RERANKER_COHERE_MODEL = "rerank-english-v3.0"
 # Vector extension (pgvector vs vchord)
 DEFAULT_VECTOR_EXTENSION = "pgvector"  # Options: "pgvector", "vchord"
 
-# Text search extension (native PostgreSQL, vchord BM25, or Timescale pg_textsearch)
-DEFAULT_TEXT_SEARCH_EXTENSION = "native"  # Options: "native", "vchord", "pg_textsearch"
+# Text search extension (native PostgreSQL vs vchord BM25)
+DEFAULT_TEXT_SEARCH_EXTENSION = "native"  # Options: "native", "vchord"
 
 # LiteLLM defaults
 DEFAULT_LITELLM_API_BASE = "http://localhost:4000"
 DEFAULT_EMBEDDINGS_LITELLM_MODEL = "text-embedding-3-small"
 DEFAULT_RERANKER_LITELLM_MODEL = "cohere/rerank-english-v3.0"
 
-# LiteLLM SDK defaults
-DEFAULT_EMBEDDINGS_LITELLM_SDK_MODEL = "cohere/embed-english-v3.0"
-DEFAULT_RERANKER_LITELLM_SDK_MODEL = "cohere/rerank-english-v3.0"
-
 DEFAULT_HOST = "0.0.0.0"
 DEFAULT_PORT = 8888
 DEFAULT_BASE_PATH = ""  # Empty string = root path
@@ -372,7 +359,6 @@ DEFAULT_RETAIN_EXTRACT_CAUSAL_LINKS = True  # Extract causal links between facts
 DEFAULT_RETAIN_EXTRACTION_MODE = "concise"  # Extraction mode: "concise", "verbose", or "custom"
 RETAIN_EXTRACTION_MODES = ("concise", "verbose", "custom")  # Allowed extraction modes
 DEFAULT_RETAIN_CUSTOM_INSTRUCTIONS = None  # Custom extraction guidelines (only used when mode="custom")
-DEFAULT_RETAIN_BATCH_TOKENS = 10_000  # ~40KB of text  # Max chars per sub-batch for async retain auto-splitting
 
 # Observations defaults (consolidated knowledge from facts)
 DEFAULT_ENABLE_OBSERVATIONS = True  # Observations enabled by default
@@ -546,9 +532,6 @@ class HindsightConfig:
     embeddings_litellm_api_base: str
     embeddings_litellm_api_key: str | None
     embeddings_litellm_model: str
-    embeddings_litellm_sdk_api_key: str | None
-    embeddings_litellm_sdk_model: str
-    embeddings_litellm_sdk_api_base: str | None
 
     # Reranker
     reranker_provider: str
@@ -566,9 +549,6 @@ class HindsightConfig:
     reranker_litellm_api_base: str
     reranker_litellm_api_key: str | None
     reranker_litellm_model: str
-    reranker_litellm_sdk_api_key: str | None
-    reranker_litellm_sdk_model: str
-    reranker_litellm_sdk_api_base: str | None
 
     # Server
     host: str
@@ -592,7 +572,6 @@ class HindsightConfig:
     retain_extract_causal_links: bool
     retain_extraction_mode: str
     retain_custom_instructions: str | None
-    retain_batch_tokens: int
 
     # Observations settings (consolidated knowledge from facts)
     enable_observations: bool
@@ -727,7 +706,7 @@ class HindsightConfig:
             )
 
         # Validate text_search_extension
-        valid_text_search = ("native", "vchord", "pg_textsearch")
+        valid_text_search = ("native", "vchord")
         if self.text_search_extension not in valid_text_search:
             raise ValueError(
                 f"Invalid text_search_extension: {self.text_search_extension}. Must be one of: {', '.join(valid_text_search)}"
@@ -868,12 +847,6 @@ class HindsightConfig:
             or os.getenv(ENV_LITELLM_API_BASE, DEFAULT_LITELLM_API_BASE),
             embeddings_litellm_api_key=os.getenv(ENV_EMBEDDINGS_LITELLM_API_KEY) or os.getenv(ENV_LITELLM_API_KEY),
             embeddings_litellm_model=os.getenv(ENV_EMBEDDINGS_LITELLM_MODEL, DEFAULT_EMBEDDINGS_LITELLM_MODEL),
-            # LiteLLM SDK embeddings (direct API access)
-            embeddings_litellm_sdk_api_key=os.getenv(ENV_EMBEDDINGS_LITELLM_SDK_API_KEY),
-            embeddings_litellm_sdk_model=os.getenv(
-                ENV_EMBEDDINGS_LITELLM_SDK_MODEL, DEFAULT_EMBEDDINGS_LITELLM_SDK_MODEL
-            ),
-            embeddings_litellm_sdk_api_base=os.getenv(ENV_EMBEDDINGS_LITELLM_SDK_API_BASE) or None,
             # Reranker
             reranker_provider=os.getenv(ENV_RERANKER_PROVIDER, DEFAULT_RERANKER_PROVIDER),
             reranker_local_model=os.getenv(ENV_RERANKER_LOCAL_MODEL, DEFAULT_RERANKER_LOCAL_MODEL),
@@ -903,10 +876,6 @@ class HindsightConfig:
             or os.getenv(ENV_LITELLM_API_BASE, DEFAULT_LITELLM_API_BASE),
             reranker_litellm_api_key=os.getenv(ENV_RERANKER_LITELLM_API_KEY) or os.getenv(ENV_LITELLM_API_KEY),
             reranker_litellm_model=os.getenv(ENV_RERANKER_LITELLM_MODEL, DEFAULT_RERANKER_LITELLM_MODEL),
-            # LiteLLM SDK reranker (direct API access)
-            reranker_litellm_sdk_api_key=os.getenv(ENV_RERANKER_LITELLM_SDK_API_KEY),
-            reranker_litellm_sdk_model=os.getenv(ENV_RERANKER_LITELLM_SDK_MODEL, DEFAULT_RERANKER_LITELLM_SDK_MODEL),
-            reranker_litellm_sdk_api_base=os.getenv(ENV_RERANKER_LITELLM_SDK_API_BASE) or None,
             # Server
             host=os.getenv(ENV_HOST, DEFAULT_HOST),
             port=int(os.getenv(ENV_PORT, DEFAULT_PORT)),
@@ -942,7 +911,6 @@ class HindsightConfig:
                 os.getenv(ENV_RETAIN_EXTRACTION_MODE, DEFAULT_RETAIN_EXTRACTION_MODE)
             ),
             retain_custom_instructions=os.getenv(ENV_RETAIN_CUSTOM_INSTRUCTIONS) or DEFAULT_RETAIN_CUSTOM_INSTRUCTIONS,
-            retain_batch_tokens=int(os.getenv(ENV_RETAIN_BATCH_TOKENS, str(DEFAULT_RETAIN_BATCH_TOKENS))),
             # Observations settings (consolidated knowledge from facts)
             enable_observations=os.getenv(ENV_ENABLE_OBSERVATIONS, str(DEFAULT_ENABLE_OBSERVATIONS)).lower() == "true",
             consolidation_batch_size=int(

hindsight-api/hindsight_api/engine/consolidation/consolidator.py

@@ -1030,9 +1030,8 @@ async def _create_observation_directly(
                     tokenize($3, 'llmlingua2')::bm25_catalog.bm25vector)
             RETURNING id
         """
-    else:  # native or pg_textsearch
+    else:  # native
         # Native PostgreSQL: search_vector is GENERATED ALWAYS, don't include it
-        # pg_textsearch: indexes operate on base columns directly, don't populate search_vector
         query = f"""
             INSERT INTO {fq_table("memory_units")} (
                 id, bank_id, text, fact_type, embedding, proof_count, source_memory_ids, history,

hindsight-api/hindsight_api/engine/cross_encoder.py

@@ -21,7 +21,6 @@ from ..config import (
     DEFAULT_RERANKER_FLASHRANK_CACHE_DIR,
     DEFAULT_RERANKER_FLASHRANK_MODEL,
     DEFAULT_RERANKER_LITELLM_MODEL,
-    DEFAULT_RERANKER_LITELLM_SDK_MODEL,
     DEFAULT_RERANKER_LOCAL_FORCE_CPU,
     DEFAULT_RERANKER_LOCAL_MAX_CONCURRENT,
     DEFAULT_RERANKER_LOCAL_MODEL,
@@ -33,7 +32,6 @@ from ..config import (
     ENV_RERANKER_COHERE_MODEL,
     ENV_RERANKER_FLASHRANK_CACHE_DIR,
     ENV_RERANKER_FLASHRANK_MODEL,
-    ENV_RERANKER_LITELLM_SDK_API_KEY,
     ENV_RERANKER_LOCAL_FORCE_CPU,
     ENV_RERANKER_LOCAL_MAX_CONCURRENT,
     ENV_RERANKER_LOCAL_MODEL,
@@ -830,126 +828,6 @@ class LiteLLMCrossEncoder(CrossEncoderModel):
         return all_scores
 
 
-class LiteLLMSDKCrossEncoder(CrossEncoderModel):
-    """
-    LiteLLM SDK cross-encoder for direct API integration.
-
-    Supports reranking via LiteLLM SDK without requiring a proxy server.
-    Supported providers: Cohere, DeepInfra, Together AI, HuggingFace, Jina AI, Voyage AI, AWS Bedrock.
-
-    Example model names:
-    - cohere/rerank-english-v3.0
-    - deepinfra/Qwen3-reranker-8B
-    - together_ai/Salesforce/Llama-Rank-V1
-    - huggingface/BAAI/bge-reranker-v2-m3
-    """
-
-    def __init__(
-        self,
-        api_key: str,
-        model: str = DEFAULT_RERANKER_LITELLM_SDK_MODEL,
-        api_base: str | None = None,
-        timeout: float = 60.0,
-    ):
-        """
-        Initialize LiteLLM SDK cross-encoder client.
-
-        Args:
-            api_key: API key for the reranking provider
-            model: Model name with provider prefix (e.g., "deepinfra/Qwen3-reranker-8B")
-            api_base: Custom base URL for API (optional)
-            timeout: Request timeout in seconds (default: 60.0)
-        """
-        self.api_key = api_key
-        self.model = model
-        self.api_base = api_base
-        self.timeout = timeout
-        self._initialized = False
-        self._litellm = None  # Will be set during initialization
-
-    @property
-    def provider_name(self) -> str:
-        return "litellm-sdk"
-
-    async def initialize(self) -> None:
-        """Initialize the LiteLLM SDK client."""
-        if self._initialized:
-            return
-
-        try:
-            import litellm
-
-            self._litellm = litellm  # Store reference
-        except ImportError:
-            raise ImportError("litellm is required for LiteLLMSDKCrossEncoder. Install it with: pip install litellm")
-
-        api_base_msg = f" at {self.api_base}" if self.api_base else ""
-        logger.info(f"Reranker: initializing LiteLLM SDK provider with model {self.model}{api_base_msg}")
-
-        self._initialized = True
-        logger.info("Reranker: LiteLLM SDK provider initialized")
-
-    async def predict(self, pairs: list[tuple[str, str]]) -> list[float]:
-        """
-        Score query-document pairs using the LiteLLM SDK.
-
-        Args:
-            pairs: List of (query, document) tuples to score
-
-        Returns:
-            List of relevance scores
-        """
-        if not self._initialized:
-            raise RuntimeError("Reranker not initialized. Call initialize() first.")
-
-        if not pairs:
-            return []
-
-        # Group pairs by query for efficient batching
-        # LiteLLM rerank expects one query with multiple documents
-        query_groups: dict[str, list[tuple[int, str]]] = {}
-        for idx, (query, text) in enumerate(pairs):
-            if query not in query_groups:
-                query_groups[query] = []
-            query_groups[query].append((idx, text))
-
-        all_scores = [0.0] * len(pairs)
-
-        for query, indexed_texts in query_groups.items():
-            texts = [text for _, text in indexed_texts]
-            indices = [idx for idx, _ in indexed_texts]
-
-            # Build kwargs for rerank call
-            rerank_kwargs = {
-                "model": self.model,
-                "query": query,
-                "documents": texts,
-                "api_key": self.api_key,
-            }
-            if self.api_base:
-                rerank_kwargs["api_base"] = self.api_base
-
-            response = await self._litellm.arerank(**rerank_kwargs)
-
-            # Map scores back to original positions
-            # Response format: RerankResponse with results list
-            # Each result is a TypedDict with "index" and "relevance_score"
-            if hasattr(response, "results") and response.results:
-                for result in response.results:
-                    # Results are TypedDicts, use dict-style access
-                    original_idx = result["index"]
-                    score = result.get("relevance_score", result.get("score", 0.0))
-                    all_scores[indices[original_idx]] = score
-            elif isinstance(response, list):
-                # Direct list of scores (unlikely but defensive)
-                for i, score in enumerate(response):
-                    all_scores[indices[i]] = score
-            else:
-                logger.warning(f"Unexpected response format from LiteLLM rerank: {type(response)}")
-
-        return all_scores
-
-
 def create_cross_encoder_from_env() -> CrossEncoderModel:
     """
     Create a CrossEncoderModel instance based on configuration.
@@ -999,20 +877,9 @@ def create_cross_encoder_from_env() -> CrossEncoderModel:
             api_key=config.reranker_litellm_api_key,
             model=config.reranker_litellm_model,
         )
-    elif provider == "litellm-sdk":
-        api_key = config.reranker_litellm_sdk_api_key
-        if not api_key:
-            raise ValueError(
-                f"{ENV_RERANKER_LITELLM_SDK_API_KEY} is required when {ENV_RERANKER_PROVIDER} is 'litellm-sdk'"
-            )
-        return LiteLLMSDKCrossEncoder(
-            api_key=api_key,
-            model=config.reranker_litellm_sdk_model,
-            api_base=config.reranker_litellm_sdk_api_base,
-        )
     elif provider == "rrf":
         return RRFPassthroughCrossEncoder()
     else:
         raise ValueError(
-            f"Unknown reranker provider: {provider}. Supported: 'local', 'tei', 'cohere', 'flashrank', 'litellm', 'litellm-sdk', 'rrf'"
+            f"Unknown reranker provider: {provider}. Supported: 'local', 'tei', 'cohere', 'flashrank', 'litellm', 'rrf'"
         )

hindsight-api/hindsight_api/engine/embeddings.py

@@ -19,7 +19,6 @@ import httpx
 from ..config import (
     DEFAULT_EMBEDDINGS_COHERE_MODEL,
     DEFAULT_EMBEDDINGS_LITELLM_MODEL,
-    DEFAULT_EMBEDDINGS_LITELLM_SDK_MODEL,
     DEFAULT_EMBEDDINGS_LOCAL_FORCE_CPU,
     DEFAULT_EMBEDDINGS_LOCAL_MODEL,
     DEFAULT_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE,
@@ -27,7 +26,6 @@ from ..config import (
     DEFAULT_EMBEDDINGS_PROVIDER,
     DEFAULT_LITELLM_API_BASE,
     ENV_EMBEDDINGS_COHERE_API_KEY,
-    ENV_EMBEDDINGS_LITELLM_SDK_API_KEY,
     ENV_EMBEDDINGS_LOCAL_FORCE_CPU,
     ENV_EMBEDDINGS_LOCAL_MODEL,
     ENV_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE,
@@ -722,148 +720,6 @@ class LiteLLMEmbeddings(Embeddings):
         return all_embeddings
 
