feat: add configs for database connection

* fix: duplicated causal relationships and token optimization

* doc

* doc

.github/workflows/test.yml

@@ -325,6 +325,7 @@ jobs:
       GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
       GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
       HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
       HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -5,7 +5,8 @@ build/
 dist/
 wheels/
 *.egg-info
-
+.mcp.json
+.osgrep
 # Virtual environments
 .venv
 
@@ -41,4 +42,8 @@ hindsight-docs/static/llms-full.txt
 hindsight-dev/benchmarks/locomo/results/
 hindsight-dev/benchmarks/longmemeval/results/
 hindsight-cli/target
-hindsight-clients/rust/target
+hindsight-clients/rust/target
+.claude
+whats-next.md
+TASK.md
+CHANGELOG.md

CLAUDE.md

@@ -4,7 +4,11 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 ## Project Overview
 
-Hindsight is an agent memory system that provides long-term memory for AI agents using biomimetic data structures. It stores memories as World facts, Experiences, Opinions, and Observations across memory banks.
+Hindsight is an agent memory system that provides long-term memory for AI agents using biomimetic data structures. Memories are organized as:
+- **World facts**: General knowledge ("The sky is blue")
+- **Experience facts**: Personal experiences ("I visited Paris in 2023")
+- **Opinion facts**: Beliefs with confidence scores ("Paris is beautiful" - 0.9 confidence)
+- **Observations**: Complex mental models derived from reflection
 
 ## Development Commands
 
@@ -13,14 +17,21 @@ Hindsight is an agent memory system that provides long-term memory for AI agents
 # Start API server (loads .env automatically)
 ./scripts/dev/start-api.sh
 
-# Run tests
+# Run all tests (parallelized with pytest-xdist)
 cd hindsight-api && uv run pytest tests/
 
 # Run specific test file
 cd hindsight-api && uv run pytest tests/test_http_api_integration.py -v
 
-# Lint
+# Run single test function
+cd hindsight-api && uv run pytest tests/test_retain.py::test_retain_simple -v
+
+# Lint and format
 cd hindsight-api && uv run ruff check .
+cd hindsight-api && uv run ruff format .
+
+# Type checking (uses ty - extremely fast type checker from Astral)
+cd hindsight-api && uv run ty check hindsight_api/
 ```
 
 ### Control Plane (Next.js)
@@ -37,7 +48,7 @@ cd hindsight-control-plane && npm run dev
 
 ### Generating Clients/OpenAPI
 ```bash
-# Regenerate OpenAPI spec after API changes
+# Regenerate OpenAPI spec after API changes (REQUIRED after changing endpoints)
 ./scripts/generate-openapi.sh
 
 # Regenerate all client SDKs (Python, TypeScript, Rust)
@@ -57,64 +68,64 @@ cd hindsight-control-plane && npm run dev
 - **hindsight-api/**: Core FastAPI server with memory engine (Python, uv)
 - **hindsight/**: Embedded Python bundle (hindsight-all package)
 - **hindsight-control-plane/**: Admin UI (Next.js, npm)
-- **hindsight-cli/**: CLI tool (Rust, cargo)
+- **hindsight-cli/**: CLI tool (Rust, cargo, uses progenitor for API client)
 - **hindsight-clients/**: Generated SDK clients (Python, TypeScript, Rust)
 - **hindsight-docs/**: Docusaurus documentation site
 - **hindsight-integrations/**: Framework integrations (LiteLLM, OpenAI)
 - **hindsight-dev/**: Development tools and benchmarks
 
 ### Core Engine (hindsight-api/hindsight_api/engine/)
-- `memory_engine.py`: Main orchestrator for retain/recall/reflect operations
+- `memory_engine.py`: Main orchestrator (~170KB) for retain/recall/reflect operations
 - `llm_wrapper.py`: LLM abstraction supporting OpenAI, Anthropic, Gemini, Groq, Ollama, LM Studio
-- `embeddings.py`: Embedding generation (local or TEI)
+- `embeddings.py`: Embedding generation (local sentence-transformers or TEI)
 - `cross_encoder.py`: Reranking (local or TEI)
 - `entity_resolver.py`: Entity extraction and normalization
 - `query_analyzer.py`: Query intent analysis
-- `retain/`: Memory ingestion pipeline
-- `search/`: Multi-strategy retrieval (semantic, BM25, graph, temporal)
+
+**retain/**: Memory ingestion pipeline
+- `orchestrator.py`: Coordinates the retain flow
+- `fact_extraction.py`: LLM-based fact extraction from content
+- `link_utils.py`: Entity link creation and management
+
+**search/**: Multi-strategy retrieval
+- `retrieval.py`: Main retrieval orchestrator
+- `graph_retrieval.py`: Entity/relationship graph traversal
+- `mpfp_retrieval.py`: Multi-Path Fact Propagation retrieval
+- `fusion.py`: Reciprocal rank fusion for combining results
+- `reranking.py`: Cross-encoder reranking
 
 ### API Layer (hindsight-api/hindsight_api/api/)
-FastAPI routers for all endpoints. Main operations:
+- `http.py`: FastAPI HTTP routers (~80KB) for all REST endpoints
+- `mcp.py`: Model Context Protocol server implementation
+
+Main operations:
 - **Retain**: Store memories, extracts facts/entities/relationships
-- **Recall**: Retrieve memories via parallel search strategies + reranking
-- **Reflect**: Deep analysis forming new opinions/observations
+- **Recall**: Retrieve memories via 4 parallel strategies (semantic, BM25, graph, temporal) + reranking
+- **Reflect**: Deep analysis forming new opinions/observations (disposition-aware)
 
 ### Database
 PostgreSQL with pgvector. Schema managed via Alembic migrations in `hindsight-api/hindsight_api/alembic/`. Migrations run automatically on API startup.
 
 Key tables: `banks`, `memory_units`, `documents`, `entities`, `entity_links`
 
-### Database Backups (IMPORTANT)
-**Before any operation that may affect the database, run a backup:**
-```bash
-docker exec hindsight /backups/backup.sh
-```
-
-Operations requiring backup:
-- Running database migrations
-- Modifying Alembic migration files
-- Rebuilding Docker images
-- Resetting or recreating containers
-- Any schema changes
-- Bulk data operations
-
-Backups are stored in `~/hindsight-backups/` on the host.
-
-To restore:
-```bash
-docker exec -it hindsight /backups/restore.sh <backup-file.sql.gz>
-```
-
 ## Key Conventions
 
+### Code Quality
+**Always run the lint script after making Python or TypeScript/Node changes:**
+```bash
+./scripts/hooks/lint.sh
+```
+This runs the same checks as the pre-commit hook (Ruff for Python, ESLint/Prettier for TypeScript).
+
 ### Memory Banks
-- Each bank is isolated (no cross-bank data access)
+- Each bank is an isolated memory store (like a "brain" for one user/agent)
 - Banks have dispositions (skepticism, literalism, empathy traits 1-5) affecting reflect
 - Banks can have background context
+- Bank isolation is strict - no cross-bank data leakage
 
 ### API Design
 - All endpoints operate on a single bank per request
-- Multi-bank queries are client responsibility
+- Multi-bank queries are client responsibility to orchestrate
 - Disposition traits only affect reflect, not recall
 
 ### Python Style
@@ -122,11 +133,35 @@ docker exec -it hindsight /backups/restore.sh <backup-file.sql.gz>
 - Async throughout (asyncpg, async FastAPI)
 - Pydantic models for request/response
 - Ruff for linting (line-length 120)
+- No Python files at project root - maintain clean directory structure
 
 ### TypeScript Style
 - Next.js App Router for control plane
 - Tailwind CSS with shadcn/ui components
 
+### Adding New API Configuration Flags
+
+When adding a new environment variable configuration:
+
+1. **config.py** (`hindsight-api/hindsight_api/config.py`):
+   - Add `ENV_*` constant for the environment variable name
+   - Add `DEFAULT_*` constant for the default value
+   - Add field to `HindsightConfig` dataclass
+   - Add initialization in `from_env()` method
+
+2. **main.py** (`hindsight-api/hindsight_api/main.py`):
+   - Add field to the manual `HindsightConfig()` constructor call (search for "CLI override")
+
+3. **Use the config** in code:
+   ```python
+   from ...config import get_config
+   config = get_config()
+   value = config.your_new_field
+   ```
+
+4. **Documentation** (`hindsight-docs/docs/developer/configuration.md`):
+   - Add to appropriate section table with Variable, Description, Default
+
 ## Environment Setup
 
 ```bash
@@ -136,7 +171,7 @@ cp .env.example .env
 # Python deps
 uv sync --directory hindsight-api/
 
-# Node deps (workspace)
+# Node deps (uses npm workspaces)
 npm install
 ```
 