 
-class LiteLLMSDKEmbeddings(Embeddings):
-    """
-    LiteLLM SDK embeddings for direct API integration.
-
-    Supports embeddings via LiteLLM SDK without requiring a proxy server.
-    Supported providers: Cohere, OpenAI, Azure OpenAI, HuggingFace, Voyage AI, Together AI, etc.
-
-    Example model names:
-    - cohere/embed-english-v3.0
-    - openai/text-embedding-3-small
-    - together_ai/togethercomputer/m2-bert-80M-8k-retrieval
-    - voyage/voyage-2
-    """
-
-    def __init__(
-        self,
-        api_key: str,
-        model: str = DEFAULT_EMBEDDINGS_LITELLM_SDK_MODEL,
-        api_base: str | None = None,
-        batch_size: int = 100,
-        timeout: float = 60.0,
-    ):
-        """
-        Initialize LiteLLM SDK embeddings client.
-
-        Args:
-            api_key: API key for the embedding provider
-            model: Model name with provider prefix (e.g., "cohere/embed-english-v3.0")
-            api_base: Custom base URL for API (optional)
-            batch_size: Maximum batch size for embedding requests (default: 100)
-            timeout: Request timeout in seconds (default: 60.0)
-        """
-        self.api_key = api_key
-        self.model = model
-        self.api_base = api_base
-        self.batch_size = batch_size
-        self.timeout = timeout
-        self._litellm = None  # Will be set during initialization
-        self._dimension: int | None = None
-
-    @property
-    def provider_name(self) -> str:
-        return "litellm-sdk"
-
-    @property
-    def dimension(self) -> int:
-        if self._dimension is None:
-            raise RuntimeError("Embeddings not initialized. Call initialize() first.")
-        return self._dimension
-
-    async def initialize(self) -> None:
-        """Initialize the LiteLLM SDK client and detect dimension."""
-        if self._litellm is not None:
-            return
-
-        try:
-            import litellm
-
-            self._litellm = litellm  # Store reference
-        except ImportError:
-            raise ImportError("litellm is required for LiteLLMSDKEmbeddings. Install it with: pip install litellm")
-
-        api_base_msg = f" at {self.api_base}" if self.api_base else ""
-        logger.info(f"Embeddings: initializing LiteLLM SDK provider with model {self.model}{api_base_msg}")
-
-        # Do a test embedding to detect dimension
-        try:
-            # Build kwargs for embedding call
-            embed_kwargs = {
-                "model": self.model,
-                "input": ["test"],
-                "api_key": self.api_key,
-            }
-            if self.api_base:
-                embed_kwargs["api_base"] = self.api_base
-
-            # Use async embedding method (standard in litellm)
-            response = await self._litellm.aembedding(**embed_kwargs)
-
-            # Extract dimension from response
-            if response.data and len(response.data) > 0:
-                self._dimension = len(response.data[0]["embedding"])
-            else:
-                raise RuntimeError(f"Unable to detect embedding dimension for model {self.model}")
-
-        except Exception as e:
-            raise RuntimeError(f"Failed to initialize LiteLLM SDK embeddings: {e}")
-
-        logger.info(f"Embeddings: LiteLLM SDK provider initialized (model: {self.model}, dim: {self._dimension})")
-
-    def encode(self, texts: list[str]) -> list[list[float]]:
-        """
-        Generate embeddings using the LiteLLM SDK.
-
-        Args:
-            texts: List of text strings to encode
-
-        Returns:
-            List of embedding vectors (one per input text)
-        """
-        if self._litellm is None:
-            raise RuntimeError("Embeddings not initialized. Call initialize() first.")
-
-        if not texts:
-            return []
-
-        all_embeddings = []
-
-        # Process in batches
-        for i in range(0, len(texts), self.batch_size):
-            batch = texts[i : i + self.batch_size]
-
-            try:
-                # Build kwargs for embedding call
-                embed_kwargs = {
-                    "model": self.model,
-                    "input": batch,
-                    "api_key": self.api_key,
-                }
-                if self.api_base:
-                    embed_kwargs["api_base"] = self.api_base
-
-                # Use sync embedding (litellm doesn't have async in thread-safe way)
-                response = self._litellm.embedding(**embed_kwargs)
-
-                # Extract embeddings from response
-                # Sort by index to ensure correct order
-                batch_embeddings = sorted(response.data, key=lambda x: x.get("index", 0))
-                all_embeddings.extend([e["embedding"] for e in batch_embeddings])
-
-            except Exception as e:
-                import traceback
-
-                logger.error(
-                    f"Error in LiteLLM embedding for batch starting at index {i}: {e}\n"
-                    f"Traceback: {traceback.format_exc()}"
-                )
-                raise
-
-        return all_embeddings
-
-
 def create_embeddings_from_env() -> Embeddings:
     """
     Create an Embeddings instance based on configuration.
@@ -915,19 +771,7 @@ def create_embeddings_from_env() -> Embeddings:
             api_key=config.embeddings_litellm_api_key,
             model=config.embeddings_litellm_model,
         )
-    elif provider == "litellm-sdk":
-        api_key = config.embeddings_litellm_sdk_api_key
-        if not api_key:
-            raise ValueError(
-                f"{ENV_EMBEDDINGS_LITELLM_SDK_API_KEY} is required when {ENV_EMBEDDINGS_PROVIDER} is 'litellm-sdk'"
-            )
-        return LiteLLMSDKEmbeddings(
-            api_key=api_key,
-            model=config.embeddings_litellm_sdk_model,
-            api_base=config.embeddings_litellm_sdk_api_base,
-        )
     else:
         raise ValueError(
-            f"Unknown embeddings provider: {provider}. "
-            f"Supported: 'local', 'tei', 'openai', 'cohere', 'litellm', 'litellm-sdk'"
+            f"Unknown embeddings provider: {provider}. Supported: 'local', 'tei', 'openai', 'cohere', 'litellm'"
         )

hindsight-api/hindsight_api/engine/interface.py

@@ -48,7 +48,6 @@ class MemoryEngineInterface(ABC):
         contents: list[dict[str, Any]],
         *,
         request_context: "RequestContext",
-        document_tags: list[str] | None = None,
     ) -> dict[str, Any]:
         """
         Retain a batch of memory items.
@@ -56,9 +55,8 @@ class MemoryEngineInterface(ABC):
         Args:
             bank_id: The memory bank ID.
             contents: List of content dicts with 'content', optional 'event_date',
-                     'context', 'metadata', 'document_id', and per-item 'tags'.
+                     'context', 'metadata', 'document_id'.
             request_context: Request context for authentication.
-            document_tags: Optional tags applied to all items in the batch.
 
         Returns:
             Dict with processing results.
@@ -563,7 +561,6 @@ class MemoryEngineInterface(ABC):
         contents: list[dict[str, Any]],
         *,
         request_context: "RequestContext",
-        document_tags: list[str] | None = None,
     ) -> dict[str, Any]:
         """
         Submit a batch retain operation to run asynchronously.
@@ -572,7 +569,6 @@ class MemoryEngineInterface(ABC):
             bank_id: The memory bank ID.
             contents: List of content dicts to retain.
             request_context: Request context for authentication.
-            document_tags: Optional tags applied to all items in the async batch.
 
         Returns:
             Dict with operation_id and items_count.

hindsight-api/hindsight_api/engine/memory_engine.py

@@ -18,20 +18,11 @@ import uuid
 from datetime import UTC, datetime, timedelta
 from typing import TYPE_CHECKING, Any
 
-import tiktoken
-
 from ..config import get_config
 from ..metrics import get_metrics_collector
 from ..tracing import create_operation_span
 from ..utils import mask_network_location
 from .db_budget import budgeted_operation
-from .operation_metadata import (
-    BatchRetainChildMetadata,
-    BatchRetainParentMetadata,
-    ConsolidationMetadata,
-    RefreshMentalModelMetadata,
-    RetainMetadata,
-)
 
 # Context variable for current schema (async-safe, per-task isolation)
 # Note: default is None, actual default comes from config via get_current_schema()
@@ -47,15 +38,6 @@ def get_current_schema() -> str:
     return schema
 
 
-# Initialize tiktoken encoder once at module level for efficiency
-_tiktoken_encoder = tiktoken.get_encoding("cl100k_base")  # GPT-4/GPT-3.5-turbo encoding
-
-
-def count_tokens(text: str) -> int:
-    """Count tokens in text using tiktoken (cl100k_base encoding for GPT-4/3.5)."""
-    return len(_tiktoken_encoder.encode(text))
-
-
 def fq_table(table_name: str) -> str:
     """
     Get fully-qualified table name with current schema.
@@ -558,7 +540,6 @@ class MemoryEngine(MemoryEngineInterface):
         if not bank_id:
             raise ValueError("bank_id is required for batch retain task")
         contents = task_dict.get("contents", [])
-        document_tags = task_dict.get("document_tags")
 
         logger.info(
             f"[BATCH_RETAIN_TASK] Starting background batch retain for bank_id={bank_id}, {len(contents)} items"
@@ -576,12 +557,7 @@ class MemoryEngine(MemoryEngineInterface):
             tenant_id=task_dict.get("_tenant_id"),
             api_key_id=task_dict.get("_api_key_id"),
         )
-        await self.retain_batch_async(
-            bank_id=bank_id,
-            contents=contents,
-            document_tags=document_tags,
-            request_context=context,
-        )
+        await self.retain_batch_async(bank_id=bank_id, contents=contents, request_context=context)
 
         logger.info(f"[BATCH_RETAIN_TASK] Completed background batch retain for bank_id={bank_id}")
 
@@ -844,11 +820,7 @@ class MemoryEngine(MemoryEngineInterface):
             logger.error(f"Failed to delete async operation record {operation_id}: {e}")
 
     async def _mark_operation_failed(self, operation_id: str, error_message: str, error_traceback: str):
-        """Helper to mark an operation as failed in the database.
-
-        Also checks if this is a child operation and updates the parent if all siblings are done.
-        Uses a single transaction to avoid race conditions when multiple children fail simultaneously.
-        """
+        """Helper to mark an operation as failed in the database."""
         try:
             pool = await self._get_pool()
             # Truncate error message to avoid extremely long strings
@@ -856,160 +828,36 @@ class MemoryEngine(MemoryEngineInterface):
             truncated_error = full_error[:5000] if len(full_error) > 5000 else full_error
 
             async with acquire_with_retry(pool) as conn:
-                async with conn.transaction():
-                    # Mark this operation as failed
-                    await conn.execute(
-                        f"""
-                        UPDATE {fq_table("async_operations")}
-                        SET status = 'failed', error_message = $2, updated_at = NOW()
-                        WHERE operation_id = $1
-                        """,
-                        uuid.UUID(operation_id),
-                        truncated_error,
-                    )
-                    logger.info(f"Marked async operation as failed: {operation_id}")
-
-                    # Check if this is a child operation and update parent if all siblings are done
-                    # This happens in the same transaction after the child status is updated
-                    await self._maybe_update_parent_operation(operation_id, conn)
+                await conn.execute(
+                    f"""
+                    UPDATE {fq_table("async_operations")}
+                    SET status = 'failed', error_message = $2, updated_at = NOW()
+                    WHERE operation_id = $1
+                    """,
+                    uuid.UUID(operation_id),
+                    truncated_error,
+                )
+            logger.info(f"Marked async operation as failed: {operation_id}")
         except Exception as e:
             logger.error(f"Failed to mark operation as failed {operation_id}: {e}")
 
     async def _mark_operation_completed(self, operation_id: str):
-        """Helper to mark an operation as completed in the database.
-
-        Also checks if this is a child operation and updates the parent if all siblings are done.
-        Uses a single transaction to avoid race conditions when multiple children complete simultaneously.
-        """
+        """Helper to mark an operation as completed in the database."""
         try:
             pool = await self._get_pool()
             async with acquire_with_retry(pool) as conn:
-                async with conn.transaction():
-                    # Mark this operation as completed
-                    await conn.execute(
-                        f"""
-                        UPDATE {fq_table("async_operations")}
-                        SET status = 'completed', updated_at = NOW(), completed_at = NOW()
-                        WHERE operation_id = $1
-                        """,
-                        uuid.UUID(operation_id),
-                    )
-                    logger.info(f"Marked async operation as completed: {operation_id}")
-
-                    # Check if this is a child operation and update parent if all siblings are done
-                    # This happens in the same transaction after the child status is updated
-                    await self._maybe_update_parent_operation(operation_id, conn)
+                await conn.execute(
+                    f"""
+                    UPDATE {fq_table("async_operations")}
+                    SET status = 'completed', updated_at = NOW(), completed_at = NOW()
+                    WHERE operation_id = $1
+                    """,
+                    uuid.UUID(operation_id),
+                )
+            logger.info(f"Marked async operation as completed: {operation_id}")
         except Exception as e:
             logger.error(f"Failed to mark operation as completed {operation_id}: {e}")
 
-    async def _maybe_update_parent_operation(self, child_operation_id: str, conn):
-        """Check if this is a child operation and update parent status if all siblings are done.
-
-        Must be called within an active transaction that has already updated the child's status.
-        Uses SELECT FOR UPDATE to lock the parent and prevent race conditions.
-
-        Args:
-            child_operation_id: The operation ID that just completed or failed
-            conn: Database connection with an active transaction
-        """
-        try:
-            # Get this operation's metadata to check if it has a parent
-            row = await conn.fetchrow(
-                f"""
-                SELECT result_metadata, bank_id
-                FROM {fq_table("async_operations")}
-                WHERE operation_id = $1
-                """,
-                uuid.UUID(child_operation_id),
-            )
-
-            if not row:
-                return
-
-            result_metadata = json.loads(row["result_metadata"]) if row["result_metadata"] else {}
-            parent_operation_id = result_metadata.get("parent_operation_id")
-
-            if not parent_operation_id:
-                # Not a child operation
-                return
-
-            bank_id = row["bank_id"]
-
-            # Lock the parent operation to prevent concurrent updates from other children
-            # Use FOR UPDATE to ensure only one child can update the parent at a time
-            parent_row = await conn.fetchrow(
-                f"""
-                SELECT operation_id
-                FROM {fq_table("async_operations")}
-                WHERE operation_id = $1 AND bank_id = $2
-                FOR UPDATE
-                """,
-                uuid.UUID(parent_operation_id),
-                bank_id,
-            )
-
-            if not parent_row:
-                # Parent doesn't exist (shouldn't happen)
-                return
-
-            # Get all sibling operations (including this one)
-            # This query runs in the same transaction, so it sees the current child's updated status
-            siblings = await conn.fetch(
-                f"""
-                SELECT status
-                FROM {fq_table("async_operations")}
-                WHERE bank_id = $1
-                AND result_metadata::jsonb @> $2::jsonb
-                """,
-                bank_id,
-                json.dumps({"parent_operation_id": parent_operation_id}),
-            )
-
-            if not siblings:
-                return
-
-            # Check if all siblings are done (completed or failed)
-            all_completed = all(sib["status"] == "completed" for sib in siblings)
-            any_failed = any(sib["status"] == "failed" for sib in siblings)
-            all_done = all(sib["status"] in ("completed", "failed") for sib in siblings)
-
-            if not all_done:
-                # Some siblings still pending/processing
-                return
-
-            # All siblings are done - update parent status
-            if any_failed:
-                new_status = "failed"
-                # Set parent error message to indicate child failure
-                await conn.execute(
-                    f"""
-                    UPDATE {fq_table("async_operations")}
-                    SET status = $2, error_message = $3, updated_at = NOW()
-                    WHERE operation_id = $1
-                    """,
-                    uuid.UUID(parent_operation_id),
-                    new_status,
-                    "One or more sub-batches failed",
-                )
-            elif all_completed:
-                new_status = "completed"
-                await conn.execute(
-                    f"""
-                    UPDATE {fq_table("async_operations")}
-                    SET status = $2, updated_at = NOW(), completed_at = NOW()
-                    WHERE operation_id = $1
-                    """,
-                    uuid.UUID(parent_operation_id),
-                    new_status,
-                )
-
-            logger.info(f"Updated parent operation {parent_operation_id} to status '{new_status}' (all children done)")
-
-        except Exception as e:
-            logger.error(f"Failed to update parent operation for child {child_operation_id}: {e}")
-            # Re-raise to rollback the transaction
-            raise
-
     async def initialize(self):
         """Initialize the connection pool, models, and background workers.
 
@@ -1576,49 +1424,35 @@ class MemoryEngine(MemoryEngineInterface):
                 if "document_id" not in item:
                     item["document_id"] = document_id
 
-        # Validate no duplicate document_ids in the batch
-        # Having duplicate document_ids causes race conditions in document upserts during parallel processing
-        doc_ids = [item.get("document_id") for item in contents if item.get("document_id")]
-        if len(doc_ids) != len(set(doc_ids)):
-            from collections import Counter
-
-            duplicates = [doc_id for doc_id, count in Counter(doc_ids).items() if count > 1]
-            raise ValueError(
-                f"Batch contains duplicate document_ids: {duplicates}. "
-                f"Each content item in a batch must have a unique document_id to avoid race conditions."
-            )
-
-        # Auto-chunk large batches by token count to avoid timeouts and memory issues
-        # Calculate total token count
-        total_tokens = sum(count_tokens(item.get("content", "")) for item in contents)
+        # Auto-chunk large batches by character count to avoid timeouts and memory issues
+        # Calculate total character count
+        total_chars = sum(len(item.get("content", "")) for item in contents)
         total_usage = TokenUsage()
 
-        # Get batch size threshold from config
-        config = get_config()
-        tokens_per_batch = config.retain_batch_tokens
+        CHARS_PER_BATCH = 600_000
 
-        if total_tokens > tokens_per_batch:
-            # Split into smaller batches based on token count
+        if total_chars > CHARS_PER_BATCH:
+            # Split into smaller batches based on character count
             logger.info(
-                f"Large batch detected ({total_tokens:,} tokens from {len(contents)} items). Splitting into sub-batches of ~{tokens_per_batch:,} tokens each..."
+                f"Large batch detected ({total_chars:,} chars from {len(contents)} items). Splitting into sub-batches of ~{CHARS_PER_BATCH:,} chars each..."
             )
 
             sub_batches = []
             current_batch = []
-            current_batch_tokens = 0
+            current_batch_chars = 0
 
             for item in contents:
-                item_tokens = count_tokens(item.get("content", ""))
+                item_chars = len(item.get("content", ""))
 
                 # If adding this item would exceed the limit, start a new batch
                 # (unless current batch is empty - then we must include it even if it's large)
-                if current_batch and current_batch_tokens + item_tokens > tokens_per_batch:
+                if current_batch and current_batch_chars + item_chars > CHARS_PER_BATCH:
                     sub_batches.append(current_batch)
                     current_batch = [item]
-                    current_batch_tokens = item_tokens
+                    current_batch_chars = item_chars
                 else:
                     current_batch.append(item)
-                    current_batch_tokens += item_tokens
+                    current_batch_chars += item_chars
 
             # Add the last batch
             if current_batch:
@@ -1629,9 +1463,9 @@ class MemoryEngine(MemoryEngineInterface):
             # Process each sub-batch
             all_results = []
             for i, sub_batch in enumerate(sub_batches, 1):
-                sub_batch_tokens = sum(count_tokens(item.get("content", "")) for item in sub_batch)
+                sub_batch_chars = sum(len(item.get("content", "")) for item in sub_batch)
                 logger.info(
-                    f"Processing sub-batch {i}/{len(sub_batches)}: {len(sub_batch)} items, {sub_batch_tokens:,} tokens"
+                    f"Processing sub-batch {i}/{len(sub_batches)}: {len(sub_batch)} items, {sub_batch_chars:,} chars"
                 )
 
                 sub_results, sub_usage = await self._retain_batch_async_internal(
@@ -1848,21 +1682,15 @@ class MemoryEngine(MemoryEngineInterface):
             max_entity_tokens: Maximum tokens for entity observations (default 500)
             include_chunks: Whether to include raw chunks in the response
             max_chunk_tokens: Maximum tokens for chunks (default 8192)
-                             NOTE: Chunks are fetched independently of max_tokens filtering.
-                             This means setting max_tokens=0 will return 0 facts but can still
-                             return chunks from the top-scored (reranked) results.
-                             Chunks are fetched in batches (estimated as (max_chunk_tokens // retain_chunk_size) * 2)
-                             until the token budget is exhausted or all chunks are fetched.
-                             This handles varying chunk sizes across documents.
             tags: Optional list of tags for visibility filtering (OR matching - returns
                   memories that have at least one matching tag)
 
         Returns:
             RecallResultModel containing:
-            - results: List of MemoryFact objects (filtered by max_tokens)
+            - results: List of MemoryFact objects
             - trace: Optional trace information for debugging
             - entities: Optional dict of entity states (if include_entities=True)
-            - chunks: Optional dict of chunks (if include_chunks=True, independent of max_tokens)
+            - chunks: Optional dict of chunks (if include_chunks=True)
         """
         # Authenticate tenant and set schema in context (for fq_table())
         await self._authenticate_tenant(request_context)
@@ -2090,8 +1918,7 @@ class MemoryEngine(MemoryEngineInterface):
         2. Merge: RRF to combine ranked lists
         3. Reranking: Pluggable strategy (heuristic or cross-encoder)
         4. Diversity: MMR with λ=0.5
-        5. Chunks: Fetch chunks from top-scored results (BEFORE token filtering)
-        6. Token Filter: Limit facts to max_tokens budget
+        5. Token Filter: Limit results to max_tokens budget
 
         Args:
             bank_id: bank IDentifier
@@ -2102,7 +1929,7 @@ class MemoryEngine(MemoryEngineInterface):
             enable_trace: Whether to return search trace (deprecated)
             include_entities: Whether to include entity observations
             max_entity_tokens: Maximum tokens for entity observations
-            include_chunks: Whether to include raw chunks (fetched before max_tokens filtering)
+            include_chunks: Whether to include raw chunks
             max_chunk_tokens: Maximum tokens for chunks
 
         Returns:
@@ -2525,85 +2352,6 @@ class MemoryEngine(MemoryEngineInterface):
             top_scored = scored_results[:rerank_limit]
             log_buffer.append(f"  [5] Truncated to top {len(top_scored)} results")
 
-            # Step 5.5: Fetch chunks from top-scored results (before token filtering)
-            # Chunks are fetched independently of max_tokens filtering
-            chunks_dict = None
-            total_chunk_tokens = 0
-            if include_chunks and top_scored:
-                from .response_models import ChunkInfo
-
-                # Collect chunk_ids in order of fact relevance (preserving order from top_scored)
-                # Use a list to maintain order, but track seen chunks to avoid duplicates
-                chunk_ids_ordered = []
-                seen_chunk_ids = set()
-                for sr in top_scored:
-                    chunk_id = sr.retrieval.chunk_id
-                    if chunk_id and chunk_id not in seen_chunk_ids:
-                        chunk_ids_ordered.append(chunk_id)
-                        seen_chunk_ids.add(chunk_id)
-
-                if chunk_ids_ordered:
-                    # Estimate batch size based on retain_chunk_size * 2 (rough estimate)
-                    # Chunk sizes vary per document, so we fetch in batches until budget is exhausted
-                    bank_config = await self._config_resolver.resolve_full_config(bank_id, request_context)
-                    estimated_batch_size = max(1, (max_chunk_tokens // bank_config.retain_chunk_size) * 2)
-
-                    chunks_dict = {}
-                    encoding = _get_tiktoken_encoding()
-                    chunk_offset = 0
-
-                    # Fetch chunks in batches until we run out of budget or chunks
-                    while chunk_offset < len(chunk_ids_ordered) and total_chunk_tokens < max_chunk_tokens:
-                        # Get next batch of chunk IDs
-                        batch_chunk_ids = chunk_ids_ordered[chunk_offset : chunk_offset + estimated_batch_size]
-                        chunk_offset += estimated_batch_size
-
-                        # Fetch chunk data from database
-                        async with acquire_with_retry(pool) as conn:
-                            chunks_rows = await conn.fetch(
-                                f"""
-                                SELECT chunk_id, chunk_text, chunk_index
-                                FROM {fq_table("chunks")}
-                                WHERE chunk_id = ANY($1::text[])
-                                """,
-                                batch_chunk_ids,
-                            )
-
-                        # Create a lookup dict for fast access (preserves order from batch_chunk_ids)
-                        chunks_lookup = {row["chunk_id"]: row for row in chunks_rows}
-
-                        # Process chunks in order, respecting token budget
-                        for chunk_id in batch_chunk_ids:
-                            if chunk_id not in chunks_lookup:
-                                continue
-
-                            row = chunks_lookup[chunk_id]
-                            chunk_text = row["chunk_text"]
-                            chunk_tokens = len(encoding.encode(chunk_text))
-
-                            # Check if adding this chunk would exceed the limit
-                            if total_chunk_tokens + chunk_tokens > max_chunk_tokens:
-                                # Truncate the chunk to fit within the remaining budget
-                                remaining_tokens = max_chunk_tokens - total_chunk_tokens
-                                if remaining_tokens > 0:
-                                    # Truncate to remaining tokens
-                                    truncated_text = encoding.decode(encoding.encode(chunk_text)[:remaining_tokens])
-                                    chunks_dict[chunk_id] = ChunkInfo(
-                                        chunk_text=truncated_text, chunk_index=row["chunk_index"], truncated=True
-                                    )
-                                    total_chunk_tokens = max_chunk_tokens
-                                # Budget exhausted - stop fetching more batches
-                                break
-                            else:
-                                chunks_dict[chunk_id] = ChunkInfo(
-                                    chunk_text=chunk_text, chunk_index=row["chunk_index"], truncated=False
-                                )
-                                total_chunk_tokens += chunk_tokens
-
-                        # If we hit the budget limit in this batch, stop fetching more batches
-                        if total_chunk_tokens >= max_chunk_tokens:
-                            break
-
             # Step 6: Token budget filtering
             step_start = time.time()
 
@@ -2698,6 +2446,68 @@ class MemoryEngine(MemoryEngineInterface):
             # Entity observations removed - always set to None
             entities_dict = None
 
+            # Fetch chunks if requested
+            chunks_dict = None
+            total_chunk_tokens = 0
+            if include_chunks and top_scored:
+                from .response_models import ChunkInfo
+
+                # Collect chunk_ids in order of fact relevance (preserving order from top_scored)
+                # Use a list to maintain order, but track seen chunks to avoid duplicates
+                chunk_ids_ordered = []
+                seen_chunk_ids = set()
+                for sr in top_scored:
+                    chunk_id = sr.retrieval.chunk_id
+                    if chunk_id and chunk_id not in seen_chunk_ids:
+                        chunk_ids_ordered.append(chunk_id)
+                        seen_chunk_ids.add(chunk_id)
+
+                if chunk_ids_ordered:
+                    # Fetch chunk data from database using chunk_ids (no ORDER BY to preserve input order)
+                    async with acquire_with_retry(pool) as conn:
+                        chunks_rows = await conn.fetch(
+                            f"""
+                            SELECT chunk_id, chunk_text, chunk_index
+                            FROM {fq_table("chunks")}
+                            WHERE chunk_id = ANY($1::text[])
+                            """,
+                            chunk_ids_ordered,
+                        )
+
+                    # Create a lookup dict for fast access
+                    chunks_lookup = {row["chunk_id"]: row for row in chunks_rows}
+
+                    # Apply token limit and build chunks_dict in the order of chunk_ids_ordered
+                    chunks_dict = {}
+                    encoding = _get_tiktoken_encoding()
+
+                    for chunk_id in chunk_ids_ordered:
+                        if chunk_id not in chunks_lookup:
+                            continue
+
+                        row = chunks_lookup[chunk_id]
+                        chunk_text = row["chunk_text"]
+                        chunk_tokens = len(encoding.encode(chunk_text))
+
+                        # Check if adding this chunk would exceed the limit
+                        if total_chunk_tokens + chunk_tokens > max_chunk_tokens:
+                            # Truncate the chunk to fit within the remaining budget
+                            remaining_tokens = max_chunk_tokens - total_chunk_tokens
+                            if remaining_tokens > 0:
+                                # Truncate to remaining tokens
+                                truncated_text = encoding.decode(encoding.encode(chunk_text)[:remaining_tokens])
+                                chunks_dict[chunk_id] = ChunkInfo(
+                                    chunk_text=truncated_text, chunk_index=row["chunk_index"], truncated=True
+                                )
+                                total_chunk_tokens = max_chunk_tokens
+                            # Stop adding more chunks once we hit the limit
+                            break
+                        else:
+                            chunks_dict[chunk_id] = ChunkInfo(
+                                chunk_text=chunk_text, chunk_index=row["chunk_index"], truncated=False
+                            )
+                            total_chunk_tokens += chunk_tokens
+
             # Finalize trace if enabled
             trace_dict = None
             if tracer:
@@ -5623,10 +5433,10 @@ class MemoryEngine(MemoryEngineInterface):
             )
             total = total_row["total"] if total_row else 0
 
-            # Get operations with pagination (include result_metadata to check for parent operations)
+            # Get operations with pagination
             operations = await conn.fetch(
                 f"""
-                SELECT operation_id, operation_type, created_at, status, error_message, result_metadata
+                SELECT operation_id, operation_type, created_at, status, error_message
                 FROM {fq_table("async_operations")}
                 WHERE {where_clause}
                 ORDER BY created_at DESC
@@ -5637,29 +5447,21 @@ class MemoryEngine(MemoryEngineInterface):
                 offset,
             )
 
-            # Build operation list using status from database
-            # Parent operations have their status updated when all children complete/fail
-            operation_list = []
-            for row in operations:
-                # Map DB status to API status (pending includes processing)
-                db_status = row["status"]
-                api_status = "pending" if db_status in ("pending", "processing") else db_status
-
-                operation_list.append(
+            return {
+                "total": total,
+                "operations": [
                     {
                         "id": str(row["operation_id"]),
                         "task_type": row["operation_type"],
                         "items_count": 0,
                         "document_id": None,
                         "created_at": row["created_at"].isoformat(),
-                        "status": api_status,
+                        # Map DB status to API status (processing -> pending for simplicity)
+                        "status": "pending" if row["status"] in ("pending", "processing") else row["status"],
                         "error_message": row["error_message"],
                     }
-                )
-
-            return {
-                "total": total,
-                "operations": operation_list,
+                    for row in operations
+                ],
             }
 
     async def get_operation_status(
@@ -5671,13 +5473,10 @@ class MemoryEngine(MemoryEngineInterface):
     ) -> dict[str, Any]:
         """Get the status of a specific async operation.
 
-        For parent operations, the status is automatically updated in the database when all children complete/fail.
-
         Returns:
-            - status: "pending", "completed", or "failed" (from database)
+            - status: "pending", "completed", or "failed"
             - updated_at: last update timestamp
             - completed_at: completion timestamp (if completed)
-            - child_operations: (for parent operations) list of child operation statuses
         """
         await self._authenticate_tenant(request_context)
         pool = await self._get_pool()
@@ -5687,7 +5486,7 @@ class MemoryEngine(MemoryEngineInterface):
         async with acquire_with_retry(pool) as conn:
             row = await conn.fetchrow(
                 f"""
-                SELECT operation_id, operation_type, created_at, updated_at, completed_at, status, error_message, result_metadata
+                SELECT operation_id, operation_type, created_at, updated_at, completed_at, status, error_message
                 FROM {fq_table("async_operations")}
                 WHERE operation_id = $1 AND bank_id = $2
                 """,
@@ -5696,98 +5495,18 @@ class MemoryEngine(MemoryEngineInterface):
             )
 
             if row:
-                # Check if this is a parent operation
-                result_metadata = json.loads(row["result_metadata"]) if row["result_metadata"] else {}
-                is_parent = result_metadata.get("is_parent", False)
-
-                # Use status from database (parent status is updated when all children complete/fail)
+                # Map DB status to API status (processing -> pending for simplicity)
                 db_status = row["status"]
                 api_status = "pending" if db_status in ("pending", "processing") else db_status
-
-                # For parent operations, include child operations list
-                if is_parent:
-                    # Query child operations
-                    child_rows = await conn.fetch(
-                        f"""
-                        SELECT operation_id, status, error_message, result_metadata
-                        FROM {fq_table("async_operations")}
-                        WHERE bank_id = $1
-                        AND result_metadata::jsonb @> $2::jsonb
-                        ORDER BY (result_metadata->>'sub_batch_index')::int
-                        """,
-                        bank_id,
-                        json.dumps({"parent_operation_id": operation_id}),
-                    )
-
-                    # Build child operations list and check if parent status needs updating
-                    child_statuses = []
-                    all_done = True
-                    any_failed = False
-                    all_completed = True
-
-                    for child_row in child_rows:
-                        child_metadata = (
-                            json.loads(child_row["result_metadata"]) if child_row["result_metadata"] else {}
-                        )
-                        child_status = child_row["status"]
-
-                        child_statuses.append(
-                            {
-                                "operation_id": str(child_row["operation_id"]),
-                                "status": child_status,
-                                "sub_batch_index": child_metadata.get("sub_batch_index"),
-                                "items_count": child_metadata.get("items_count"),
-                                "error_message": child_row["error_message"],
-                            }
-                        )
-
-                        if child_status not in ("completed", "failed"):
-                            all_done = False
-                        if child_status == "failed":
-                            any_failed = True
-                        if child_status != "completed":
-                            all_completed = False
-
-                    # Self-healing: if parent status is out of sync with children, update it
-                    if all_done and api_status == "pending":
-                        correct_status = "failed" if any_failed else "completed"
-                        logger.warning(
-                            f"Parent operation {operation_id} status out of sync (DB: pending, should be: {correct_status}). Fixing."
-                        )
-                        await conn.execute(
-                            f"""
-                            UPDATE {fq_table("async_operations")}
-                            SET status = $2, updated_at = NOW(), completed_at = NOW()
-                            WHERE operation_id = $1
-                            """,
-                            op_uuid,
-                            correct_status,
-                        )
-                        api_status = correct_status
-
-                    return {
-                        "operation_id": operation_id,
-                        "status": api_status,
-                        "operation_type": row["operation_type"],
-                        "created_at": row["created_at"].isoformat() if row["created_at"] else None,
-                        "updated_at": row["updated_at"].isoformat() if row["updated_at"] else None,
-                        "completed_at": row["completed_at"].isoformat() if row["completed_at"] else None,
-                        "error_message": row["error_message"],
-                        "result_metadata": result_metadata,
-                        "child_operations": child_statuses,
-                    }
-                else:
-                    # Regular operation (not a parent)
-                    return {
-                        "operation_id": operation_id,
-                        "status": api_status,
-                        "operation_type": row["operation_type"],
-                        "created_at": row["created_at"].isoformat() if row["created_at"] else None,
-                        "updated_at": row["updated_at"].isoformat() if row["updated_at"] else None,
-                        "completed_at": row["completed_at"].isoformat() if row["completed_at"] else None,
-                        "error_message": row["error_message"],
-                        "result_metadata": result_metadata,
-                    }
+                return {
+                    "operation_id": operation_id,
+                    "status": api_status,
+                    "operation_type": row["operation_type"],
+                    "created_at": row["created_at"].isoformat() if row["created_at"] else None,
+                    "updated_at": row["updated_at"].isoformat() if row["updated_at"] else None,
+                    "completed_at": row["completed_at"].isoformat() if row["completed_at"] else None,
+                    "error_message": row["error_message"],
+                }
             else:
                 # Operation not found
                 return {
@@ -5963,126 +5682,31 @@ class MemoryEngine(MemoryEngineInterface):
         request_context: "RequestContext",
         document_tags: list[str] | None = None,
     ) -> dict[str, Any]:
-        """Submit a batch retain operation to run asynchronously.
-
-        For large batches (exceeding retain_batch_chars threshold), automatically splits
-        into smaller sub-batches and creates a parent operation that tracks all children.
-        """
+        """Submit a batch retain operation to run asynchronously."""
         await self._authenticate_tenant(request_context)
 