@@ -144,3 +179,8 @@ Required env vars:
 - `HINDSIGHT_API_LLM_PROVIDER`: openai, anthropic, gemini, groq, ollama, lmstudio
 - `HINDSIGHT_API_LLM_API_KEY`: Your API key
 - `HINDSIGHT_API_LLM_MODEL`: Model name (e.g., o3-mini, claude-sonnet-4-20250514)
+
+Optional (uses local models by default):
+- `HINDSIGHT_API_EMBEDDINGS_PROVIDER`: local (default) or tei
+- `HINDSIGHT_API_RERANKER_PROVIDER`: local (default) or tei
+- `HINDSIGHT_API_DATABASE_URL`: External PostgreSQL (uses embedded pg0 by default)

helm/hindsight/templates/_helpers.tpl

@@ -110,3 +110,14 @@ API URL for control plane
 {{- define "hindsight.apiUrl" -}}
 {{- printf "http://%s-api:%d" (include "hindsight.fullname" .) (.Values.api.service.port | int) }}
 {{- end }}
+
+{{/*
+Get the name of the secret to use
+*/}}
+{{- define "hindsight.secretName" -}}
+{{- if .Values.existingSecret }}
+{{- .Values.existingSecret }}
+{{- else }}
+{{- printf "%s-secret" (include "hindsight.fullname" .) }}
+{{- end }}
+{{- end }}

helm/hindsight/templates/api-deployment.yaml

@@ -15,7 +15,9 @@ spec:
   template:
     metadata:
       annotations:
+        {{- if not .Values.existingSecret }}
         checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }}
+        {{- end }}
         {{- with .Values.podAnnotations }}
         {{- toYaml . | nindent 8 }}
         {{- end }}
@@ -37,27 +39,36 @@ spec:
         - name: http
           containerPort: {{ .Values.api.service.targetPort }}
           protocol: TCP
+        {{- if .Values.existingSecret }}
+        envFrom:
+        - secretRef:
+            name: {{ .Values.existingSecret }}
+        {{- end }}
         env:
-        - name: HINDSIGHT_API_DATABASE_URL
-          value: {{ include "hindsight.databaseUrl" . | quote }}
+        {{- /* POSTGRES_PASSWORD must be defined before DATABASE_URL for $(VAR) interpolation */}}
         {{- if not .Values.postgresql.enabled }}
         - name: POSTGRES_PASSWORD
           valueFrom:
             secretKeyRef:
-              name: {{ include "hindsight.fullname" . }}-secret
+              name: {{ include "hindsight.secretName" . }}
               key: postgres-password
         {{- end }}
+        - name: HINDSIGHT_API_DATABASE_URL
+          value: {{ include "hindsight.databaseUrl" . | quote }}
         {{- range $key, $value := .Values.api.env }}
         - name: {{ $key }}
           value: {{ $value | quote }}
         {{- end }}
+        {{- /* Only use api.secrets when not using existingSecret (for chart-managed secrets) */}}
+        {{- if not .Values.existingSecret }}
         {{- range $key, $value := .Values.api.secrets }}
         - name: {{ $key }}
           valueFrom:
             secretKeyRef:
-              name: {{ include "hindsight.fullname" $ }}-secret
+              name: {{ include "hindsight.secretName" $ }}
               key: {{ $key }}
         {{- end }}
+        {{- end }}
         livenessProbe:
           {{- toYaml .Values.api.livenessProbe | nindent 10 }}
         readinessProbe:

helm/hindsight/templates/controlplane-deployment.yaml

@@ -15,7 +15,9 @@ spec:
   template:
     metadata:
       annotations:
+        {{- if not .Values.existingSecret }}
         checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }}
+        {{- end }}
         {{- with .Values.podAnnotations }}
         {{- toYaml . | nindent 8 }}
         {{- end }}
@@ -37,6 +39,11 @@ spec:
         - name: http
           containerPort: {{ .Values.controlPlane.service.targetPort }}
           protocol: TCP
+        {{- if .Values.existingSecret }}
+        envFrom:
+        - secretRef:
+            name: {{ .Values.existingSecret }}
+        {{- end }}
         env:
         - name: HINDSIGHT_CP_DATAPLANE_API_URL
           value: {{ include "hindsight.apiUrl" . | quote }}
@@ -44,13 +51,16 @@ spec:
         - name: {{ $key }}
           value: {{ $value | quote }}
         {{- end }}
+        {{- /* Only use controlPlane.secrets when not using existingSecret (for chart-managed secrets) */}}
+        {{- if not .Values.existingSecret }}
         {{- range $key, $value := .Values.controlPlane.secrets }}
         - name: {{ $key }}
           valueFrom:
             secretKeyRef:
-              name: {{ include "hindsight.fullname" $ }}-secret
+              name: {{ include "hindsight.secretName" $ }}
               key: {{ $key }}
         {{- end }}
+        {{- end }}
         livenessProbe:
           {{- toYaml .Values.controlPlane.livenessProbe | nindent 10 }}
         readinessProbe:

helm/hindsight/templates/secret.yaml

@@ -1,7 +1,8 @@
+{{- if not .Values.existingSecret }}
 apiVersion: v1
 kind: Secret
 metadata:
-  name: {{ include "hindsight.fullname" . }}-secret
+  name: {{ include "hindsight.secretName" . }}
   labels:
     {{- include "hindsight.labels" . | nindent 4 }}
 type: Opaque
@@ -15,3 +16,4 @@ data:
   {{- if and (not .Values.postgresql.enabled) .Values.postgresql.external.password }}
   postgres-password: {{ .Values.postgresql.external.password | b64enc | quote }}
   {{- end }}
+{{- end }}

helm/hindsight/values.yaml

@@ -3,6 +3,15 @@
 # Chart version - use this to set a consistent image tag across all components
 version: "0.1.1"
 
+# Use an existing secret instead of creating one from values
+# When set, all keys from this secret are injected as environment variables via envFrom
+# Required keys:
+#   - postgres-password: PostgreSQL password (when postgresql.enabled=false)
+# Optional keys (any key becomes an env var):
+#   - HINDSIGHT_API_LLM_API_KEY: API key for LLM provider
+#   - Any other env vars you want to inject
+# existingSecret: "my-hindsight-secret"
+
 # Global settings
 replicaCount: 1
 