-        # Validate no duplicate document_ids in the batch
-        # Having duplicate document_ids causes race conditions in document upserts during parallel processing
-        doc_ids = [item.get("document_id") for item in contents if item.get("document_id")]
-        if len(doc_ids) != len(set(doc_ids)):
-            from collections import Counter
+        task_payload: dict[str, Any] = {"contents": contents}
+        if document_tags:
+            task_payload["document_tags"] = document_tags
+        # Pass tenant_id and api_key_id through task payload so the worker
+        # can propagate request context to downstream operations (e.g.,
+        # consolidation and mental model refreshes triggered after retain).
+        if request_context.tenant_id:
+            task_payload["_tenant_id"] = request_context.tenant_id
+        if request_context.api_key_id:
+            task_payload["_api_key_id"] = request_context.api_key_id
 
-            duplicates = [doc_id for doc_id, count in Counter(doc_ids).items() if count > 1]
-            raise ValueError(
-                f"Batch contains duplicate document_ids: {duplicates}. "
-                f"Each content item in a batch must have a unique document_id to avoid race conditions."
-            )
-
-        # Calculate total token count and determine if we need to split
-        total_tokens = sum(count_tokens(item.get("content", "")) for item in contents)
-        config = get_config()
-        tokens_per_batch = config.retain_batch_tokens
-
-        # Split into sub-batches based on token count
-        sub_batches = []
-        current_batch = []
-        current_batch_tokens = 0
-
-        for item in contents:
-            item_tokens = count_tokens(item.get("content", ""))
-
-            # If adding this item would exceed the limit, start a new batch
-            # (unless current batch is empty - then we must include it even if it's large)
-            if current_batch and current_batch_tokens + item_tokens > tokens_per_batch:
-                sub_batches.append(current_batch)
-                current_batch = [item]
-                current_batch_tokens = item_tokens
-            else:
-                current_batch.append(item)
-                current_batch_tokens += item_tokens
-
-        # Add the last batch
-        if current_batch:
-            sub_batches.append(current_batch)
-
-        # Log splitting info if we actually split
-        if len(sub_batches) > 1:
-            logger.info(
-                f"Large async retain batch ({total_tokens:,} tokens from {len(contents)} items). "
-                f"Split into {len(sub_batches)} sub-batches: {[len(b) for b in sub_batches]} items each"
-            )
-
-        # Always create parent operation (even for single batch - simpler, more reliable code path)
-        import uuid
-
-        parent_operation_id = uuid.uuid4()
-        pool = await self._get_pool()
-
-        # Create typed metadata for parent operation
-        parent_metadata = BatchRetainParentMetadata(
-            items_count=len(contents),
-            total_tokens=total_tokens,
-            num_sub_batches=len(sub_batches),
+        result = await self._submit_async_operation(
+            bank_id=bank_id,
+            operation_type="retain",
+            task_type="batch_retain",
+            task_payload=task_payload,
+            result_metadata={"items_count": len(contents)},
+            dedupe_by_bank=False,
         )
 
-        async with acquire_with_retry(pool) as conn:
-            await conn.execute(
-                f"""
-                INSERT INTO {fq_table("async_operations")} (operation_id, bank_id, operation_type, result_metadata, status)
-                VALUES ($1, $2, $3, $4, $5)
-                """,
-                parent_operation_id,
-                bank_id,
-                "batch_retain",
-                json.dumps(parent_metadata.to_dict()),
-                "pending",  # Will be updated by status aggregation
-            )
-
-        logger.info(f"Created parent operation {parent_operation_id} for {len(sub_batches)} sub-batch(es)")
-
-        # Submit child operations for each sub-batch
-        for i, sub_batch in enumerate(sub_batches, 1):
-            if len(sub_batches) > 1:
-                sub_batch_tokens = sum(count_tokens(item.get("content", "")) for item in sub_batch)
-                logger.info(
-                    f"Submitting sub-batch {i}/{len(sub_batches)}: {len(sub_batch)} items, {sub_batch_tokens:,} tokens"
-                )
-
-            task_payload: dict[str, Any] = {"contents": sub_batch}
-            if document_tags:
-                task_payload["document_tags"] = document_tags
-            # Pass tenant_id and api_key_id through task payload
-            if request_context.tenant_id:
-                task_payload["_tenant_id"] = request_context.tenant_id
-            if request_context.api_key_id:
-                task_payload["_api_key_id"] = request_context.api_key_id
-
-            # Create typed metadata for child operation
-            child_metadata = BatchRetainChildMetadata(
-                items_count=len(sub_batch),
-                parent_operation_id=str(parent_operation_id),
-                sub_batch_index=i,
-                total_sub_batches=len(sub_batches),
-            )
-
-            # Create child operation with reference to parent
-            await self._submit_async_operation(
-                bank_id=bank_id,
-                operation_type="retain",
-                task_type="batch_retain",
-                task_payload=task_payload,
-                result_metadata=child_metadata.to_dict(),
-                dedupe_by_bank=False,
-            )
-
-        return {
-            "operation_id": str(parent_operation_id),
-            "items_count": len(contents),
-        }
+        result["items_count"] = len(contents)
+        return result
 
     async def submit_async_consolidation(
         self,

hindsight-api/hindsight_api/engine/operation_metadata.py

@@ -1,69 +0,0 @@
-"""
-Typed metadata models for async operations.
-
-These dataclasses define the structure of result_metadata for different operation types.
-The metadata is exposed in the API for debugging purposes and may change without notice.
-"""
-
-from dataclasses import asdict, dataclass
-from typing import Any
-
-
-@dataclass
-class BatchRetainParentMetadata:
-    """Metadata for parent batch_retain operations (when split into sub-batches)."""
-
-    items_count: int
-    total_tokens: int
-    num_sub_batches: int
-    is_parent: bool = True
-
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dict for JSON serialization."""
-        return asdict(self)
-
-
-@dataclass
-class BatchRetainChildMetadata:
-    """Metadata for child batch_retain operations (individual sub-batches)."""
-
-    items_count: int
-    parent_operation_id: str
-    sub_batch_index: int
-    total_sub_batches: int
-
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dict for JSON serialization."""
-        return asdict(self)
-
-
-@dataclass
-class RetainMetadata:
-    """Metadata for regular retain operations (non-batched, deprecated async path)."""
-
-    items_count: int
-
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dict for JSON serialization."""
-        return asdict(self)
-
-
-@dataclass
-class ConsolidationMetadata:
-    """Metadata for consolidation operations."""
-
-    # Currently empty, but structure for future fields
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dict for JSON serialization."""
-        return asdict(self)
-
-
-@dataclass
-class RefreshMentalModelMetadata:
-    """Metadata for mental model refresh operations."""
-
-    mental_model_id: str
-
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dict for JSON serialization."""
-        return asdict(self)

hindsight-api/hindsight_api/engine/retain/fact_storage.py

@@ -97,9 +97,8 @@ async def insert_facts_batch(
             FROM input_data
             RETURNING id
         """
-    else:  # native or pg_textsearch
+    else:  # native
         # Native PostgreSQL: search_vector is GENERATED ALWAYS, don't include it
-        # pg_textsearch: indexes operate on base columns directly, don't populate search_vector
         query = f"""
             WITH input_data AS (
                 SELECT * FROM unnest(

hindsight-api/hindsight_api/engine/search/retrieval.py

@@ -164,74 +164,99 @@ async def retrieve_semantic_bm25_combined(
     # Build tags clause - param 6 if tags provided
     tags_clause = build_tags_where_clause_simple(tags, 6, match=tags_match)
 
-    # Build backend-specific BM25 parts
     if config.text_search_extension == "vchord":
         # VectorChord BM25: use <&> operator with to_bm25query and tokenize
         # Note: VectorChord scores are negative (higher = better, so -1 > -10)
-        bm25_score_expr = "search_vector <&> to_bm25query('idx_memory_units_text_search', tokenize($5, 'llmlingua2'))"
-        bm25_order_by = f"{bm25_score_expr} DESC"
-        bm25_where_filter = ""  # No additional WHERE filter for vchord
         params = [query_emb_str, bank_id, fact_types, limit, query_text]  # Pass raw query_text for tokenization
-    elif config.text_search_extension == "pg_textsearch":
-        # Timescale pg_textsearch: use <@> operator with to_bm25query
-        # Note: pg_textsearch scores are negative (lower/more negative = better, so -10 > -1)
-        # We negate the score to maintain API consistency (higher = better)
-        bm25_score_expr = "-(text <@> to_bm25query($5, 'idx_memory_units_text_search'))"
-        bm25_order_by = "text <@> to_bm25query($5, 'idx_memory_units_text_search') ASC"
-        bm25_where_filter = ""  # No additional WHERE filter for pg_textsearch
-        params = [query_emb_str, bank_id, fact_types, limit, query_text]
+        if tags:
+            params.append(tags)
+
+        query = f"""
+            WITH semantic_ranked AS (
+                SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
+                       1 - (embedding <=> $1::vector) AS similarity,
+                       NULL::float AS bm25_score,
+                       'semantic' AS source,
+                       ROW_NUMBER() OVER (PARTITION BY fact_type ORDER BY embedding <=> $1::vector) AS rn
+                FROM {fq_table("memory_units")}
+                WHERE bank_id = $2
+                  AND embedding IS NOT NULL
+                  AND fact_type = ANY($3)
+                  AND (1 - (embedding <=> $1::vector)) >= 0.3
+                  {tags_clause}
+            ),
+            bm25_ranked AS (
+                SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
+                       NULL::float AS similarity,
+                       search_vector <&> to_bm25query('idx_memory_units_text_search', tokenize($5, 'llmlingua2')) AS bm25_score,
+                       'bm25' AS source,
+                       ROW_NUMBER() OVER (PARTITION BY fact_type ORDER BY search_vector <&> to_bm25query('idx_memory_units_text_search', tokenize($5, 'llmlingua2')) DESC) AS rn
+                FROM {fq_table("memory_units")}
+                WHERE bank_id = $2
+                  AND fact_type = ANY($3)
+                  {tags_clause}
+            ),
+            semantic AS (
+                SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
+                       similarity, bm25_score, source
+                FROM semantic_ranked WHERE rn <= $4
+            ),
+            bm25 AS (
+                SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
+                       similarity, bm25_score, source
+                FROM bm25_ranked WHERE rn <= $4
+            )
+            SELECT * FROM semantic
+            UNION ALL
+            SELECT * FROM bm25
+        """
     else:  # native
         # Native PostgreSQL: use ts_rank_cd with to_tsquery
         query_tsquery = " | ".join(tokens)
-        bm25_score_expr = "ts_rank_cd(search_vector, to_tsquery('english', $5))"
-        bm25_order_by = f"{bm25_score_expr} DESC"
-        bm25_where_filter = "AND search_vector @@ to_tsquery('english', $5)"
         params = [query_emb_str, bank_id, fact_types, limit, query_tsquery]
+        if tags:
+            params.append(tags)
 
-    if tags:
-        params.append(tags)
-
-    # Single query template with backend-specific parts injected
-    query = f"""
-        WITH semantic_ranked AS (
-            SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
-                   1 - (embedding <=> $1::vector) AS similarity,
-                   NULL::float AS bm25_score,
-                   'semantic' AS source,
-                   ROW_NUMBER() OVER (PARTITION BY fact_type ORDER BY embedding <=> $1::vector) AS rn
-            FROM {fq_table("memory_units")}
-            WHERE bank_id = $2
-              AND embedding IS NOT NULL
-              AND fact_type = ANY($3)
-              AND (1 - (embedding <=> $1::vector)) >= 0.3
-              {tags_clause}
-        ),
-        bm25_ranked AS (
-            SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
-                   NULL::float AS similarity,
-                   {bm25_score_expr} AS bm25_score,
-                   'bm25' AS source,
-                   ROW_NUMBER() OVER (PARTITION BY fact_type ORDER BY {bm25_order_by}) AS rn
-            FROM {fq_table("memory_units")}
-            WHERE bank_id = $2
-              AND fact_type = ANY($3)
-              {bm25_where_filter}
-              {tags_clause}
-        ),
-        semantic AS (
-            SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
-                   similarity, bm25_score, source
-            FROM semantic_ranked WHERE rn <= $4
-        ),
-        bm25 AS (
-            SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
-                   similarity, bm25_score, source
-            FROM bm25_ranked WHERE rn <= $4
-        )
-        SELECT * FROM semantic
-        UNION ALL
-        SELECT * FROM bm25
-    """
+        query = f"""
+            WITH semantic_ranked AS (
+                SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
+                       1 - (embedding <=> $1::vector) AS similarity,
+                       NULL::float AS bm25_score,
+                       'semantic' AS source,
+                       ROW_NUMBER() OVER (PARTITION BY fact_type ORDER BY embedding <=> $1::vector) AS rn
+                FROM {fq_table("memory_units")}
+                WHERE bank_id = $2
+                  AND embedding IS NOT NULL
+                  AND fact_type = ANY($3)
+                  AND (1 - (embedding <=> $1::vector)) >= 0.3
+                  {tags_clause}
+            ),
+            bm25_ranked AS (
+                SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
+                       NULL::float AS similarity,
+                       ts_rank_cd(search_vector, to_tsquery('english', $5)) AS bm25_score,
+                       'bm25' AS source,
+                       ROW_NUMBER() OVER (PARTITION BY fact_type ORDER BY ts_rank_cd(search_vector, to_tsquery('english', $5)) DESC) AS rn
+                FROM {fq_table("memory_units")}
+                WHERE bank_id = $2
+                  AND fact_type = ANY($3)
+                  AND search_vector @@ to_tsquery('english', $5)
+                  {tags_clause}
+            ),
+            semantic AS (
+                SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
+                       similarity, bm25_score, source
+                FROM semantic_ranked WHERE rn <= $4
+            ),
+            bm25 AS (
+                SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
+                       similarity, bm25_score, source
+                FROM bm25_ranked WHERE rn <= $4
+            )
+            SELECT * FROM semantic
+            UNION ALL
+            SELECT * FROM bm25
+        """
 
     # Combined CTE query for both semantic and BM25 across all fact types
     # Uses window functions to limit per fact_type per method

hindsight-api/hindsight_api/main.py

@@ -208,9 +208,6 @@ def main():
             embeddings_litellm_api_base=config.embeddings_litellm_api_base,
             embeddings_litellm_api_key=config.embeddings_litellm_api_key,
             embeddings_litellm_model=config.embeddings_litellm_model,
-            embeddings_litellm_sdk_api_key=config.embeddings_litellm_sdk_api_key,
-            embeddings_litellm_sdk_model=config.embeddings_litellm_sdk_model,
-            embeddings_litellm_sdk_api_base=config.embeddings_litellm_sdk_api_base,
             reranker_provider=config.reranker_provider,
             reranker_local_model=config.reranker_local_model,
             reranker_local_force_cpu=config.reranker_local_force_cpu,
@@ -226,9 +223,6 @@ def main():
             reranker_litellm_api_base=config.reranker_litellm_api_base,
             reranker_litellm_api_key=config.reranker_litellm_api_key,
             reranker_litellm_model=config.reranker_litellm_model,
-            reranker_litellm_sdk_api_key=config.reranker_litellm_sdk_api_key,
-            reranker_litellm_sdk_model=config.reranker_litellm_sdk_model,
-            reranker_litellm_sdk_api_base=config.reranker_litellm_sdk_api_base,
             host=args.host,
             port=args.port,
             base_path=config.base_path,
@@ -245,7 +239,6 @@ def main():
             retain_extract_causal_links=config.retain_extract_causal_links,
             retain_extraction_mode=config.retain_extraction_mode,
             retain_custom_instructions=config.retain_custom_instructions,
-            retain_batch_tokens=config.retain_batch_tokens,
             enable_observations=config.enable_observations,
             consolidation_batch_size=config.consolidation_batch_size,
             consolidation_max_tokens=config.consolidation_max_tokens,

hindsight-api/hindsight_api/migrations.py

@@ -688,9 +688,6 @@ def ensure_text_search_extension(
         if text_search_extension == "vchord":
             target_column_type = "bm25vector"
             target_index_type = "bm25"
-        elif text_search_extension == "pg_textsearch":
-            target_column_type = "text"
-            target_index_type = "bm25"
         else:  # native
             target_column_type = "tsvector"
             target_index_type = "gin"
@@ -778,16 +775,7 @@ def ensure_text_search_extension(
         # If there's data in any mismatched table, raise error
         if tables_with_data:
             table_list = ", ".join([f"{table}({count} rows)" for table, count in tables_with_data])
-            # Detect current extension from column type
-            current_col_type = mismatched_tables[0][1]
-            if current_col_type == "tsvector":
-                current_ext = "native"
-            elif current_col_type == "bm25vector":
-                current_ext = "vchord"
-            elif current_col_type == "text":
-                current_ext = "pg_textsearch"
-            else:
-                current_ext = "unknown"
+            current_ext = "native" if mismatched_tables[0][1] == "tsvector" else "vchord"
             raise RuntimeError(
                 f"Cannot change text search extension from {current_ext} to {text_search_extension}: "
                 f"the following tables contain data: {table_list}. "
@@ -832,27 +820,6 @@ def ensure_text_search_extension(
                         USING bm25 (search_vector bm25_catalog.bm25_ops)
                     """)
                 )
-            elif text_search_extension == "pg_textsearch":
-                logger.info(f"Creating TEXT column on {table_name}")
-                # Dummy TEXT column for consistency (indexes operate on base columns)
-                conn.execute(text(f"ALTER TABLE {schema_name}.{table_name} ADD COLUMN search_vector TEXT"))
-
-                # Create BM25 index on expression
-                logger.info(f"Creating BM25 index on {table_name}")
-                # Different expression for each table
-                if table_name == "memory_units":
-                    index_expr = "(COALESCE(text, '') || ' ' || COALESCE(context, ''))"
-                else:  # reflections
-                    index_expr = "(COALESCE(name, '') || ' ' || content)"
-
-                conn.execute(
-                    text(f"""
-                        CREATE INDEX idx_{table_name.replace(".", "_")}_text_search
-                        ON {schema_name}.{table_name}
-                        USING bm25({index_expr})
-                        WITH (text_config='english')
-                    """)
-                )
             else:  # native
                 logger.info(f"Creating tsvector column on {table_name}")
                 # Different GENERATED expression for each table

hindsight-api/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "hindsight-api"
-version = "0.4.11"
+version = "0.4.10"
 description = "Hindsight: Agent Memory That Works Like Human Memory"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -42,7 +42,6 @@ dependencies = [
     "typer>=0.9.0",
     "cohere>=5.0.0",
     "flashrank>=0.2.0",
-    "litellm>=1.0.0",
     # Local ML models for embeddings/reranking - can be excluded in Docker with INCLUDE_LOCAL_MODELS=false
     "sentence-transformers>=3.3.0",
     "transformers>=4.53.0", # Security fixes for ReDoS vulnerabilities

hindsight-api/tests/test_async_batch_retain.py

@@ -1,423 +0,0 @@
-"""Test async batch retain with smart batching and parent-child operations."""
-
-import asyncio
-import json
-import uuid
-
-import pytest
-
-from hindsight_api.extensions import RequestContext
-
-
-@pytest.mark.asyncio
-async def test_duplicate_document_ids_rejected_async(memory, request_context):
-    """Test that async retain rejects batches with duplicate document_ids."""
-    bank_id = "test_duplicate_async"
-    contents = [
-        {"content": "First item", "document_id": "doc1"},
-        {"content": "Second item", "document_id": "doc2"},
-        {"content": "Third item", "document_id": "doc1"},  # Duplicate!
-    ]
-
-    # Should raise ValueError due to duplicate document_ids
-    with pytest.raises(ValueError, match="duplicate document_ids.*doc1"):
-        await memory.submit_async_retain(
-            bank_id=bank_id,
-            contents=contents,
-            request_context=request_context,
-        )
-
-
-@pytest.mark.asyncio
-async def test_duplicate_document_ids_rejected_sync(memory, request_context):
-    """Test that sync retain also rejects batches with duplicate document_ids."""
-    bank_id = "test_duplicate_sync"
-    contents = [
-        {"content": "First item", "document_id": "doc1"},
-        {"content": "Second item", "document_id": "doc1"},  # Duplicate!
-    ]
-
-    # Should raise ValueError due to duplicate document_ids
-    with pytest.raises(ValueError, match="duplicate document_ids.*doc1"):
-        await memory.retain_batch_async(
-            bank_id=bank_id,
-            contents=contents,
-            request_context=request_context,
-        )
-
-
-@pytest.mark.asyncio
-async def test_small_async_batch_no_splitting(memory, request_context):
-    """Test that small async batches create parent with single child (simplified code path)."""
-    bank_id = "test_small_async"
-    contents = [{"content": "Alice works at Google", "document_id": f"doc{i}"} for i in range(5)]
-
-    # Calculate total chars (should be well under threshold)
-    total_chars = sum(len(item["content"]) for item in contents)
-    assert total_chars < 10_000, "Test batch should be small"
-
-    # Submit async retain
-    result = await memory.submit_async_retain(
-        bank_id=bank_id,
-        contents=contents,
-        request_context=request_context,
-    )
-
-    # Verify we got an operation_id back
-    assert "operation_id" in result
-    assert "items_count" in result
-    assert result["items_count"] == 5
-
-    operation_id = result["operation_id"]
-
-    # Wait for task to complete (SyncTaskBackend executes immediately)
-    await asyncio.sleep(0.1)
-
-    # Check operation status
-    status = await memory.get_operation_status(
-        bank_id=bank_id,
-        operation_id=operation_id,
-        request_context=request_context,
-    )
-
-    # Should be a parent operation with single child (simplified code path)
-    assert status["status"] == "completed"
-    assert status["operation_type"] == "batch_retain"
-    assert "child_operations" in status
-    assert status["result_metadata"]["num_sub_batches"] == 1  # Single sub-batch
-    assert len(status["child_operations"]) == 1
-    assert status["child_operations"][0]["status"] == "completed"
-
-
-@pytest.mark.asyncio
-async def test_large_async_batch_auto_splits(memory, request_context):
-    """Test that large async batches automatically split into sub-batches with parent operation."""
-    from hindsight_api.engine.memory_engine import count_tokens
-
-    bank_id = "test_large_async"
-
-    # Create a large batch that exceeds the threshold (10k tokens default)
-    # Repeating "A"s gets heavily compressed by tokenizer, use varied content
-    # Use ~22k chars per item = ~5.5k tokens per item, 2 items = ~11k tokens total (exceeds 10k)
-    large_content = "The quick brown fox jumps over the lazy dog. " * 500  # ~22k chars = ~5.5k tokens
-    contents = [{"content": large_content + f" item {i}", "document_id": f"doc{i}"} for i in range(2)]
-
-    # Calculate total tokens (should exceed threshold)
-    total_tokens = sum(count_tokens(item["content"]) for item in contents)
-    assert total_tokens > 10_000, "Test batch should exceed threshold"
-
-    # Submit async retain
-    result = await memory.submit_async_retain(
-        bank_id=bank_id,
-        contents=contents,
-        request_context=request_context,
-    )
-
-    # Verify we got an operation_id back
-    assert "operation_id" in result
-    assert "items_count" in result
-    assert result["items_count"] == 2
-
-    parent_operation_id = result["operation_id"]
-
-    # Wait for tasks to complete
-    await asyncio.sleep(0.5)
-
-    # Check parent operation status
-    parent_status = await memory.get_operation_status(
-        bank_id=bank_id,
-        operation_id=parent_operation_id,
-        request_context=request_context,
-    )
-
-    # Should be a parent operation with children
-    assert parent_status["operation_type"] == "batch_retain"
-    assert "child_operations" in parent_status
-    assert "num_sub_batches" in parent_status["result_metadata"]
-    assert parent_status["result_metadata"]["num_sub_batches"] >= 2  # Should split into at least 2 batches
-    assert parent_status["result_metadata"]["items_count"] == 2
-
-    # Verify child operations
-    child_ops = parent_status["child_operations"]
-    assert len(child_ops) >= 2, "Should have at least 2 child operations"
-
-    # All children should be completed (SyncTaskBackend executes immediately)
-    for child in child_ops:
-        assert child["status"] == "completed"
-        assert child["sub_batch_index"] is not None
-        assert child["items_count"] > 0
-
-    # Parent status should be aggregated as "completed"
-    assert parent_status["status"] == "completed"
-
-
-@pytest.mark.asyncio
-async def test_parent_operation_status_aggregation_pending(memory, request_context):
-    """Test that parent operation shows 'pending' when children are pending."""
-    bank_id = "test_parent_pending"
-    pool = await memory._get_pool()
-
-    # Manually create a parent operation
-    parent_id = uuid.uuid4()
-    async with pool.acquire() as conn:
-        await conn.execute(
-            """
-            INSERT INTO async_operations (operation_id, bank_id, operation_type, result_metadata, status)
-            VALUES ($1, $2, $3, $4, $5)
-            """,
-            parent_id,
-            bank_id,
-            "batch_retain",
-            json.dumps({"items_count": 20, "num_sub_batches": 2, "is_parent": True}),
-            "pending",
-        )
-
-        # Create 2 child operations - one completed, one pending
-        child1_id = uuid.uuid4()
-        await conn.execute(
-            """
-            INSERT INTO async_operations (operation_id, bank_id, operation_type, result_metadata, status)
-            VALUES ($1, $2, $3, $4, $5)
-            """,
-            child1_id,
-            bank_id,
-            "retain",
-            json.dumps(
-                {
-                    "items_count": 10,
-                    "parent_operation_id": str(parent_id),
-                    "sub_batch_index": 1,
-                    "total_sub_batches": 2,
-                }
-            ),
-            "completed",
-        )
-
-        child2_id = uuid.uuid4()
-        await conn.execute(
-            """
-            INSERT INTO async_operations (operation_id, bank_id, operation_type, result_metadata, status)
-            VALUES ($1, $2, $3, $4, $5)
-            """,
-            child2_id,
-            bank_id,
-            "retain",
-            json.dumps(
-                {
-                    "items_count": 10,
-                    "parent_operation_id": str(parent_id),
-                    "sub_batch_index": 2,
-                    "total_sub_batches": 2,
-                }
-            ),
-            "pending",
-        )
-
-    # Check parent status
-    parent_status = await memory.get_operation_status(
-        bank_id=bank_id,
-        operation_id=str(parent_id),
-        request_context=request_context,
-    )
-
-    # Parent should aggregate as "pending" since one child is still pending
-    assert parent_status["status"] == "pending"
-    assert len(parent_status["child_operations"]) == 2
-
-
-@pytest.mark.asyncio
-async def test_parent_operation_status_aggregation_failed(memory, request_context):
-    """Test that parent operation shows 'failed' when any child fails."""
-    bank_id = "test_parent_failed"
-    pool = await memory._get_pool()
-
-    # Manually create a parent operation
-    parent_id = uuid.uuid4()
-    async with pool.acquire() as conn:
-        await conn.execute(
-            """
-            INSERT INTO async_operations (operation_id, bank_id, operation_type, result_metadata, status)
-            VALUES ($1, $2, $3, $4, $5)
-            """,
-            parent_id,
-            bank_id,
-            "batch_retain",
-            json.dumps({"items_count": 20, "num_sub_batches": 2, "is_parent": True}),
-            "pending",
-        )
-
-        # Create 2 child operations - one completed, one failed
-        child1_id = uuid.uuid4()
-        await conn.execute(
-            """
-            INSERT INTO async_operations (operation_id, bank_id, operation_type, result_metadata, status)
-            VALUES ($1, $2, $3, $4, $5)
-            """,
-            child1_id,
-            bank_id,
-            "retain",
-            json.dumps(
-                {
-                    "items_count": 10,
-                    "parent_operation_id": str(parent_id),
-                    "sub_batch_index": 1,
-                    "total_sub_batches": 2,
-                }
-            ),
-            "completed",
-        )
-
-        child2_id = uuid.uuid4()
-        await conn.execute(
-            """
-            INSERT INTO async_operations (operation_id, bank_id, operation_type, result_metadata, status, error_message)
-            VALUES ($1, $2, $3, $4, $5, $6)
-            """,
-            child2_id,
-            bank_id,
-            "retain",
-            json.dumps(
-                {
-                    "items_count": 10,
-                    "parent_operation_id": str(parent_id),
-                    "sub_batch_index": 2,
-                    "total_sub_batches": 2,
-                }
-            ),
-            "failed",
-            "Test error",
-        )
-
-    # Check parent status
-    parent_status = await memory.get_operation_status(
-        bank_id=bank_id,
-        operation_id=str(parent_id),
-        request_context=request_context,
-    )
-
-    # Parent should aggregate as "failed" since one child failed
-    assert parent_status["status"] == "failed"
-    assert len(parent_status["child_operations"]) == 2
-
-    # Verify child with error is included
-    failed_child = [c for c in parent_status["child_operations"] if c["status"] == "failed"][0]
-    assert failed_child["error_message"] == "Test error"
-
-
-@pytest.mark.asyncio
-async def test_parent_operation_status_aggregation_completed(memory, request_context):
-    """Test that parent operation shows 'completed' when all children are completed."""
-    bank_id = "test_parent_completed"
-    pool = await memory._get_pool()
-
-    # Manually create a parent operation
-    parent_id = uuid.uuid4()
-    async with pool.acquire() as conn:
-        await conn.execute(
-            """
-            INSERT INTO async_operations (operation_id, bank_id, operation_type, result_metadata, status)
-            VALUES ($1, $2, $3, $4, $5)
-            """,
-            parent_id,
-            bank_id,
-            "batch_retain",
-            json.dumps({"items_count": 20, "num_sub_batches": 2, "is_parent": True}),
-            "pending",
-        )
-
-        # Create 2 child operations - both completed
-        child1_id = uuid.uuid4()
-        await conn.execute(
-            """
-            INSERT INTO async_operations (operation_id, bank_id, operation_type, result_metadata, status)
-            VALUES ($1, $2, $3, $4, $5)
-            """,
-            child1_id,
-            bank_id,
-            "retain",
-            json.dumps(
-                {
-                    "items_count": 10,
-                    "parent_operation_id": str(parent_id),
-                    "sub_batch_index": 1,
-                    "total_sub_batches": 2,
-                }
-            ),
-            "completed",
-        )
-
-        child2_id = uuid.uuid4()
-        await conn.execute(
-            """
-            INSERT INTO async_operations (operation_id, bank_id, operation_type, result_metadata, status)
-            VALUES ($1, $2, $3, $4, $5)
-            """,
-            child2_id,
-            bank_id,
-            "retain",
-            json.dumps(
-                {
-                    "items_count": 10,
-                    "parent_operation_id": str(parent_id),
-                    "sub_batch_index": 2,
-                    "total_sub_batches": 2,
-                }
-            ),
-            "completed",
-        )
-
-    # Check parent status
-    parent_status = await memory.get_operation_status(
-        bank_id=bank_id,
-        operation_id=str(parent_id),
-        request_context=request_context,
-    )
-
-    # Parent should aggregate as "completed" since all children are completed
-    assert parent_status["status"] == "completed"
-    assert len(parent_status["child_operations"]) == 2
-    assert all(c["status"] == "completed" for c in parent_status["child_operations"])
-
-
-@pytest.mark.asyncio
-async def test_config_retain_batch_tokens_respected(memory, request_context):
-    """Test that the retain_batch_tokens config setting is respected."""
-    from hindsight_api.config import get_config
-    from hindsight_api.engine.memory_engine import count_tokens
-
-    bank_id = "test_config_batch_tokens"
-    config = get_config()
-
-    # Check that config has the retain_batch_tokens setting
-    assert hasattr(config, "retain_batch_tokens")
-    assert config.retain_batch_tokens > 0
-
-    # Create a batch that's just under the threshold
-    # Use content that produces roughly half the token limit per item
-    content_size = config.retain_batch_tokens * 2  # chars (rough estimate: 1 token ~= 4 chars)
-    contents = [{"content": "A" * content_size, "document_id": f"doc{i}"} for i in range(2)]
-
-    total_tokens = sum(count_tokens(item["content"]) for item in contents)
-    # Should be equal to threshold (boundary case, no splitting since we use > not >=)
-    assert total_tokens <= config.retain_batch_tokens
-
-    # Submit - should NOT split
-    result = await memory.submit_async_retain(
-        bank_id=bank_id,
-        contents=contents,
-        request_context=request_context,
-    )
-
-    # Wait for completion
-    await asyncio.sleep(0.1)
-
-    # Check status - should be a parent with single child (even for small batches)
-    status = await memory.get_operation_status(
-        bank_id=bank_id,
-        operation_id=result["operation_id"],
-        request_context=request_context,
-    )
-
-    # Even small batches use parent-child pattern now (simpler code path)
-    assert "child_operations" in status
-    assert status["result_metadata"]["num_sub_batches"] == 1