hindsight-api/hindsight_api/admin/__init__.py

@@ -0,0 +1 @@
+# Admin CLI for Hindsight

hindsight-api/hindsight_api/admin/cli.py

@@ -0,0 +1,252 @@
+"""
+Hindsight Admin CLI - backup and restore operations.
+"""
+
+import asyncio
+import io
+import json
+import logging
+import zipfile
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any
+
+import asyncpg
+import typer
+
+from ..config import HindsightConfig
+from ..pg0 import parse_pg0_url, resolve_database_url
+
+
+def _fq_table(table: str, schema: str) -> str:
+    """Get fully-qualified table name with schema prefix."""
+    return f"{schema}.{table}"
+
+
+# Setup logging
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(message)s",
+)
+logger = logging.getLogger(__name__)
+
+app = typer.Typer(name="hindsight-admin", help="Hindsight administrative commands")
+
+# Tables to backup/restore in dependency order
+# Import must happen in this order due to foreign key constraints
+BACKUP_TABLES = [
+    "banks",
+    "documents",
+    "entities",
+    "chunks",
+    "memory_units",
+    "unit_entities",
+    "entity_cooccurrences",
+    "memory_links",
+]
+
+MANIFEST_VERSION = "1"
+
+
+async def _backup(database_url: str, output_path: Path, schema: str = "public") -> dict[str, Any]:
+    """Backup all tables to a zip file using binary COPY protocol."""
+    conn = await asyncpg.connect(database_url)
+    try:
+        tables: dict[str, Any] = {}
+        manifest: dict[str, Any] = {
+            "version": MANIFEST_VERSION,
+            "created_at": datetime.now(timezone.utc).isoformat(),
+            "schema": schema,
+            "tables": tables,
+        }
+
+        # Use a transaction with REPEATABLE READ isolation to get a consistent
+        # snapshot across all tables. This prevents race conditions where
+        # entity_cooccurrences could reference entities created after the
+        # entities table was backed up.
+        async with conn.transaction(isolation="repeatable_read"):
+            with zipfile.ZipFile(output_path, "w", zipfile.ZIP_DEFLATED) as zf:
+                for i, table in enumerate(BACKUP_TABLES, 1):
+                    typer.echo(f"  [{i}/{len(BACKUP_TABLES)}] Backing up {table}...", nl=False)
+
+                    buffer = io.BytesIO()
+
+                    # Use binary COPY for exact type preservation
+                    # asyncpg requires schema_name as separate parameter
+                    await conn.copy_from_table(table, schema_name=schema, output=buffer, format="binary")
+
+                    data = buffer.getvalue()
+                    zf.writestr(f"{table}.bin", data)
+
+                    # Get row count for manifest
+                    qualified_table = _fq_table(table, schema)
+                    row_count = await conn.fetchval(f"SELECT COUNT(*) FROM {qualified_table}")
+                    tables[table] = {
+                        "rows": row_count,
+                        "size_bytes": len(data),
+                    }
+
+                    typer.echo(f" {row_count} rows")
+
+                zf.writestr("manifest.json", json.dumps(manifest, indent=2))
+
+        return manifest
+    finally:
+        await conn.close()
+
+
+async def _restore(database_url: str, input_path: Path, schema: str = "public") -> dict[str, Any]:
+    """Restore all tables from a zip file using binary COPY protocol."""
+    conn = await asyncpg.connect(database_url)
+    try:
+        with zipfile.ZipFile(input_path, "r") as zf:
+            # Read and validate manifest
+            manifest: dict[str, Any] = json.loads(zf.read("manifest.json"))
+            if manifest.get("version") != MANIFEST_VERSION:
+                raise ValueError(f"Unsupported backup version: {manifest.get('version')}")
+
+            # Use a transaction for atomic restore - either all tables are
+            # restored or none are, preventing partial/inconsistent state.
+            async with conn.transaction():
+                typer.echo("  Clearing existing data...")
+                # Truncate tables in reverse order (respects FK constraints)
+                for table in reversed(BACKUP_TABLES):
+                    qualified_table = _fq_table(table, schema)
+                    await conn.execute(f"TRUNCATE TABLE {qualified_table} CASCADE")
+
+                # Restore tables in forward order
+                for i, table in enumerate(BACKUP_TABLES, 1):
+                    filename = f"{table}.bin"
+                    if filename not in zf.namelist():
+                        typer.echo(f"  [{i}/{len(BACKUP_TABLES)}] {table}: skipped (not in backup)")
+                        continue
+
+                    expected_rows = manifest["tables"].get(table, {}).get("rows", "?")
+                    typer.echo(f"  [{i}/{len(BACKUP_TABLES)}] Restoring {table}... {expected_rows} rows")
+
+                    data = zf.read(filename)
+                    buffer = io.BytesIO(data)
+                    # asyncpg requires schema_name as separate parameter
+                    await conn.copy_to_table(table, schema_name=schema, source=buffer, format="binary")
+
+                # Refresh materialized view
+                typer.echo("  Refreshing materialized views...")
+                await conn.execute(f"REFRESH MATERIALIZED VIEW {_fq_table('memory_units_bm25', schema)}")
+
+        return manifest
+    finally:
+        await conn.close()
+
+
+async def _run_backup(db_url: str, output: Path, schema: str = "public") -> dict[str, Any]:
+    """Resolve database URL and run backup."""
+    is_pg0, instance_name, _ = parse_pg0_url(db_url)
+    if is_pg0:
+        typer.echo(f"Starting embedded PostgreSQL (instance: {instance_name})...")
+    resolved_url = await resolve_database_url(db_url)
+    return await _backup(resolved_url, output, schema)
+
+
+async def _run_restore(db_url: str, input_file: Path, schema: str = "public") -> dict[str, Any]:
+    """Resolve database URL and run restore."""
+    is_pg0, instance_name, _ = parse_pg0_url(db_url)
+    if is_pg0:
+        typer.echo(f"Starting embedded PostgreSQL (instance: {instance_name})...")
+    resolved_url = await resolve_database_url(db_url)
+    return await _restore(resolved_url, input_file, schema)
+
+
+@app.command()
+def backup(
+    output: Path = typer.Argument(..., help="Output file path (.zip)"),
+    schema: str = typer.Option("public", "--schema", "-s", help="Database schema to backup"),
+):
+    """Backup the Hindsight database to a zip file."""
+    config = HindsightConfig.from_env()
+
+    if not config.database_url:
+        typer.echo("Error: Database URL not configured.", err=True)
+        typer.echo("Set HINDSIGHT_API_DATABASE_URL environment variable.", err=True)
+        raise typer.Exit(1)
+
+    if output.suffix != ".zip":
+        output = output.with_suffix(".zip")
+
+    typer.echo(f"Backing up database (schema: {schema}) to {output}...")
+
+    manifest = asyncio.run(_run_backup(config.database_url, output, schema))
+
+    total_rows = sum(t["rows"] for t in manifest["tables"].values())
+    typer.echo(f"Backed up {total_rows} rows across {len(BACKUP_TABLES)} tables")
+    typer.echo(f"Backup saved to {output}")
+
+
+@app.command()
+def restore(
+    input_file: Path = typer.Argument(..., help="Input backup file (.zip)"),
+    schema: str = typer.Option("public", "--schema", "-s", help="Database schema to restore to"),
+    yes: bool = typer.Option(False, "--yes", "-y", help="Skip confirmation prompt"),
+):
+    """Restore the database from a backup file. WARNING: This deletes all existing data."""
+    config = HindsightConfig.from_env()
+
+    if not config.database_url:
+        typer.echo("Error: Database URL not configured.", err=True)
+        typer.echo("Set HINDSIGHT_API_DATABASE_URL environment variable.", err=True)
+        raise typer.Exit(1)
+
+    if not input_file.exists():
+        typer.echo(f"Error: File not found: {input_file}", err=True)
+        raise typer.Exit(1)
+
+    if not yes:
+        typer.confirm(
+            "This will DELETE all existing data and replace it with the backup. Continue?",
+            abort=True,
+        )
+
+    typer.echo(f"Restoring database (schema: {schema}) from {input_file}...")
+
+    manifest = asyncio.run(_run_restore(config.database_url, input_file, schema))
+
+    total_rows = sum(t["rows"] for t in manifest["tables"].values())
+    typer.echo(f"Restored {total_rows} rows across {len(BACKUP_TABLES)} tables")
+    typer.echo("Restore complete")
+
+
+async def _run_migration(db_url: str, schema: str = "public") -> None:
+    """Resolve database URL and run migrations."""
+    from ..migrations import run_migrations
+
+    is_pg0, instance_name, _ = parse_pg0_url(db_url)
+    if is_pg0:
+        typer.echo(f"Starting embedded PostgreSQL (instance: {instance_name})...")
+    resolved_url = await resolve_database_url(db_url)
+    run_migrations(resolved_url, schema=schema)
+
+
+@app.command(name="run-db-migration")
+def run_db_migration(
+    schema: str = typer.Option("public", "--schema", "-s", help="Database schema to run migrations on"),
+):
+    """Run database migrations to the latest version."""
+    config = HindsightConfig.from_env()
+
+    if not config.database_url:
+        typer.echo("Error: Database URL not configured.", err=True)
+        typer.echo("Set HINDSIGHT_API_DATABASE_URL environment variable.", err=True)
+        raise typer.Exit(1)
+
+    typer.echo(f"Running database migrations (schema: {schema})...")
+
+    asyncio.run(_run_migration(config.database_url, schema))
+
+    typer.echo("Database migrations completed successfully")
+
+
+def main():
+    app()
+
+
+if __name__ == "__main__":
+    main()

hindsight-api/hindsight_api/api/http.py

@@ -36,7 +36,7 @@ from pydantic import BaseModel, ConfigDict, Field, field_validator
 from hindsight_api import MemoryEngine
 from hindsight_api.engine.db_utils import acquire_with_retry
 from hindsight_api.engine.memory_engine import Budget, fq_table
-from hindsight_api.engine.response_models import VALID_RECALL_FACT_TYPES
+from hindsight_api.engine.response_models import VALID_RECALL_FACT_TYPES, TokenUsage
 from hindsight_api.extensions import HttpExtension, OperationValidationError, load_extension
 from hindsight_api.metrics import create_metrics_collector, get_metrics_collector, initialize_metrics
 from hindsight_api.models import RequestContext
@@ -364,7 +364,15 @@ class RetainResponse(BaseModel):
 