hindsight-api/tests/test_async_retain_tags.py

@@ -1,93 +0,0 @@
-"""Unit tests for async retain tag propagation."""
-
-from unittest.mock import AsyncMock, MagicMock
-
-import pytest
-
-from hindsight_api.engine.memory_engine import MemoryEngine
-from hindsight_api.models import RequestContext
-
-
-@pytest.mark.asyncio
-async def test_submit_async_retain_includes_document_tags_in_task_payload():
-    """submit_async_retain should include document_tags in queued task payload."""
-    engine = MemoryEngine.__new__(MemoryEngine)
-    engine._initialized = True
-    engine._authenticate_tenant = AsyncMock()
-    engine._submit_async_operation = AsyncMock(return_value={"operation_id": "op-1"})
-
-    # Mock the pool and connection for parent operation creation
-    mock_conn = AsyncMock()
-    mock_conn.execute = AsyncMock()
-    mock_conn.transaction = MagicMock()
-    mock_conn.transaction.return_value.__aenter__ = AsyncMock()
-    mock_conn.transaction.return_value.__aexit__ = AsyncMock()
-
-    mock_pool = AsyncMock()
-    mock_pool.acquire = AsyncMock(return_value=mock_conn)
-    mock_pool.release = AsyncMock()
-
-    engine._get_pool = AsyncMock(return_value=mock_pool)
-
-    request_context = RequestContext(tenant_id="tenant-a", api_key_id="key-a")
-    contents = [{"content": "Async retain payload test."}]
-    document_tags = ["scope:tools", "user:alice"]
-
-    result = await MemoryEngine.submit_async_retain(
-        engine,
-        bank_id="bank-1",
-        contents=contents,
-        document_tags=document_tags,
-        request_context=request_context,
-    )
-
-    # Check result structure
-    assert "operation_id" in result
-    assert "items_count" in result
-    assert result["items_count"] == 1
-
-    # Verify authentication was called
-    engine._authenticate_tenant.assert_awaited_once_with(request_context)
-
-    # Verify child operation was submitted
-    engine._submit_async_operation.assert_awaited_once()
-
-    # Verify child operation payload contains document_tags
-    kwargs = engine._submit_async_operation.await_args.kwargs
-    assert kwargs["bank_id"] == "bank-1"
-    assert kwargs["operation_type"] == "retain"
-    assert kwargs["task_type"] == "batch_retain"
-    assert kwargs["task_payload"]["contents"] == contents
-    assert kwargs["task_payload"]["document_tags"] == document_tags
-    assert kwargs["task_payload"]["_tenant_id"] == "tenant-a"
-    assert kwargs["task_payload"]["_api_key_id"] == "key-a"
-
-
-@pytest.mark.asyncio
-async def test_handle_batch_retain_forwards_document_tags_to_retain_batch_async():
-    """Worker handler should forward document_tags from task payload."""
-    engine = MemoryEngine.__new__(MemoryEngine)
-    engine._initialized = True
-    engine.retain_batch_async = AsyncMock(return_value={"items_count": 1})
-
-    task_dict = {
-        "bank_id": "bank-1",
-        "contents": [{"content": "Forward tags test."}],
-        "document_tags": ["scope:client"],
-        "_tenant_id": "tenant-a",
-        "_api_key_id": "key-a",
-    }
-
-    await MemoryEngine._handle_batch_retain(engine, task_dict)
-
-    engine.retain_batch_async.assert_awaited_once()
-    kwargs = engine.retain_batch_async.await_args.kwargs
-    assert kwargs["bank_id"] == "bank-1"
-    assert kwargs["contents"] == task_dict["contents"]
-    assert kwargs["document_tags"] == ["scope:client"]
-
-    request_context = kwargs["request_context"]
-    assert request_context.internal is True
-    assert request_context.user_initiated is True
-    assert request_context.tenant_id == "tenant-a"
-    assert request_context.api_key_id == "key-a"

hindsight-api/tests/test_http_api_integration.py

@@ -528,7 +528,7 @@ async def test_delete_bank(api_client):
                 {
                     "content": "Bob is the CTO and leads the engineering team.",
                     "context": "team info",
-                    "document_id": "team-doc-2",
+                    "document_id": "team-doc-1",
                 },
             ]
         },

hindsight-api/tests/test_litellm_sdk_cross_encoder.py

@@ -1,392 +0,0 @@
-"""
-Tests for LiteLLMSDKCrossEncoder.
-
-Tests the LiteLLM SDK-based cross-encoder implementation for reranking.
-"""
-
-import os
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-from hindsight_api.engine.cross_encoder import LiteLLMSDKCrossEncoder, create_cross_encoder_from_env
-
-
-class TestLiteLLMSDKCrossEncoder:
-    """Test suite for LiteLLMSDKCrossEncoder class."""
-
-    @pytest.mark.asyncio
-    async def test_initialization_success(self):
-        """Test successful initialization with valid config."""
-        encoder = LiteLLMSDKCrossEncoder(
-            api_key="test_key",
-            model="deepinfra/Qwen3-reranker-8B",
-        )
-
-        assert encoder.provider_name == "litellm-sdk"
-        assert encoder.api_key == "test_key"
-        assert encoder.model == "deepinfra/Qwen3-reranker-8B"
-        assert encoder._initialized is False
-
-        # Mock the litellm import
-        mock_litellm = MagicMock()
-        with patch.dict("sys.modules", {"litellm": mock_litellm}):
-            await encoder.initialize()
-            assert encoder._initialized is True
-
-    @pytest.mark.asyncio
-    async def test_initialization_missing_package(self):
-        """Test initialization fails when litellm package is missing."""
-        encoder = LiteLLMSDKCrossEncoder(
-            api_key="test_key",
-            model="cohere/rerank-english-v3.0",
-        )
-
-        with patch.dict("sys.modules", {"litellm": None}):
-            with pytest.raises(ImportError, match="litellm is required"):
-                await encoder.initialize()
-
-    @pytest.mark.asyncio
-    async def test_initialization_idempotent(self):
-        """Test that calling initialize() multiple times is safe."""
-        encoder = LiteLLMSDKCrossEncoder(
-            api_key="test_key",
-            model="cohere/rerank-english-v3.0",
-        )
-
-        mock_litellm = MagicMock()
-        with patch.dict("sys.modules", {"litellm": mock_litellm}):
-            await encoder.initialize()
-            assert encoder._initialized is True
-
-            # Second call should be no-op
-            await encoder.initialize()
-            assert encoder._initialized is True
-
-    @pytest.mark.asyncio
-    async def test_predict_single_query(self):
-        """Test prediction with a single query and multiple documents."""
-        encoder = LiteLLMSDKCrossEncoder(
-            api_key="test_key",
-            model="deepinfra/Qwen3-reranker-8B",
-        )
-
-        # Create mock response with results as TypedDicts
-        mock_response = MagicMock()
-        mock_response.results = [
-            {"index": 0, "relevance_score": 0.9},
-            {"index": 1, "relevance_score": 0.7},
-            {"index": 2, "relevance_score": 0.5},
-        ]
-
-        mock_litellm = MagicMock()
-        mock_litellm.arerank = AsyncMock(return_value=mock_response)
-
-        with patch.dict("sys.modules", {"litellm": mock_litellm}):
-            await encoder.initialize()
-
-            pairs = [
-                ("What is Python?", "Python is a programming language"),
-                ("What is Python?", "Python is a snake"),
-                ("What is Python?", "Python is a British comedy group"),
-            ]
-
-            scores = await encoder.predict(pairs)
-
-            assert len(scores) == 3
-            assert scores == [0.9, 0.7, 0.5]
-
-            # Verify arerank was called correctly
-            mock_litellm.arerank.assert_called_once()
-            call_args = mock_litellm.arerank.call_args
-            assert call_args.kwargs["model"] == "deepinfra/Qwen3-reranker-8B"
-            assert call_args.kwargs["query"] == "What is Python?"
-            assert len(call_args.kwargs["documents"]) == 3
-            assert call_args.kwargs["api_key"] == "test_key"
-
-    @pytest.mark.asyncio
-    async def test_predict_multiple_queries(self):
-        """Test prediction with multiple different queries (grouped efficiently)."""
-        encoder = LiteLLMSDKCrossEncoder(
-            api_key="test_key",
-            model="cohere/rerank-english-v3.0",
-        )
-
-        # First query response
-        mock_response1 = MagicMock()
-        mock_response1.results = [
-            {"index": 0, "relevance_score": 0.9},
-            {"index": 1, "relevance_score": 0.7},
-        ]
-
-        # Second query response
-        mock_response2 = MagicMock()
-        mock_response2.results = [
-            {"index": 0, "relevance_score": 0.8},
-        ]
-
-        mock_litellm = MagicMock()
-        mock_litellm.arerank = AsyncMock(side_effect=[mock_response1, mock_response2])
-
-        with patch.dict("sys.modules", {"litellm": mock_litellm}):
-            await encoder.initialize()
-
-            pairs = [
-                ("What is Python?", "Python is a programming language"),
-                ("What is Python?", "Python is a snake"),
-                ("What is Java?", "Java is a programming language"),
-            ]
-
-            scores = await encoder.predict(pairs)
-
-            assert len(scores) == 3
-            assert scores[0] == 0.9  # First query, first doc
-            assert scores[1] == 0.7  # First query, second doc
-            assert scores[2] == 0.8  # Second query, first doc
-
-            # Verify arerank was called twice (once per unique query)
-            assert mock_litellm.arerank.call_count == 2
-
-    @pytest.mark.asyncio
-    async def test_predict_empty_pairs(self):
-        """Test prediction with empty input."""
-        encoder = LiteLLMSDKCrossEncoder(
-            api_key="test_key",
-            model="cohere/rerank-english-v3.0",
-        )
-
-        mock_litellm = MagicMock()
-        with patch.dict("sys.modules", {"litellm": mock_litellm}):
-            await encoder.initialize()
-            scores = await encoder.predict([])
-            assert scores == []
-
-    @pytest.mark.asyncio
-    async def test_predict_not_initialized(self):
-        """Test that predict fails if encoder not initialized."""
-        encoder = LiteLLMSDKCrossEncoder(
-            api_key="test_key",
-            model="cohere/rerank-english-v3.0",
-        )
-
-        pairs = [("query", "document")]
-
-        with pytest.raises(RuntimeError, match="not initialized"):
-            await encoder.predict(pairs)
-
-    @pytest.mark.asyncio
-    async def test_predict_error_handling(self):
-        """Test that errors during prediction are raised."""
-        encoder = LiteLLMSDKCrossEncoder(
-            api_key="test_key",
-            model="cohere/rerank-english-v3.0",
-        )
-
-        # Mock litellm to raise an error
-        mock_litellm = MagicMock()
-        mock_litellm.arerank = AsyncMock(side_effect=Exception("API Error"))
-
-        with patch.dict("sys.modules", {"litellm": mock_litellm}):
-            await encoder.initialize()
-
-            pairs = [
-                ("What is Python?", "Python is a programming language"),
-            ]
-
-            # Should raise the exception
-            with pytest.raises(Exception, match="API Error"):
-                await encoder.predict(pairs)
-
-    @pytest.mark.asyncio
-    async def test_custom_api_base(self):
-        """Test that custom API base URL is passed to rerank calls."""
-        encoder = LiteLLMSDKCrossEncoder(
-            api_key="test_key",
-            model="cohere/rerank-english-v3.0",
-            api_base="https://custom.api.example.com",
-        )
-
-        mock_response = MagicMock()
-        mock_response.results = [
-            {"index": 0, "relevance_score": 0.9},
-        ]
-
-        mock_litellm = MagicMock()
-        mock_litellm.arerank = AsyncMock(return_value=mock_response)
-
-        with patch.dict("sys.modules", {"litellm": mock_litellm}):
-            await encoder.initialize()
-
-            # Test that api_base is passed to arerank
-            pairs = [("query", "document")]
-            scores = await encoder.predict(pairs)
-
-            assert scores == [0.9]
-            mock_litellm.arerank.assert_called_once()
-            call_args = mock_litellm.arerank.call_args
-            assert call_args.kwargs["api_base"] == "https://custom.api.example.com"
-
-    @pytest.mark.asyncio
-    async def test_response_with_direct_score_list(self):
-        """Test handling of response format with direct score list."""
-        encoder = LiteLLMSDKCrossEncoder(
-            api_key="test_key",
-            model="some-provider/model",
-        )
-
-        # Mock litellm to return direct list of scores
-        mock_litellm = MagicMock()
-        mock_litellm.arerank = AsyncMock(return_value=[0.9, 0.7, 0.5])
-
-        with patch.dict("sys.modules", {"litellm": mock_litellm}):
-            await encoder.initialize()
-
-            pairs = [
-                ("query", "doc1"),
-                ("query", "doc2"),
-                ("query", "doc3"),
-            ]
-
-            scores = await encoder.predict(pairs)
-
-            assert scores == [0.9, 0.7, 0.5]
-
-
-class TestFactoryFunction:
-    """Test suite for create_cross_encoder_from_env factory function."""
-
-    @pytest.mark.asyncio
-    async def test_create_litellm_sdk_from_env(self):
-        """Test creating LiteLLM SDK cross-encoder from environment variables."""
-        env_vars = {
-            "HINDSIGHT_API_RERANKER_PROVIDER": "litellm-sdk",
-            "HINDSIGHT_API_RERANKER_LITELLM_SDK_API_KEY": "test_key",
-            "HINDSIGHT_API_RERANKER_LITELLM_SDK_MODEL": "deepinfra/Qwen3-reranker-8B",
-        }
-
-        with patch.dict(os.environ, env_vars, clear=False):
-            # Need to reload config to pick up env vars
-            from hindsight_api.config import HindsightConfig
-
-            config = HindsightConfig.from_env()
-
-            with patch("hindsight_api.config.get_config", return_value=config):
-                encoder = create_cross_encoder_from_env()
-
-                assert isinstance(encoder, LiteLLMSDKCrossEncoder)
-                assert encoder.api_key == "test_key"
-                assert encoder.model == "deepinfra/Qwen3-reranker-8B"
-
-    @pytest.mark.asyncio
-    async def test_create_litellm_sdk_missing_api_key(self):
-        """Test that factory raises error when API key is missing."""
-        env_vars = {
-            "HINDSIGHT_API_RERANKER_PROVIDER": "litellm-sdk",
-            "HINDSIGHT_API_RERANKER_LITELLM_SDK_MODEL": "deepinfra/Qwen3-reranker-8B",
-        }
-
-        with patch.dict(os.environ, env_vars, clear=False):
-            # Remove API key if set
-            if "HINDSIGHT_API_RERANKER_LITELLM_SDK_API_KEY" in os.environ:
-                del os.environ["HINDSIGHT_API_RERANKER_LITELLM_SDK_API_KEY"]
-
-            from hindsight_api.config import HindsightConfig
-
-            config = HindsightConfig.from_env()
-
-            with patch("hindsight_api.config.get_config", return_value=config):
-                with pytest.raises(ValueError, match="HINDSIGHT_API_RERANKER_LITELLM_SDK_API_KEY is required"):
-                    create_cross_encoder_from_env()
-
-    @pytest.mark.asyncio
-    async def test_create_litellm_sdk_with_custom_api_base(self):
-        """Test creating LiteLLM SDK cross-encoder with custom API base."""
-        env_vars = {
-            "HINDSIGHT_API_RERANKER_PROVIDER": "litellm-sdk",
-            "HINDSIGHT_API_RERANKER_LITELLM_SDK_API_KEY": "test_key",
-            "HINDSIGHT_API_RERANKER_LITELLM_SDK_MODEL": "cohere/rerank-english-v3.0",
-            "HINDSIGHT_API_RERANKER_LITELLM_SDK_API_BASE": "https://custom.api.example.com",
-        }
-
-        with patch.dict(os.environ, env_vars, clear=False):
-            from hindsight_api.config import HindsightConfig
-
-            config = HindsightConfig.from_env()
-
-            with patch("hindsight_api.config.get_config", return_value=config):
-                encoder = create_cross_encoder_from_env()
-
-                assert isinstance(encoder, LiteLLMSDKCrossEncoder)
-                assert encoder.api_base == "https://custom.api.example.com"
-
-
-class TestLiteLLMSDKCohereCrossEncoder:
-    """Tests for LiteLLM SDK calling Cohere (runs in CI with COHERE_API_KEY)."""
-
-    @pytest.fixture
-    async def litellm_cohere_cross_encoder(self):
-        """Create LiteLLM SDK cross-encoder instance for Cohere."""
-        if not os.environ.get("COHERE_API_KEY"):
-            pytest.skip("Cohere API key not available (set COHERE_API_KEY)")
-
-        encoder = LiteLLMSDKCrossEncoder(
-            api_key=os.environ["COHERE_API_KEY"],
-            model="cohere/rerank-english-v3.0",
-        )
-        await encoder.initialize()
-        return encoder
-
-    @pytest.mark.asyncio
-    async def test_litellm_sdk_cohere_initialization(self, litellm_cohere_cross_encoder):
-        """Test that LiteLLM SDK Cohere cross-encoder initializes correctly."""
-        assert litellm_cohere_cross_encoder.provider_name == "litellm-sdk"
-        assert litellm_cohere_cross_encoder.model == "cohere/rerank-english-v3.0"
-
-    @pytest.mark.asyncio
-    async def test_litellm_sdk_cohere_predict(self, litellm_cohere_cross_encoder):
-        """Test that LiteLLM SDK can call Cohere rerank API."""
-        pairs = [
-            ("What is the capital of France?", "Paris is the capital of France."),
-            ("What is the capital of France?", "The Eiffel Tower is in Paris."),
-            ("What is the capital of France?", "Python is a programming language."),
-        ]
-        scores = await litellm_cohere_cross_encoder.predict(pairs)
-
-        assert len(scores) == 3
-        assert all(isinstance(s, float) for s in scores)
-        # The first result should be most relevant
-        assert scores[0] > scores[2], "Direct answer should score higher than unrelated text"
-        # All scores should be in valid range
-        assert all(0.0 <= score <= 1.0 for score in scores)
-
-
-class TestIntegration:
-    """Integration tests with real API (optional - requires API keys)."""
-
-    @pytest.mark.skipif(
-        not os.environ.get("DEEPINFRA_API_KEY"),
-        reason="DEEPINFRA_API_KEY not set - skipping integration test",
-    )
-    @pytest.mark.asyncio
-    async def test_real_deepinfra_api(self):
-        """Test with real DeepInfra API (requires DEEPINFRA_API_KEY env var)."""
-        encoder = LiteLLMSDKCrossEncoder(
-            api_key=os.environ["DEEPINFRA_API_KEY"],
-            model="deepinfra/Qwen3-reranker-8B",
-        )
-
-        await encoder.initialize()
-
-        pairs = [
-            ("What is Python?", "Python is a high-level programming language"),
-            ("What is Python?", "Python is a species of snake"),
-            ("What is Python?", "Python is unrelated text about cars"),
-        ]
-
-        scores = await encoder.predict(pairs)
-
-        # First doc should have highest score (most relevant)
-        assert len(scores) == 3
-        assert scores[0] > scores[1]
-        assert scores[1] > scores[2]
-        assert all(0.0 <= score <= 1.0 for score in scores)