     model_config = ConfigDict(
         populate_by_name=True,
-        json_schema_extra={"example": {"success": True, "bank_id": "user123", "items_count": 2, "async": False}},
+        json_schema_extra={
+            "example": {
+                "success": True,
+                "bank_id": "user123",
+                "items_count": 2,
+                "async": False,
+                "usage": {"input_tokens": 500, "output_tokens": 100, "total_tokens": 600},
+            }
+        },
     )
 
     success: bool
@@ -373,6 +381,10 @@ class RetainResponse(BaseModel):
     is_async: bool = Field(
         alias="async", serialization_alias="async", description="Whether the operation was processed asynchronously"
     )
+    usage: TokenUsage | None = Field(
+        default=None,
+        description="Token usage metrics for LLM calls during fact extraction (only present for synchronous operations)",
+    )
 
 
 class FactsIncludeOptions(BaseModel):
@@ -472,6 +484,7 @@ class ReflectResponse(BaseModel):
                     "summary": "AI is transformative",
                     "key_points": ["Used in healthcare", "Discussed recently"],
                 },
+                "usage": {"input_tokens": 1500, "output_tokens": 500, "total_tokens": 2000},
             }
         }
     )
@@ -482,6 +495,10 @@ class ReflectResponse(BaseModel):
         default=None,
         description="Structured output parsed according to the request's response_schema. Only present when response_schema was provided in the request.",
     )
+    usage: TokenUsage | None = Field(
+        default=None,
+        description="Token usage metrics for LLM calls during reflection.",
+    )
 
 
 class BanksResponse(BaseModel):
@@ -630,6 +647,7 @@ class GraphDataResponse(BaseModel):
                     }
                 ],
                 "total_units": 2,
+                "limit": 1000,
             }
         }
     )
@@ -638,6 +656,7 @@ class GraphDataResponse(BaseModel):
     edges: list[dict[str, Any]]
     table_rows: list[dict[str, Any]]
     total_units: int
+    limit: int
 
 
 class ListMemoryUnitsResponse(BaseModel):
@@ -1049,16 +1068,19 @@ def _register_routes(app: FastAPI):
         "/v1/default/banks/{bank_id}/graph",
         response_model=GraphDataResponse,
         summary="Get memory graph data",
-        description="Retrieve graph data for visualization, optionally filtered by type (world/experience/opinion). Limited to 1000 most recent items.",
+        description="Retrieve graph data for visualization, optionally filtered by type (world/experience/opinion).",
         operation_id="get_graph",
         tags=["Memory"],
     )
     async def api_graph(
-        bank_id: str, type: str | None = None, request_context: RequestContext = Depends(get_request_context)
+        bank_id: str,
+        type: str | None = None,
+        limit: int = 1000,
+        request_context: RequestContext = Depends(get_request_context),
     ):
         """Get graph data from database, filtered by bank_id and optionally by type."""
         try:
-            data = await app.state.memory.get_graph_data(bank_id, type, request_context=request_context)
+            data = await app.state.memory.get_graph_data(bank_id, type, limit=limit, request_context=request_context)
             return data
         except (AuthenticationError, HTTPException):
             raise
@@ -1290,6 +1312,7 @@ def _register_routes(app: FastAPI):
                 text=core_result.text,
                 based_on=based_on_facts,
                 structured_output=core_result.structured_output,
+                usage=core_result.usage,
             )
 
         except OperationValidationError as e:
@@ -2016,12 +2039,12 @@ def _register_routes(app: FastAPI):
             else:
                 # Synchronous processing: wait for completion (record metrics)
                 with metrics.record_operation("retain", bank_id=bank_id):
-                    result = await app.state.memory.retain_batch_async(
-                        bank_id=bank_id, contents=contents, request_context=request_context
+                    result, usage = await app.state.memory.retain_batch_async(
+                        bank_id=bank_id, contents=contents, request_context=request_context, return_usage=True
                     )
 
                 return RetainResponse.model_validate(
-                    {"success": True, "bank_id": bank_id, "items_count": len(contents), "async": False}
+                    {"success": True, "bank_id": bank_id, "items_count": len(contents), "async": False, "usage": usage}
                 )
         except OperationValidationError as e:
             raise HTTPException(status_code=e.status_code, detail=e.reason)

hindsight-api/hindsight_api/api/mcp.py

@@ -8,7 +8,6 @@ from contextvars import ContextVar
 from fastmcp import FastMCP
 
 from hindsight_api import MemoryEngine
-from hindsight_api.api.http import BankListItem, BankListResponse, BankProfileResponse, DispositionTraits
 from hindsight_api.engine.response_models import VALID_RECALL_FACT_TYPES
 from hindsight_api.models import RequestContext
 
@@ -54,7 +53,12 @@ def create_mcp_server(memory: MemoryEngine) -> FastMCP:
     mcp = FastMCP("hindsight-mcp-server", stateless_http=True)
 
     @mcp.tool()
-    async def retain(content: str, context: str = "general", bank_id: str | None = None) -> str:
+    async def retain(
+        content: str,
+        context: str = "general",
+        async_processing: bool = True,
+        bank_id: str | None = None,
+    ) -> str:
         """
         Store important information to long-term memory.
 
@@ -70,18 +74,28 @@ def create_mcp_server(memory: MemoryEngine) -> FastMCP:
         Args:
             content: The fact/memory to store (be specific and include relevant details)
             context: Category for the memory (e.g., 'preferences', 'work', 'hobbies', 'family'). Default: 'general'
+            async_processing: If True, queue for background processing and return immediately. If False, wait for completion. Default: True
             bank_id: Optional bank to store in (defaults to session bank). Use for cross-bank operations.
         """
         try:
             target_bank = bank_id or get_current_bank_id()
             if target_bank is None:
                 return "Error: No bank_id configured"
-            await memory.retain_batch_async(
-                bank_id=target_bank,
-                contents=[{"content": content, "context": context}],
-                request_context=RequestContext(),
-            )
-            return f"Memory stored successfully in bank '{target_bank}'"
+            contents = [{"content": content, "context": context}]
+            if async_processing:
+                # Queue for background processing and return immediately
+                result = await memory.submit_async_retain(
+                    bank_id=target_bank, contents=contents, request_context=RequestContext()
+                )
+                return f"Memory queued for background processing (operation_id: {result.get('operation_id', 'N/A')})"
+            else:
+                # Wait for completion
+                await memory.retain_batch_async(
+                    bank_id=target_bank,
+                    contents=contents,
+                    request_context=RequestContext(),
+                )
+                return f"Memory stored successfully in bank '{target_bank}'"
         except Exception as e:
             logger.error(f"Error storing memory: {e}", exc_info=True)
             return f"Error: {str(e)}"
@@ -178,28 +192,15 @@ def create_mcp_server(memory: MemoryEngine) -> FastMCP:
         """
         List all available memory banks.
 
-        Use this to discover banks for orchestration or to find
-        the correct bank_id for cross-bank operations.
+        Use this tool to discover what memory banks exist in the system.
+        Each bank is an isolated memory store (like a separate "brain").
 
         Returns:
-            JSON object with banks array containing bank_id, name, disposition, background, and timestamps
+            JSON list of banks with their IDs, names, dispositions, and backgrounds.
         """
         try:
             banks = await memory.list_banks(request_context=RequestContext())
-            bank_items = [
-                BankListItem(
-                    bank_id=b.get("bank_id") or b.get("id"),
-                    name=b.get("name"),
-                    disposition=DispositionTraits(
-                        **b.get("disposition", {"skepticism": 3, "literalism": 3, "empathy": 3})
-                    ),
-                    background=b.get("background"),
-                    created_at=str(b.get("created_at")) if b.get("created_at") else None,
-                    updated_at=str(b.get("updated_at")) if b.get("updated_at") else None,
-                )
-                for b in banks
-            ]
-            return BankListResponse(banks=bank_items).model_dump_json(indent=2)
+            return json.dumps({"banks": banks}, indent=2)
         except Exception as e:
             logger.error(f"Error listing banks: {e}", exc_info=True)
             return f'{{"error": "{e}", "banks": []}}'
@@ -207,44 +208,38 @@ def create_mcp_server(memory: MemoryEngine) -> FastMCP:
     @mcp.tool()
     async def create_bank(bank_id: str, name: str | None = None, background: str | None = None) -> str:
         """
-        Create or update a memory bank.
+        Create a new memory bank or get an existing one.
 
-        Use this to create new banks for different agents, sessions, or purposes.
-        Banks are isolated memory stores - each bank has its own memories and personality.
+        Memory banks are isolated stores - each one is like a separate "brain" for a user/agent.
+        Banks are auto-created with default settings if they don't exist.
 
         Args:
-            bank_id: Unique identifier for the bank (e.g., 'orchestrator-memory', 'agent-1')
-            name: Human-readable name for the bank
-            background: Context about what this bank stores or its purpose
+            bank_id: Unique identifier for the bank (e.g., 'user-123', 'agent-alpha')
+            name: Optional human-friendly name for the bank
+            background: Optional background context about the bank's owner/purpose
         """
         try:
-            # Get or create the bank profile (auto-creates with defaults)
-            await memory.get_bank_profile(bank_id, request_context=RequestContext())
-
-            # Update name and/or background if provided
-            if name is not None or background is not None:
-                await memory.update_bank(bank_id, name=name, background=background, request_context=RequestContext())
-
-            # Get final profile and return using BankProfileResponse model
+            # get_bank_profile auto-creates bank if it doesn't exist
             profile = await memory.get_bank_profile(bank_id, request_context=RequestContext())
-            disposition = profile.get("disposition")
-            if hasattr(disposition, "model_dump"):
-                disposition_traits = DispositionTraits(**disposition.model_dump())
-            else:
-                disposition_traits = DispositionTraits(
-                    **dict(disposition or {"skepticism": 3, "literalism": 3, "empathy": 3})
-                )
 
-            response = BankProfileResponse(
-                bank_id=bank_id,
-                name=profile.get("name") or "",
-                disposition=disposition_traits,
-                background=profile.get("background") or "",
-            )
-            return response.model_dump_json(indent=2)
+            # Update name/background if provided
+            if name is not None or background is not None:
+                await memory.update_bank(
+                    bank_id,
+                    name=name,
+                    background=background,
+                    request_context=RequestContext(),
+                )
+                # Fetch updated profile
+                profile = await memory.get_bank_profile(bank_id, request_context=RequestContext())
+
+            # Serialize disposition if it's a Pydantic model
+            if "disposition" in profile and hasattr(profile["disposition"], "model_dump"):
+                profile["disposition"] = profile["disposition"].model_dump()
+            return json.dumps(profile, indent=2)
         except Exception as e:
             logger.error(f"Error creating bank: {e}", exc_info=True)
-            return json.dumps({"error": str(e)})
+            return f'{{"error": "{e}"}}'
 
     return mcp
 

hindsight-api/hindsight_api/config.py

@@ -8,6 +8,11 @@ import logging
 import os
 from dataclasses import dataclass
 
+from dotenv import find_dotenv, load_dotenv
+
+# Load .env file, searching current and parent directories (overrides existing env vars)
+load_dotenv(find_dotenv(usecwd=True), override=True)
+
 logger = logging.getLogger(__name__)
 
 # Environment variable names
@@ -20,12 +25,27 @@ ENV_LLM_MAX_CONCURRENT = "HINDSIGHT_API_LLM_MAX_CONCURRENT"
 ENV_LLM_TIMEOUT = "HINDSIGHT_API_LLM_TIMEOUT"
 ENV_LLM_GROQ_SERVICE_TIER = "HINDSIGHT_API_LLM_GROQ_SERVICE_TIER"
 
+# Per-operation LLM configuration (optional, falls back to global LLM config)
+ENV_RETAIN_LLM_PROVIDER = "HINDSIGHT_API_RETAIN_LLM_PROVIDER"
+ENV_RETAIN_LLM_API_KEY = "HINDSIGHT_API_RETAIN_LLM_API_KEY"
+ENV_RETAIN_LLM_MODEL = "HINDSIGHT_API_RETAIN_LLM_MODEL"
+ENV_RETAIN_LLM_BASE_URL = "HINDSIGHT_API_RETAIN_LLM_BASE_URL"
+
+ENV_REFLECT_LLM_PROVIDER = "HINDSIGHT_API_REFLECT_LLM_PROVIDER"
+ENV_REFLECT_LLM_API_KEY = "HINDSIGHT_API_REFLECT_LLM_API_KEY"
+ENV_REFLECT_LLM_MODEL = "HINDSIGHT_API_REFLECT_LLM_MODEL"
+ENV_REFLECT_LLM_BASE_URL = "HINDSIGHT_API_REFLECT_LLM_BASE_URL"
+
 ENV_EMBEDDINGS_PROVIDER = "HINDSIGHT_API_EMBEDDINGS_PROVIDER"
 ENV_EMBEDDINGS_LOCAL_MODEL = "HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL"
 ENV_EMBEDDINGS_TEI_URL = "HINDSIGHT_API_EMBEDDINGS_TEI_URL"
 ENV_EMBEDDINGS_OPENAI_API_KEY = "HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY"
 ENV_EMBEDDINGS_OPENAI_MODEL = "HINDSIGHT_API_EMBEDDINGS_OPENAI_MODEL"
 
+ENV_COHERE_API_KEY = "HINDSIGHT_API_COHERE_API_KEY"
+ENV_EMBEDDINGS_COHERE_MODEL = "HINDSIGHT_API_EMBEDDINGS_COHERE_MODEL"
+ENV_RERANKER_COHERE_MODEL = "HINDSIGHT_API_RERANKER_COHERE_MODEL"
+
 ENV_RERANKER_PROVIDER = "HINDSIGHT_API_RERANKER_PROVIDER"
 ENV_RERANKER_LOCAL_MODEL = "HINDSIGHT_API_RERANKER_LOCAL_MODEL"
 ENV_RERANKER_TEI_URL = "HINDSIGHT_API_RERANKER_TEI_URL"
@@ -42,10 +62,27 @@ ENV_MCP_INSTRUCTIONS = "HINDSIGHT_API_MCP_INSTRUCTIONS"
 ENV_OBSERVATION_MIN_FACTS = "HINDSIGHT_API_OBSERVATION_MIN_FACTS"
 ENV_OBSERVATION_TOP_ENTITIES = "HINDSIGHT_API_OBSERVATION_TOP_ENTITIES"
 
+# Retain settings
+ENV_RETAIN_MAX_COMPLETION_TOKENS = "HINDSIGHT_API_RETAIN_MAX_COMPLETION_TOKENS"
+ENV_RETAIN_CHUNK_SIZE = "HINDSIGHT_API_RETAIN_CHUNK_SIZE"
+
 # Optimization flags
 ENV_SKIP_LLM_VERIFICATION = "HINDSIGHT_API_SKIP_LLM_VERIFICATION"
 ENV_LAZY_RERANKER = "HINDSIGHT_API_LAZY_RERANKER"
 
+# Database migrations
+ENV_RUN_MIGRATIONS_ON_STARTUP = "HINDSIGHT_API_RUN_MIGRATIONS_ON_STARTUP"
+
+# Database connection pool
+ENV_DB_POOL_MIN_SIZE = "HINDSIGHT_API_DB_POOL_MIN_SIZE"
+ENV_DB_POOL_MAX_SIZE = "HINDSIGHT_API_DB_POOL_MAX_SIZE"
+ENV_DB_COMMAND_TIMEOUT = "HINDSIGHT_API_DB_COMMAND_TIMEOUT"
+ENV_DB_ACQUIRE_TIMEOUT = "HINDSIGHT_API_DB_ACQUIRE_TIMEOUT"
+
+# Background task processing
+ENV_TASK_BATCH_SIZE = "HINDSIGHT_API_TASK_BATCH_SIZE"
+ENV_TASK_BATCH_INTERVAL = "HINDSIGHT_API_TASK_BATCH_INTERVAL"
+
 # Default values
 DEFAULT_DATABASE_URL = "pg0"
 DEFAULT_LLM_PROVIDER = "openai"
@@ -61,6 +98,9 @@ DEFAULT_EMBEDDING_DIMENSION = 384
 DEFAULT_RERANKER_PROVIDER = "local"
 DEFAULT_RERANKER_LOCAL_MODEL = "cross-encoder/ms-marco-MiniLM-L-6-v2"
 
+DEFAULT_EMBEDDINGS_COHERE_MODEL = "embed-english-v3.0"
+DEFAULT_RERANKER_COHERE_MODEL = "rerank-english-v3.0"
+
 DEFAULT_HOST = "0.0.0.0"
 DEFAULT_PORT = 8888
 DEFAULT_LOG_LEVEL = "info"
@@ -72,6 +112,23 @@ DEFAULT_MCP_LOCAL_BANK_ID = "mcp"
 DEFAULT_OBSERVATION_MIN_FACTS = 5  # Min facts required to generate entity observations
 DEFAULT_OBSERVATION_TOP_ENTITIES = 5  # Max entities to process per retain batch
 
+# Retain settings
+DEFAULT_RETAIN_MAX_COMPLETION_TOKENS = 64000  # Max tokens for fact extraction LLM call
+DEFAULT_RETAIN_CHUNK_SIZE = 3000  # Max chars per chunk for fact extraction
+
+# Database migrations
+DEFAULT_RUN_MIGRATIONS_ON_STARTUP = True
+
+# Database connection pool
+DEFAULT_DB_POOL_MIN_SIZE = 5
+DEFAULT_DB_POOL_MAX_SIZE = 100
+DEFAULT_DB_COMMAND_TIMEOUT = 60  # seconds
+DEFAULT_DB_ACQUIRE_TIMEOUT = 30  # seconds
+
+# Background task processing
+DEFAULT_TASK_BATCH_SIZE = 10
+DEFAULT_TASK_BATCH_INTERVAL = 1.0  # seconds
+
 # Default MCP tool descriptions (can be customized via env vars)
 DEFAULT_MCP_RETAIN_DESCRIPTION = """Store important information to long-term memory.
 