hindsight-api/tests/test_litellm_sdk_embeddings.py

@@ -1,387 +0,0 @@
-"""
-Tests for LiteLLM SDK embeddings implementation.
-
-These tests cover:
-1. Initialization (success, missing package, missing API key, idempotent)
-2. Encode (single text, multiple texts, batching, error handling)
-3. Provider-specific configuration (Cohere, OpenAI, etc.)
-4. Factory function (create from env, validation errors)
-5. Dimension detection
-"""
-
-import os
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-from hindsight_api.config import (
-    ENV_EMBEDDINGS_LITELLM_SDK_API_KEY,
-    ENV_EMBEDDINGS_LITELLM_SDK_MODEL,
-    ENV_EMBEDDINGS_PROVIDER,
-    HindsightConfig,
-)
-from hindsight_api.engine.embeddings import LiteLLMSDKEmbeddings, create_embeddings_from_env
-
-
-class TestLiteLLMSDKEmbeddings:
-    """Unit tests for LiteLLMSDKEmbeddings with mocked litellm responses."""
-
-    @pytest.fixture
-    def mock_litellm(self):
-        """Mock litellm module."""
-        mock = MagicMock()
-
-        # Mock aembedding (async) for initialization
-        mock_response = MagicMock()
-        mock_response.data = [{"embedding": [0.1] * 768, "index": 0}]
-        mock.aembedding = AsyncMock(return_value=mock_response)
-
-        # Mock embedding (sync) for encode
-        mock_sync_response = MagicMock()
-        mock_sync_response.data = [
-            {"embedding": [0.1] * 768, "index": 0},
-            {"embedding": [0.2] * 768, "index": 1},
-        ]
-        mock.embedding = MagicMock(return_value=mock_sync_response)
-
-        return mock
-
-    @pytest.fixture
-    async def embeddings(self, mock_litellm):
-        """Create initialized LiteLLMSDKEmbeddings instance."""
-        emb = LiteLLMSDKEmbeddings(
-            api_key="test_key",
-            model="cohere/embed-english-v3.0",
-            api_base=None,
-            batch_size=100,
-            timeout=60.0,
-        )
-        # Manually set the mock (simulating successful initialization)
-        emb._litellm = mock_litellm
-        emb._dimension = 768
-        return emb
-
-    async def test_initialization_success(self, mock_litellm):
-        """Test successful initialization."""
-        with patch("builtins.__import__", side_effect=lambda name, *args: mock_litellm if name == "litellm" else __import__(name, *args)):
-            emb = LiteLLMSDKEmbeddings(
-                api_key="test_key",
-                model="cohere/embed-english-v3.0",
-                api_base=None,
-                batch_size=100,
-                timeout=60.0,
-            )
-
-            assert emb._litellm is None
-            assert emb._dimension is None
-
-            await emb.initialize()
-
-            assert emb._litellm is not None
-            assert emb._dimension == 768
-
-            # Verify test embedding was called
-            mock_litellm.aembedding.assert_called_once_with(
-                model="cohere/embed-english-v3.0",
-                input=["test"],
-                api_key="test_key",
-            )
-
-    async def test_initialization_missing_package(self):
-        """Test initialization fails gracefully when litellm is not installed."""
-        def mock_import(name, *args):
-            if name == "litellm":
-                raise ImportError("No module named 'litellm'")
-            return __import__(name, *args)
-
-        with patch("builtins.__import__", side_effect=mock_import):
-            emb = LiteLLMSDKEmbeddings(
-                api_key="test_key",
-                model="cohere/embed-english-v3.0",
-                api_base=None,
-                batch_size=100,
-                timeout=60.0,
-            )
-
-            with pytest.raises(ImportError, match="litellm is required"):
-                await emb.initialize()
-
-    async def test_initialization_idempotent(self, embeddings, mock_litellm):
-        """Test that calling initialize() multiple times is safe."""
-        # embeddings._litellm is already set in fixture
-        assert embeddings._litellm is not None
-
-        # Call again
-        await embeddings.initialize()
-
-        # Should still have same litellm instance
-        assert embeddings._litellm is not None
-
-    async def test_encode_single_text(self, embeddings, mock_litellm):
-        """Test encoding a single text."""
-        # Set up mock response
-        mock_litellm.embedding.return_value.data = [
-            {"embedding": [0.5] * 768, "index": 0},
-        ]
-
-        result = embeddings.encode(["Hello world"])
-
-        assert isinstance(result, list)
-        assert len(result) == 1
-        assert len(result[0]) == 768
-        assert all(isinstance(x, float) for x in result[0])
-        assert all(abs(x - 0.5) < 0.001 for x in result[0])
-
-        # Verify call
-        mock_litellm.embedding.assert_called_once_with(
-            model="cohere/embed-english-v3.0",
-            input=["Hello world"],
-            api_key="test_key",
-        )
-
-    async def test_encode_multiple_texts(self, embeddings, mock_litellm):
-        """Test encoding multiple texts."""
-        # Set up mock response
-        mock_litellm.embedding.return_value.data = [
-            {"embedding": [0.1] * 768, "index": 0},
-            {"embedding": [0.2] * 768, "index": 1},
-            {"embedding": [0.3] * 768, "index": 2},
-        ]
-
-        texts = ["First text", "Second text", "Third text"]
-        result = embeddings.encode(texts)
-
-        assert isinstance(result, list)
-        assert len(result) == 3
-        assert len(result[0]) == 768
-        assert len(result[1]) == 768
-        assert len(result[2]) == 768
-        assert all(abs(x - 0.1) < 0.001 for x in result[0])
-        assert all(abs(x - 0.2) < 0.001 for x in result[1])
-        assert all(abs(x - 0.3) < 0.001 for x in result[2])
-
-    async def test_encode_batching(self, embeddings, mock_litellm):
-        """Test that large inputs are batched correctly."""
-        # Create embeddings with small batch size
-        emb = LiteLLMSDKEmbeddings(
-            api_key="test_key",
-            model="cohere/embed-english-v3.0",
-            api_base=None,
-            batch_size=2,  # Small batch for testing
-            timeout=60.0,
-        )
-        emb._litellm = mock_litellm
-        emb._initialized = True
-        emb._dimension = 768
-
-        # Mock responses for each batch
-        def mock_embedding_side_effect(model, input, **kwargs):
-            mock_response = MagicMock()
-            mock_response.data = [
-                {"embedding": [float(i)] * 768, "index": i} for i in range(len(input))
-            ]
-            return mock_response
-
-        mock_litellm.embedding.side_effect = mock_embedding_side_effect
-
-        # Encode 5 texts (should create 3 batches: 2, 2, 1)
-        texts = [f"Text {i}" for i in range(5)]
-        result = emb.encode(texts)
-
-        assert isinstance(result, list)
-        assert len(result) == 5
-        assert all(len(embedding) == 768 for embedding in result)
-
-        # Verify batching: should be called 3 times
-        assert mock_litellm.embedding.call_count == 3
-
-        # Verify batch sizes
-        calls = mock_litellm.embedding.call_args_list
-        assert len(calls[0][1]["input"]) == 2  # First batch
-        assert len(calls[1][1]["input"]) == 2  # Second batch
-        assert len(calls[2][1]["input"]) == 1  # Third batch
-
-    async def test_encode_empty_list(self, embeddings):
-        """Test encoding empty list returns empty list."""
-        result = embeddings.encode([])
-
-        assert isinstance(result, list)
-        assert len(result) == 0
-
-    async def test_encode_before_initialization(self, mock_litellm):
-        """Test that encode raises error if not initialized."""
-        emb = LiteLLMSDKEmbeddings(
-            api_key="test_key",
-            model="cohere/embed-english-v3.0",
-            api_base=None,
-            batch_size=100,
-            timeout=60.0,
-        )
-
-        with pytest.raises(RuntimeError, match="not initialized"):
-            emb.encode(["test"])
-
-    async def test_encode_error_handling(self, embeddings, mock_litellm):
-        """Test error handling during encoding."""
-        # Make embedding raise an error
-        mock_litellm.embedding.side_effect = Exception("API Error")
-
-        with pytest.raises(Exception, match="API Error"):
-            embeddings.encode(["test"])
-
-    async def test_dimension_property(self, embeddings):
-        """Test dimension property."""
-        assert embeddings.dimension == 768
-
-    async def test_dimension_before_initialization(self, mock_litellm):
-        """Test dimension raises error if not initialized."""
-        emb = LiteLLMSDKEmbeddings(
-            api_key="test_key",
-            model="cohere/embed-english-v3.0",
-            api_base=None,
-            batch_size=100,
-            timeout=60.0,
-        )
-
-        with pytest.raises(RuntimeError, match="not initialized"):
-            _ = emb.dimension
-
-    async def test_custom_api_base(self, mock_litellm):
-        """Test custom API base URL is passed to embedding calls."""
-        with patch("builtins.__import__", side_effect=lambda name, *args: mock_litellm if name == "litellm" else __import__(name, *args)):
-            emb = LiteLLMSDKEmbeddings(
-                api_key="test_key",
-                model="cohere/embed-english-v3.0",
-                api_base="https://custom.api.com",
-                batch_size=100,
-                timeout=60.0,
-            )
-
-            await emb.initialize()
-
-            # Verify api_base is set
-            assert emb.api_base == "https://custom.api.com"
-
-            # Verify api_base is passed to aembedding
-            mock_litellm.aembedding.assert_called_once()
-            call_args = mock_litellm.aembedding.call_args
-            assert call_args.kwargs["api_base"] == "https://custom.api.com"
-
-            # Test encode also passes api_base
-            mock_litellm.embedding.return_value.data = [{"embedding": [0.1] * 768, "index": 0}]
-            emb.encode(["test"])
-
-            mock_litellm.embedding.assert_called_once()
-            call_args = mock_litellm.embedding.call_args
-            assert call_args.kwargs["api_base"] == "https://custom.api.com"
-
-
-class TestLiteLLMSDKEmbeddingsFactory:
-    """Test the factory function for creating LiteLLM SDK embeddings."""
-
-    def test_create_from_env_success(self, monkeypatch):
-        """Test creating embeddings from environment variables."""
-        # Mock get_config() to return configured HindsightConfig
-        mock_config = MagicMock()
-        mock_config.embeddings_provider = "litellm-sdk"
-        mock_config.embeddings_litellm_sdk_api_key = "test_key"
-        mock_config.embeddings_litellm_sdk_model = "cohere/embed-english-v3.0"
-        mock_config.embeddings_litellm_sdk_api_base = None
-
-        with patch("hindsight_api.config.get_config", return_value=mock_config):
-            embeddings = create_embeddings_from_env()
-
-            assert isinstance(embeddings, LiteLLMSDKEmbeddings)
-            assert embeddings.api_key == "test_key"
-            assert embeddings.model == "cohere/embed-english-v3.0"
-
-    def test_create_from_env_missing_api_key(self, monkeypatch):
-        """Test that missing API key raises error."""
-        # Mock get_config() with missing API key
-        mock_config = MagicMock()
-        mock_config.embeddings_provider = "litellm-sdk"
-        mock_config.embeddings_litellm_sdk_api_key = None  # Missing key
-        mock_config.embeddings_litellm_sdk_model = "cohere/embed-english-v3.0"
-
-        with patch("hindsight_api.config.get_config", return_value=mock_config):
-            with pytest.raises(ValueError, match=ENV_EMBEDDINGS_LITELLM_SDK_API_KEY):
-                create_embeddings_from_env()
-
-    def test_create_from_env_with_api_base(self, monkeypatch):
-        """Test creating embeddings with custom API base."""
-        # Mock get_config() with custom API base
-        mock_config = MagicMock()
-        mock_config.embeddings_provider = "litellm-sdk"
-        mock_config.embeddings_litellm_sdk_api_key = "test_key"
-        mock_config.embeddings_litellm_sdk_model = "cohere/embed-english-v3.0"
-        mock_config.embeddings_litellm_sdk_api_base = "https://custom.api.com"
-
-        with patch("hindsight_api.config.get_config", return_value=mock_config):
-            embeddings = create_embeddings_from_env()
-
-            assert isinstance(embeddings, LiteLLMSDKEmbeddings)
-            assert embeddings.api_base == "https://custom.api.com"
-
-
-class TestLiteLLMSDKCohereEmbeddings:
-    """Integration tests calling real Cohere API (matches CI pattern)."""
-
-    @pytest.fixture
-    async def litellm_cohere_embeddings(self):
-        """Create embeddings instance with real Cohere API key."""
-        if not os.environ.get("COHERE_API_KEY"):
-            pytest.skip("Cohere API key not available")
-
-        emb = LiteLLMSDKEmbeddings(
-            api_key=os.environ["COHERE_API_KEY"],
-            model="cohere/embed-english-v3.0",
-            api_base=None,
-            batch_size=100,
-            timeout=60.0,
-        )
-        await emb.initialize()
-        return emb
-
-    @pytest.mark.asyncio
-    async def test_litellm_sdk_cohere_encode(self, litellm_cohere_embeddings):
-        """Test real Cohere API call for embeddings."""
-        texts = [
-            "The quick brown fox jumps over the lazy dog",
-            "Machine learning is a subset of artificial intelligence",
-            "Python is a popular programming language",
-        ]
-
-        result = litellm_cohere_embeddings.encode(texts)
-
-        # Verify result type and shape
-        assert isinstance(result, list)
-        assert len(result) == 3
-        assert all(len(embedding) > 0 for embedding in result)
-        assert all(isinstance(x, float) for x in result[0])
-
-        # Verify embeddings are not zeros (common API failure mode)
-        for i, embedding in enumerate(result):
-            assert not all(abs(x) < 0.0001 for x in embedding), f"Embedding {i} is all zeros"
-
-        # Verify embeddings are normalized (Cohere returns normalized vectors)
-        for i, embedding in enumerate(result):
-            norm = sum(x * x for x in embedding) ** 0.5
-            assert 0.9 < norm < 1.1, f"Embedding {i} norm {norm} is not close to 1.0"
-
-    @pytest.mark.asyncio
-    async def test_litellm_sdk_cohere_dimension(self, litellm_cohere_embeddings):
-        """Test dimension detection with real Cohere API."""
-        dimension = litellm_cohere_embeddings.dimension
-
-        # Cohere embed-english-v3.0 has 1024 dimensions
-        assert dimension == 1024
-
-    @pytest.mark.asyncio
-    async def test_litellm_sdk_cohere_single_text(self, litellm_cohere_embeddings):
-        """Test encoding single text with real Cohere API."""
-        result = litellm_cohere_embeddings.encode(["Hello world"])
-
-        assert isinstance(result, list)
-        assert len(result) == 1
-        assert len(result[0]) == 1024
-        assert not all(abs(x) < 0.0001 for x in result[0])