@@ -103,7 +160,7 @@ class HindsightConfig:
     # Database
     database_url: str
 
-    # LLM
+    # LLM (default, used as fallback for per-operation config)
     llm_provider: str
     llm_api_key: str | None
     llm_model: str
@@ -111,6 +168,17 @@ class HindsightConfig:
     llm_max_concurrent: int
     llm_timeout: float
 
+    # Per-operation LLM configuration (None = use default LLM config)
+    retain_llm_provider: str | None
+    retain_llm_api_key: str | None
+    retain_llm_model: str | None
+    retain_llm_base_url: str | None
+
+    reflect_llm_provider: str | None
+    reflect_llm_api_key: str | None
+    reflect_llm_model: str | None
+    reflect_llm_base_url: str | None
+
     # Embeddings
     embeddings_provider: str
     embeddings_local_model: str
@@ -134,10 +202,27 @@ class HindsightConfig:
     observation_min_facts: int
     observation_top_entities: int
 
+    # Retain settings
+    retain_max_completion_tokens: int
+    retain_chunk_size: int
+
     # Optimization flags
     skip_llm_verification: bool
     lazy_reranker: bool
 
+    # Database migrations
+    run_migrations_on_startup: bool
+
+    # Database connection pool
+    db_pool_min_size: int
+    db_pool_max_size: int
+    db_command_timeout: int
+    db_acquire_timeout: int
+
+    # Background task processing
+    task_batch_size: int
+    task_batch_interval: float
+
     @classmethod
     def from_env(cls) -> "HindsightConfig":
         """Create configuration from environment variables."""
@@ -151,6 +236,15 @@ class HindsightConfig:
             llm_base_url=os.getenv(ENV_LLM_BASE_URL) or None,
             llm_max_concurrent=int(os.getenv(ENV_LLM_MAX_CONCURRENT, str(DEFAULT_LLM_MAX_CONCURRENT))),
             llm_timeout=float(os.getenv(ENV_LLM_TIMEOUT, str(DEFAULT_LLM_TIMEOUT))),
+            # Per-operation LLM config (None = use default)
+            retain_llm_provider=os.getenv(ENV_RETAIN_LLM_PROVIDER) or None,
+            retain_llm_api_key=os.getenv(ENV_RETAIN_LLM_API_KEY) or None,
+            retain_llm_model=os.getenv(ENV_RETAIN_LLM_MODEL) or None,
+            retain_llm_base_url=os.getenv(ENV_RETAIN_LLM_BASE_URL) or None,
+            reflect_llm_provider=os.getenv(ENV_REFLECT_LLM_PROVIDER) or None,
+            reflect_llm_api_key=os.getenv(ENV_REFLECT_LLM_API_KEY) or None,
+            reflect_llm_model=os.getenv(ENV_REFLECT_LLM_MODEL) or None,
+            reflect_llm_base_url=os.getenv(ENV_REFLECT_LLM_BASE_URL) or None,
             # Embeddings
             embeddings_provider=os.getenv(ENV_EMBEDDINGS_PROVIDER, DEFAULT_EMBEDDINGS_PROVIDER),
             embeddings_local_model=os.getenv(ENV_EMBEDDINGS_LOCAL_MODEL, DEFAULT_EMBEDDINGS_LOCAL_MODEL),
@@ -174,6 +268,21 @@ class HindsightConfig:
             observation_top_entities=int(
                 os.getenv(ENV_OBSERVATION_TOP_ENTITIES, str(DEFAULT_OBSERVATION_TOP_ENTITIES))
             ),
+            # Retain settings
+            retain_max_completion_tokens=int(
+                os.getenv(ENV_RETAIN_MAX_COMPLETION_TOKENS, str(DEFAULT_RETAIN_MAX_COMPLETION_TOKENS))
+            ),
+            retain_chunk_size=int(os.getenv(ENV_RETAIN_CHUNK_SIZE, str(DEFAULT_RETAIN_CHUNK_SIZE))),
+            # Database migrations
+            run_migrations_on_startup=os.getenv(ENV_RUN_MIGRATIONS_ON_STARTUP, "true").lower() == "true",
+            # Database connection pool
+            db_pool_min_size=int(os.getenv(ENV_DB_POOL_MIN_SIZE, str(DEFAULT_DB_POOL_MIN_SIZE))),
+            db_pool_max_size=int(os.getenv(ENV_DB_POOL_MAX_SIZE, str(DEFAULT_DB_POOL_MAX_SIZE))),
+            db_command_timeout=int(os.getenv(ENV_DB_COMMAND_TIMEOUT, str(DEFAULT_DB_COMMAND_TIMEOUT))),
+            db_acquire_timeout=int(os.getenv(ENV_DB_ACQUIRE_TIMEOUT, str(DEFAULT_DB_ACQUIRE_TIMEOUT))),
+            # Background task processing
+            task_batch_size=int(os.getenv(ENV_TASK_BATCH_SIZE, str(DEFAULT_TASK_BATCH_SIZE))),
+            task_batch_interval=float(os.getenv(ENV_TASK_BATCH_INTERVAL, str(DEFAULT_TASK_BATCH_INTERVAL))),
         )
 
     def get_llm_base_url(self) -> str:
@@ -215,11 +324,32 @@ class HindsightConfig:
         """Log the current configuration (without sensitive values)."""
         logger.info(f"Database: {self.database_url}")
         logger.info(f"LLM: provider={self.llm_provider}, model={self.llm_model}")
+        if self.retain_llm_provider or self.retain_llm_model:
+            retain_provider = self.retain_llm_provider or self.llm_provider
+            retain_model = self.retain_llm_model or self.llm_model
+            logger.info(f"LLM (retain): provider={retain_provider}, model={retain_model}")
+        if self.reflect_llm_provider or self.reflect_llm_model:
+            reflect_provider = self.reflect_llm_provider or self.llm_provider
+            reflect_model = self.reflect_llm_model or self.llm_model
+            logger.info(f"LLM (reflect): provider={reflect_provider}, model={reflect_model}")
         logger.info(f"Embeddings: provider={self.embeddings_provider}")
         logger.info(f"Reranker: provider={self.reranker_provider}")
         logger.info(f"Graph retriever: {self.graph_retriever}")
 
 
+# Cached config instance
+_config_cache: HindsightConfig | None = None
+
+
 def get_config() -> HindsightConfig:
-    """Get the current configuration from environment variables."""
-    return HindsightConfig.from_env()
+    """Get the cached configuration, loading from environment on first call."""
+    global _config_cache
+    if _config_cache is None:
+        _config_cache = HindsightConfig.from_env()
+    return _config_cache
+
+
+def clear_config_cache() -> None:
+    """Clear the config cache. Useful for testing or reloading config."""
+    global _config_cache
+    _config_cache = None

hindsight-api/hindsight_api/engine/cross_encoder.py

@@ -13,8 +13,11 @@ from abc import ABC, abstractmethod
 import httpx
 
 from ..config import (
+    DEFAULT_RERANKER_COHERE_MODEL,
     DEFAULT_RERANKER_LOCAL_MODEL,
     DEFAULT_RERANKER_PROVIDER,
+    ENV_COHERE_API_KEY,
+    ENV_RERANKER_COHERE_MODEL,
     ENV_RERANKER_LOCAL_MODEL,
     ENV_RERANKER_PROVIDER,
     ENV_RERANKER_TEI_URL,
@@ -278,6 +281,96 @@ class RemoteTEICrossEncoder(CrossEncoderModel):
         return all_scores
 
 
+class CohereCrossEncoder(CrossEncoderModel):
+    """
+    Cohere cross-encoder implementation using the Cohere Rerank API.
+
+    Supports rerank-english-v3.0 and rerank-multilingual-v3.0 models.
+    """
+
+    def __init__(
+        self,
+        api_key: str,
+        model: str = DEFAULT_RERANKER_COHERE_MODEL,
+        timeout: float = 60.0,
+    ):
+        """
+        Initialize Cohere cross-encoder client.
+
+        Args:
+            api_key: Cohere API key
+            model: Cohere rerank model name (default: rerank-english-v3.0)
+            timeout: Request timeout in seconds (default: 60.0)
+        """
+        self.api_key = api_key
+        self.model = model
+        self.timeout = timeout
+        self._client = None
+
+    @property
+    def provider_name(self) -> str:
+        return "cohere"
+
+    async def initialize(self) -> None:
+        """Initialize the Cohere client."""
+        if self._client is not None:
+            return
+
+        try:
+            import cohere
+        except ImportError:
+            raise ImportError("cohere is required for CohereCrossEncoder. Install it with: pip install cohere")
+
+        logger.info(f"Reranker: initializing Cohere provider with model {self.model}")
+        self._client = cohere.Client(api_key=self.api_key, timeout=self.timeout)
+        logger.info("Reranker: Cohere provider initialized")
+
+    def predict(self, pairs: list[tuple[str, str]]) -> list[float]:
+        """
+        Score query-document pairs using the Cohere Rerank API.
+
+        Args:
+            pairs: List of (query, document) tuples to score
+
+        Returns:
+            List of relevance scores
+        """
+        if self._client is None:
+            raise RuntimeError("Reranker not initialized. Call initialize() first.")
+
+        if not pairs:
+            return []
+
+        # Group pairs by query for efficient batching
+        # Cohere 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]
+
+            response = self._client.rerank(
+                query=query,
+                documents=texts,
+                model=self.model,
+                return_documents=False,
+            )
+
+            # Map scores back to original positions
+            for result in response.results:
+                original_idx = result.index
+                score = result.relevance_score
+                all_scores[indices[original_idx]] = score
+
+        return all_scores
+
+
 def create_cross_encoder_from_env() -> CrossEncoderModel:
     """
     Create a CrossEncoderModel instance based on environment variables.
@@ -298,5 +391,11 @@ def create_cross_encoder_from_env() -> CrossEncoderModel:
         model = os.environ.get(ENV_RERANKER_LOCAL_MODEL)
         model_name = model or DEFAULT_RERANKER_LOCAL_MODEL
         return LocalSTCrossEncoder(model_name=model_name)
+    elif provider == "cohere":
+        api_key = os.environ.get(ENV_COHERE_API_KEY)
+        if not api_key:
+            raise ValueError(f"{ENV_COHERE_API_KEY} is required when {ENV_RERANKER_PROVIDER} is 'cohere'")
+        model = os.environ.get(ENV_RERANKER_COHERE_MODEL, DEFAULT_RERANKER_COHERE_MODEL)
+        return CohereCrossEncoder(api_key=api_key, model=model)
     else:
-        raise ValueError(f"Unknown reranker provider: {provider}. Supported: 'local', 'tei'")
+        raise ValueError(f"Unknown reranker provider: {provider}. Supported: 'local', 'tei', 'cohere'")

hindsight-api/hindsight_api/engine/embeddings.py

@@ -16,9 +16,12 @@ from abc import ABC, abstractmethod
 import httpx
 
 from ..config import (
+    DEFAULT_EMBEDDINGS_COHERE_MODEL,
     DEFAULT_EMBEDDINGS_LOCAL_MODEL,
     DEFAULT_EMBEDDINGS_OPENAI_MODEL,
     DEFAULT_EMBEDDINGS_PROVIDER,
+    ENV_COHERE_API_KEY,
+    ENV_EMBEDDINGS_COHERE_MODEL,
     ENV_EMBEDDINGS_LOCAL_MODEL,
     ENV_EMBEDDINGS_OPENAI_API_KEY,
     ENV_EMBEDDINGS_OPENAI_MODEL,
@@ -409,6 +412,123 @@ class OpenAIEmbeddings(Embeddings):
         return all_embeddings
 
 
+class CohereEmbeddings(Embeddings):
+    """
+    Cohere embeddings implementation using the Cohere API.
+
+    Supports embed-english-v3.0 (1024 dims) and embed-multilingual-v3.0 (1024 dims).
+
+    The embedding dimension is auto-detected from the model at initialization.
+    """
+
+    # Known dimensions for Cohere embedding models
+    MODEL_DIMENSIONS = {
+        "embed-english-v3.0": 1024,
+        "embed-multilingual-v3.0": 1024,
+        "embed-english-light-v3.0": 384,
+        "embed-multilingual-light-v3.0": 384,
+        "embed-english-v2.0": 4096,
+        "embed-multilingual-v2.0": 768,
+    }
+
+    def __init__(
+        self,
+        api_key: str,
+        model: str = DEFAULT_EMBEDDINGS_COHERE_MODEL,
+        batch_size: int = 96,
+        timeout: float = 60.0,
+        input_type: str = "search_document",
+    ):
+        """
+        Initialize Cohere embeddings client.
+
+        Args:
+            api_key: Cohere API key
+            model: Cohere embedding model name (default: embed-english-v3.0)
+            batch_size: Maximum batch size for embedding requests (default: 96, Cohere's limit)
+            timeout: Request timeout in seconds (default: 60.0)
+            input_type: Input type for embeddings (default: search_document).
+                       Options: search_document, search_query, classification, clustering
+        """
+        self.api_key = api_key
+        self.model = model
+        self.batch_size = batch_size
+        self.timeout = timeout
+        self.input_type = input_type
+        self._client = None
+        self._dimension: int | None = None
+
+    @property
+    def provider_name(self) -> str:
+        return "cohere"
+
+    @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 Cohere client and detect dimension."""
+        if self._client is not None:
+            return
+
+        try:
+            import cohere
+        except ImportError:
+            raise ImportError("cohere is required for CohereEmbeddings. Install it with: pip install cohere")
+
+        logger.info(f"Embeddings: initializing Cohere provider with model {self.model}")
+        self._client = cohere.Client(api_key=self.api_key, timeout=self.timeout)
+
+        # Try to get dimension from known models, otherwise do a test embedding
+        if self.model in self.MODEL_DIMENSIONS:
+            self._dimension = self.MODEL_DIMENSIONS[self.model]
+        else:
+            # Do a test embedding to detect dimension
+            response = self._client.embed(
+                texts=["test"],
+                model=self.model,
+                input_type=self.input_type,
+            )
+            if response.embeddings:
+                self._dimension = len(response.embeddings[0])
+
+        logger.info(f"Embeddings: Cohere provider initialized (model: {self.model}, dim: {self._dimension})")
+
+    def encode(self, texts: list[str]) -> list[list[float]]:
+        """
+        Generate embeddings using the Cohere API.
+
+        Args:
+            texts: List of text strings to encode
+
+        Returns:
+            List of embedding vectors
+        """
+        if self._client 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]
+
+            response = self._client.embed(
+                texts=batch,
+                model=self.model,
+                input_type=self.input_type,
+            )
+
+            all_embeddings.extend(response.embeddings)
+
+        return all_embeddings
+
+
 def create_embeddings_from_env() -> Embeddings:
     """
     Create an Embeddings instance based on environment variables.
@@ -439,5 +559,11 @@ def create_embeddings_from_env() -> Embeddings:
             )
         model = os.environ.get(ENV_EMBEDDINGS_OPENAI_MODEL, DEFAULT_EMBEDDINGS_OPENAI_MODEL)
         return OpenAIEmbeddings(api_key=api_key, model=model)
+    elif provider == "cohere":
+        api_key = os.environ.get(ENV_COHERE_API_KEY)
+        if not api_key:
+            raise ValueError(f"{ENV_COHERE_API_KEY} is required when {ENV_EMBEDDINGS_PROVIDER} is 'cohere'")
+        model = os.environ.get(ENV_EMBEDDINGS_COHERE_MODEL, DEFAULT_EMBEDDINGS_COHERE_MODEL)
+        return CohereEmbeddings(api_key=api_key, model=model)
     else:
-        raise ValueError(f"Unknown embeddings provider: {provider}. Supported: 'local', 'tei', 'openai'")
+        raise ValueError(f"Unknown embeddings provider: {provider}. Supported: 'local', 'tei', 'openai', 'cohere'")

hindsight-api/hindsight_api/engine/interface.py

@@ -289,6 +289,7 @@ class MemoryEngineInterface(ABC):
         bank_id: str,
         *,
         fact_type: str | None = None,
+        limit: int = 1000,
         request_context: "RequestContext",
     ) -> dict[str, Any]:
         """
@@ -297,10 +298,11 @@ class MemoryEngineInterface(ABC):
         Args:
             bank_id: The memory bank ID.
             fact_type: Filter by fact type.
+            limit: Maximum number of items to return (default: 1000).
             request_context: Request context for authentication.
 