hindsight-api/tests/test_recall_chunks_independence.py

@@ -1,274 +0,0 @@
-"""
-Test that recall chunks are fetched independently of max_tokens filtering.
-
-This test verifies the new behavior where:
-1. Chunks are fetched BEFORE max_tokens filtering
-2. max_tokens=0 returns 0 facts but can still return chunks
-3. Chunks are fetched in batches to handle varying chunk sizes
-"""
-
-import pytest
-import pytest_asyncio
-
-from hindsight_api.engine.memory_engine import Budget
-
-
-@pytest.mark.asyncio
-async def test_recall_chunks_independent_of_max_tokens(memory, request_context):
-    """
-    Test that chunks are fetched independently of max_tokens.
-
-    When max_tokens=0, recall should:
-    - Return 0 memory facts
-    - Still return chunks (up to max_chunk_tokens)
-    - Chunks should come from top-scored results before token filtering
-    """
-    bank_id = "test-chunks-independence"
-
-    try:
-
-        # Retain some test content with substantial size to generate chunks
-        test_content = """
-        The quantum computing research team at MIT has made significant breakthroughs.
-        Dr. Sarah Chen leads the team and focuses on quantum error correction.
-        The team published three papers in Nature Physics this year.
-        Their work on topological qubits shows promise for scalable quantum computers.
-        Collaborators include IBM Research and Google Quantum AI.
-        The research is funded by a $5M NSF grant running through 2026.
-        """ * 10  # Repeat to ensure we get multiple chunks
-
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=test_content,
-            context="research notes",
-            request_context=request_context,
-        )
-
-        # Test 1: Normal recall with both facts and chunks
-        result_normal = await memory.recall_async(
-            bank_id=bank_id,
-            query="quantum computing",
-            max_tokens=4096,  # Normal token budget
-            include_chunks=True,
-            max_chunk_tokens=2000,
-            budget=Budget.MID,
-            request_context=request_context,
-        )
-
-        assert len(result_normal.results) > 0, "Should return memory facts with normal max_tokens"
-        assert result_normal.chunks is not None, "Should include chunks when requested"
-        assert len(result_normal.chunks) > 0, "Should return at least one chunk"
-
-        # Test 2: Recall with max_tokens=0 but chunks enabled
-        result_chunks_only = await memory.recall_async(
-            bank_id=bank_id,
-            query="quantum computing",
-            max_tokens=0,  # Zero token budget for facts
-            include_chunks=True,
-            max_chunk_tokens=2000,  # But allow chunks
-            budget=Budget.MID,
-            request_context=request_context,
-        )
-
-        # Key assertions for new behavior
-        assert len(result_chunks_only.results) == 0, "max_tokens=0 should return 0 facts"
-        assert result_chunks_only.chunks is not None, "Should still include chunks dict"
-        assert len(result_chunks_only.chunks) > 0, "Should return chunks even with max_tokens=0"
-
-        # Verify chunks are from the same content (non-empty text)
-        for chunk_id, chunk_info in result_chunks_only.chunks.items():
-            assert len(chunk_info.chunk_text) > 0, "Chunks should contain text"
-            assert chunk_info.chunk_index >= 0, "Chunk should have valid index"
-
-    finally:
-        # Cleanup
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_recall_chunks_batching_with_varying_sizes(memory, request_context):
-    """
-    Test that chunk batching works correctly with varying chunk sizes.
-
-    This verifies that:
-    1. Chunks are fetched in batches until token budget is exhausted
-    2. The system handles varying chunk sizes across documents
-    3. Token budget is respected across multiple batch fetches
-    """
-    bank_id = "test-chunks-batching"
-
-    try:
-
-        # Retain multiple documents with different content sizes
-        # Document 1: Short content (small chunks)
-        await memory.retain_async(
-            bank_id=bank_id,
-            content="Alice is a software engineer who specializes in Python programming and machine learning.",
-            context="doc1",
-            request_context=request_context,
-        )
-
-        # Document 2: Medium content
-        content_bob = """
-        Bob works as a data scientist at a tech startup in San Francisco.
-        He has expertise in natural language processing and computer vision.
-        Bob completed his PhD at Stanford University in 2020.
-        He leads a team of five engineers working on AI-powered recommendation systems.
-        """ * 5
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=content_bob,
-            context="doc2",
-            request_context=request_context,
-        )
-
-        # Document 3: Long content (large chunks)
-        content_charlie = """
-        Charlie is the CTO of a growing AI company focused on healthcare applications.
-        He has over 15 years of experience in software architecture and distributed systems.
-        Charlie's team builds machine learning models for medical image analysis and diagnosis.
-        The company recently raised $50 million in Series B funding.
-        They have partnerships with major hospitals in the United States and Europe.
-        Charlie holds several patents in medical imaging and deep learning.
-        """ * 20
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=content_charlie,
-            context="doc3",
-            request_context=request_context,
-        )
-
-        # Recall with modest chunk token budget
-        result = await memory.recall_async(
-            bank_id=bank_id,
-            query="Alice Bob Charlie",
-            max_tokens=0,  # No facts, only chunks
-            include_chunks=True,
-            max_chunk_tokens=1000,  # Limited chunk budget
-            budget=Budget.MID,
-            request_context=request_context,
-        )
-
-        assert len(result.results) == 0, "Should return 0 facts with max_tokens=0"
-        assert result.chunks is not None, "Should include chunks"
-
-        # Verify we got chunks and respected the token budget
-        if len(result.chunks) > 0:
-            # Count total tokens (approximate)
-            total_chunk_chars = sum(len(chunk.chunk_text) for chunk in result.chunks.values())
-            # Very rough estimate: 1 token ≈ 4 characters
-            estimated_tokens = total_chunk_chars // 4
-
-            # Should be reasonably close to budget (within 2x due to estimation and batching)
-            assert estimated_tokens <= 1000 * 2, f"Should respect chunk token budget (got ~{estimated_tokens} tokens)"
-
-    finally:
-        # Cleanup
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_recall_chunks_ordering_by_relevance(memory, request_context):
-    """
-    Test that chunks are returned in order of fact relevance.
-
-    Chunks should be ordered based on the top-scored (reranked) results,
-    not in document order or random order.
-    """
-    bank_id = "test-chunks-ordering"
-
-    try:
-
-        # Retain content with different relevance to query
-        await memory.retain_async(
-            bank_id=bank_id,
-            content="The Python programming language is widely used for machine learning and data science applications.",
-            context="topic: Python",
-            request_context=request_context,
-        )
-
-        await memory.retain_async(
-            bank_id=bank_id,
-            content="JavaScript is commonly used for web development and frontend applications.",
-            context="topic: JavaScript",
-            request_context=request_context,
-        )
-
-        await memory.retain_async(
-            bank_id=bank_id,
-            content="Python's scikit-learn library is excellent for traditional machine learning tasks and model training.",
-            context="topic: Python ML",
-            request_context=request_context,
-        )
-
-        # Query specifically about Python - should rank Python facts higher
-        result = await memory.recall_async(
-            bank_id=bank_id,
-            query="Python machine learning",
-            max_tokens=0,  # No facts
-            include_chunks=True,
-            max_chunk_tokens=5000,  # Enough for all chunks
-            budget=Budget.HIGH,  # Use high budget for better recall
-            request_context=request_context,
-        )
-
-        assert len(result.results) == 0, "Should return 0 facts with max_tokens=0"
-        assert result.chunks is not None, "Should include chunks"
-
-        # We should get chunks, and they should be ordered by relevance
-        # The exact ordering depends on the reranker, but we should have chunks
-        assert len(result.chunks) > 0, "Should return chunks from relevant facts"
-
-        # Verify chunks contain relevant content
-        all_chunk_text = " ".join(chunk.chunk_text for chunk in result.chunks.values())
-        # At least some chunks should mention Python (higher relevance)
-        # This is a soft check since exact ordering depends on scoring
-        assert "Python" in all_chunk_text or "python" in all_chunk_text.lower(), \
-            "Chunks should include content about Python (relevant to query)"
-
-    finally:
-        # Cleanup
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_recall_chunks_without_include_flag(memory, request_context):
-    """
-    Test that chunks are NOT returned when include_chunks=False (default).
-
-    This ensures backward compatibility - chunks are only fetched when explicitly requested.
-    """
-    bank_id = "test-chunks-no-include"
-
-    try:
-
-        # Retain content
-        test_content = """
-        Sarah is a product manager at a fintech company in New York.
-        She specializes in user experience design and agile methodologies.
-        Sarah graduated from MIT with a degree in computer science.
-        She has led the development of three successful mobile banking applications.
-        """
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=test_content,
-            request_context=request_context,
-        )
-
-        # Recall without include_chunks flag (default is False)
-        result = await memory.recall_async(
-            bank_id=bank_id,
-            query="Sarah product manager",
-            max_tokens=4096,
-            request_context=request_context,
-            # include_chunks=False is the default
-        )
-
-        # Should have facts but no chunks
-        assert len(result.results) > 0, "Should return facts"
-        assert result.chunks is None or len(result.chunks) == 0, \
-            "Should NOT return chunks when include_chunks=False"
-
-    finally:
-        # Cleanup
-        await memory.delete_bank(bank_id, request_context=request_context)

hindsight-cli/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "hindsight-cli"
-version = "0.4.11"
+version = "0.4.10"
 edition = "2021"
 authors = ["Hindsight Team"]
 description = "A beautiful CLI for Hindsight - semantic memory system"

hindsight-clients/python/.openapi-generator/FILES

@@ -24,7 +24,6 @@ hindsight_client_api/models/bank_profile_response.py
 hindsight_client_api/models/bank_stats_response.py
 hindsight_client_api/models/budget.py
 hindsight_client_api/models/cancel_operation_response.py
-hindsight_client_api/models/child_operation_status.py
 hindsight_client_api/models/chunk_data.py
 hindsight_client_api/models/chunk_include_options.py
 hindsight_client_api/models/chunk_response.py

hindsight-clients/python/hindsight_client_api/__init__.py

@@ -7,7 +7,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.
@@ -49,7 +49,6 @@ from hindsight_client_api.models.bank_profile_response import BankProfileRespons
 from hindsight_client_api.models.bank_stats_response import BankStatsResponse
 from hindsight_client_api.models.budget import Budget
 from hindsight_client_api.models.cancel_operation_response import CancelOperationResponse
-from hindsight_client_api.models.child_operation_status import ChildOperationStatus
 from hindsight_client_api.models.chunk_data import ChunkData
 from hindsight_client_api.models.chunk_include_options import ChunkIncludeOptions
 from hindsight_client_api.models.chunk_response import ChunkResponse

hindsight-clients/python/hindsight_client_api/api/banks_api.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/api/directives_api.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/api/documents_api.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/api/entities_api.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/api/memory_api.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/api/mental_models_api.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/api/monitoring_api.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/api/operations_api.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/api_client.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/configuration.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.
@@ -489,7 +489,7 @@ class Configuration:
         return "Python SDK Debug Report:\n"\
                "OS: {env}\n"\
                "Python Version: {pyversion}\n"\
-               "Version of the API: 0.4.11\n"\
+               "Version of the API: 0.4.10\n"\
                "SDK Package Version: 0.0.7".\
                format(env=sys.platform, pyversion=sys.version)
 

hindsight-clients/python/hindsight_client_api/exceptions.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/__init__.py

@@ -6,7 +6,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.
@@ -25,7 +25,6 @@ from hindsight_client_api.models.bank_profile_response import BankProfileRespons
 from hindsight_client_api.models.bank_stats_response import BankStatsResponse
 from hindsight_client_api.models.budget import Budget
 from hindsight_client_api.models.cancel_operation_response import CancelOperationResponse
-from hindsight_client_api.models.child_operation_status import ChildOperationStatus
 from hindsight_client_api.models.chunk_data import ChunkData
 from hindsight_client_api.models.chunk_include_options import ChunkIncludeOptions
 from hindsight_client_api.models.chunk_response import ChunkResponse

hindsight-clients/python/hindsight_client_api/models/add_background_request.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/async_operation_submit_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/background_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/bank_config_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/bank_config_update.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/bank_list_item.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/bank_list_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/bank_profile_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/bank_stats_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/budget.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/cancel_operation_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/child_operation_status.py

@@ -1,110 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.4.11
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, StrictInt, StrictStr
-from typing import Any, ClassVar, Dict, List, Optional
-from typing import Optional, Set
-from typing_extensions import Self
-
-class ChildOperationStatus(BaseModel):
-    """
-    Status of a child operation (for batch operations).
-    """ # noqa: E501
-    operation_id: StrictStr
-    status: StrictStr
-    sub_batch_index: Optional[StrictInt] = None
-    items_count: Optional[StrictInt] = None
-    error_message: Optional[StrictStr] = None
-    __properties: ClassVar[List[str]] = ["operation_id", "status", "sub_batch_index", "items_count", "error_message"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of ChildOperationStatus from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # set to None if sub_batch_index (nullable) is None
-        # and model_fields_set contains the field
-        if self.sub_batch_index is None and "sub_batch_index" in self.model_fields_set:
-            _dict['sub_batch_index'] = None
-
-        # set to None if items_count (nullable) is None
-        # and model_fields_set contains the field
-        if self.items_count is None and "items_count" in self.model_fields_set:
-            _dict['items_count'] = None
-
-        # set to None if error_message (nullable) is None
-        # and model_fields_set contains the field
-        if self.error_message is None and "error_message" in self.model_fields_set:
-            _dict['error_message'] = None
-
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of ChildOperationStatus from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "operation_id": obj.get("operation_id"),
-            "status": obj.get("status"),
-            "sub_batch_index": obj.get("sub_batch_index"),
-            "items_count": obj.get("items_count"),
-            "error_message": obj.get("error_message")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/chunk_data.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/chunk_include_options.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/chunk_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/consolidation_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/create_bank_request.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/create_directive_request.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/create_mental_model_request.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/create_mental_model_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/delete_document_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/delete_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/directive_list_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/directive_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/disposition_traits.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/document_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/entity_detail_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/entity_include_options.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/entity_input.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/entity_list_item.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/entity_list_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/entity_observation_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/entity_state_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/features_info.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/graph_data_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/http_validation_error.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/include_options.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/list_documents_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/list_memory_units_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/list_tags_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/memory_item.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/mental_model_list_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/mental_model_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/mental_model_trigger.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/operation_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/operation_status_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.
@@ -19,7 +19,6 @@ import json
 
 from pydantic import BaseModel, ConfigDict, StrictStr, field_validator
 from typing import Any, ClassVar, Dict, List, Optional
-from hindsight_client_api.models.child_operation_status import ChildOperationStatus
 from typing import Optional, Set
 from typing_extensions import Self
 
@@ -34,9 +33,7 @@ class OperationStatusResponse(BaseModel):
     updated_at: Optional[StrictStr] = None
     completed_at: Optional[StrictStr] = None
     error_message: Optional[StrictStr] = None
-    result_metadata: Optional[Dict[str, Any]] = None
-    child_operations: Optional[List[ChildOperationStatus]] = None
-    __properties: ClassVar[List[str]] = ["operation_id", "status", "operation_type", "created_at", "updated_at", "completed_at", "error_message", "result_metadata", "child_operations"]
+    __properties: ClassVar[List[str]] = ["operation_id", "status", "operation_type", "created_at", "updated_at", "completed_at", "error_message"]
 
     @field_validator('status')
     def status_validate_enum(cls, value):
@@ -84,13 +81,6 @@ class OperationStatusResponse(BaseModel):
             exclude=excluded_fields,
             exclude_none=True,
         )
-        # override the default output from pydantic by calling `to_dict()` of each item in child_operations (list)
-        _items = []
-        if self.child_operations:
-            for _item_child_operations in self.child_operations:
-                if _item_child_operations:
-                    _items.append(_item_child_operations.to_dict())
-            _dict['child_operations'] = _items
         # set to None if operation_type (nullable) is None
         # and model_fields_set contains the field
         if self.operation_type is None and "operation_type" in self.model_fields_set:
@@ -116,16 +106,6 @@ class OperationStatusResponse(BaseModel):
         if self.error_message is None and "error_message" in self.model_fields_set:
             _dict['error_message'] = None
 
-        # set to None if result_metadata (nullable) is None
-        # and model_fields_set contains the field
-        if self.result_metadata is None and "result_metadata" in self.model_fields_set:
-            _dict['result_metadata'] = None
-
-        # set to None if child_operations (nullable) is None
-        # and model_fields_set contains the field
-        if self.child_operations is None and "child_operations" in self.model_fields_set:
-            _dict['child_operations'] = None
-
         return _dict
 
     @classmethod
@@ -144,9 +124,7 @@ class OperationStatusResponse(BaseModel):
             "created_at": obj.get("created_at"),
             "updated_at": obj.get("updated_at"),
             "completed_at": obj.get("completed_at"),
-            "error_message": obj.get("error_message"),
-            "result_metadata": obj.get("result_metadata"),
-            "child_operations": [ChildOperationStatus.from_dict(_item) for _item in obj["child_operations"]] if obj.get("child_operations") is not None else None
+            "error_message": obj.get("error_message")
         })
         return _obj
 

hindsight-clients/python/hindsight_client_api/models/operations_list_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/recall_request.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/recall_response.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/recall_result.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/reflect_based_on.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/reflect_directive.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/reflect_fact.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/reflect_include_options.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/reflect_llm_call.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.

hindsight-clients/python/hindsight_client_api/models/reflect_mental_model.py

@@ -5,7 +5,7 @@
 
     HTTP API for Hindsight
 
-    The version of the OpenAPI document: 0.4.11
+    The version of the OpenAPI document: 0.4.10
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.