         Returns:
-            Dict with nodes, edges, table_rows, total_units.
+            Dict with nodes, edges, table_rows, total_units, limit.
         """
         ...
 

hindsight-api/hindsight_api/engine/llm_wrapper.py

@@ -23,6 +23,8 @@ from ..config import (
     ENV_LLM_MAX_CONCURRENT,
     ENV_LLM_TIMEOUT,
 )
+from ..metrics import get_metrics_collector
+from .response_models import TokenUsage
 
 # Seed applied to every Groq request for deterministic behavior.
 DEFAULT_LLM_SEED = 4242
@@ -86,10 +88,14 @@ class LLMProvider:
         self.groq_service_tier = groq_service_tier or os.getenv(ENV_LLM_GROQ_SERVICE_TIER, "auto")
 
         # Validate provider
-        valid_providers = ["openai", "groq", "ollama", "gemini", "anthropic", "lmstudio"]
+        valid_providers = ["openai", "groq", "ollama", "gemini", "anthropic", "lmstudio", "mock"]
         if self.provider not in valid_providers:
             raise ValueError(f"Invalid LLM provider: {self.provider}. Must be one of: {', '.join(valid_providers)}")
 
+        # Mock provider tracking (for testing)
+        self._mock_calls: list[dict] = []
+        self._mock_response: Any = None
+
         # Set default base URLs
         if not self.base_url:
             if self.provider == "groq":
@@ -99,8 +105,8 @@ class LLMProvider:
             elif self.provider == "lmstudio":
                 self.base_url = "http://localhost:1234/v1"
 
-        # Validate API key (not needed for ollama or lmstudio)
-        if self.provider not in ("ollama", "lmstudio") and not self.api_key:
+        # Validate API key (not needed for ollama, lmstudio, or mock)
+        if self.provider not in ("ollama", "lmstudio", "mock") and not self.api_key:
             raise ValueError(f"API key not found for {self.provider}")
 
         # Get timeout config (set HINDSIGHT_API_LLM_TIMEOUT for local LLMs that need longer timeouts)
@@ -111,7 +117,10 @@ class LLMProvider:
         self._gemini_client = None
         self._anthropic_client = None
 
-        if self.provider == "gemini":
+        if self.provider == "mock":
+            # Mock provider - no client needed
+            pass
+        elif self.provider == "gemini":
             self._gemini_client = genai.Client(api_key=self.api_key)
         elif self.provider == "anthropic":
             from anthropic import AsyncAnthropic
@@ -174,6 +183,7 @@ class LLMProvider:
         max_backoff: float = 60.0,
         skip_validation: bool = False,
         strict_schema: bool = False,
+        return_usage: bool = False,
     ) -> Any:
         """
         Make an LLM API call with retry logic.
@@ -189,9 +199,11 @@ class LLMProvider:
             max_backoff: Maximum backoff time in seconds.
             skip_validation: Return raw JSON without Pydantic validation.
             strict_schema: Use strict JSON schema enforcement (OpenAI only). Guarantees all required fields.
+            return_usage: If True, return tuple (result, TokenUsage) instead of just result.
 
         Returns:
-            Parsed response if response_format is provided, otherwise text content.
+            If return_usage=False: Parsed response if response_format is provided, otherwise text content.
+            If return_usage=True: Tuple of (result, TokenUsage) with token counts from the LLM call.
 
         Raises:
             OutputTooLongError: If output exceeds token limits.
@@ -200,10 +212,26 @@ class LLMProvider:
         async with _global_llm_semaphore:
             start_time = time.time()
 
+            # Handle Mock provider (for testing)
+            if self.provider == "mock":
+                return await self._call_mock(
+                    messages,
+                    response_format,
+                    scope,
+                    return_usage,
+                )
+
             # Handle Gemini provider separately
             if self.provider == "gemini":
                 return await self._call_gemini(
-                    messages, response_format, max_retries, initial_backoff, max_backoff, skip_validation, start_time
+                    messages,
+                    response_format,
+                    max_retries,
+                    initial_backoff,
+                    max_backoff,
+                    skip_validation,
+                    start_time,
+                    return_usage,
                 )
 
             # Handle Anthropic provider separately
@@ -217,6 +245,7 @@ class LLMProvider:
                     max_backoff,
                     skip_validation,
                     start_time,
+                    return_usage,
                 )
 
             # Handle Ollama with native API for structured output (better schema enforcement)
@@ -231,6 +260,7 @@ class LLMProvider:
                     max_backoff,
                     skip_validation,
                     start_time,
+                    return_usage,
                 )
 
             call_params = {
@@ -379,21 +409,45 @@ class LLMProvider:
                         response = await self._client.chat.completions.create(**call_params)
                         result = response.choices[0].message.content
 
-                    # Log slow calls
+                    # Record token usage metrics
                     duration = time.time() - start_time
                     usage = response.usage
-                    if duration > 10.0:
-                        ratio = max(1, usage.completion_tokens) / usage.prompt_tokens
+                    input_tokens = usage.prompt_tokens or 0 if usage else 0
+                    output_tokens = usage.completion_tokens or 0 if usage else 0
+                    total_tokens = usage.total_tokens or 0 if usage else 0
+
+                    # Record LLM metrics
+                    metrics = get_metrics_collector()
+                    metrics.record_llm_call(
+                        provider=self.provider,
+                        model=self.model,
+                        scope=scope,
+                        duration=duration,
+                        input_tokens=input_tokens,
+                        output_tokens=output_tokens,
+                        success=True,
+                    )
+
+                    # Log slow calls
+                    if duration > 10.0 and usage:
+                        ratio = max(1, output_tokens) / max(1, input_tokens)
                         cached_tokens = 0
                         if hasattr(usage, "prompt_tokens_details") and usage.prompt_tokens_details:
                             cached_tokens = getattr(usage.prompt_tokens_details, "cached_tokens", 0) or 0
                         cache_info = f", cached_tokens={cached_tokens}" if cached_tokens > 0 else ""
                         logger.info(
                             f"slow llm call: model={self.provider}/{self.model}, "
-                            f"input_tokens={usage.prompt_tokens}, output_tokens={usage.completion_tokens}, "
-                            f"total_tokens={usage.total_tokens}{cache_info}, time={duration:.3f}s, ratio out/in={ratio:.2f}"
+                            f"input_tokens={input_tokens}, output_tokens={output_tokens}, "
+                            f"total_tokens={total_tokens}{cache_info}, time={duration:.3f}s, ratio out/in={ratio:.2f}"
                         )
 
+                    if return_usage:
+                        token_usage = TokenUsage(
+                            input_tokens=input_tokens,
+                            output_tokens=output_tokens,
+                            total_tokens=total_tokens,
+                        )
+                        return result, token_usage
                     return result
 
                 except LengthFinishReasonError as e:
@@ -452,6 +506,7 @@ class LLMProvider:
         max_backoff: float,
         skip_validation: bool,
         start_time: float,
+        return_usage: bool = False,
     ) -> Any:
         """Handle Anthropic-specific API calls."""
         from anthropic import APIConnectionError, APIStatusError, RateLimitError
@@ -524,17 +579,39 @@ class LLMProvider:
                 else:
                     result = content
 
-                # Log slow calls
+                # Record metrics and log slow calls
                 duration = time.time() - start_time
+                input_tokens = response.usage.input_tokens or 0 if response.usage else 0
+                output_tokens = response.usage.output_tokens or 0 if response.usage else 0
+                total_tokens = input_tokens + output_tokens
+
+                # Record LLM metrics
+                metrics = get_metrics_collector()
+                metrics.record_llm_call(
+                    provider=self.provider,
+                    model=self.model,
+                    scope="memory",
+                    duration=duration,
+                    input_tokens=input_tokens,
+                    output_tokens=output_tokens,
+                    success=True,
+                )
+
+                # Log slow calls
                 if duration > 10.0:
-                    input_tokens = response.usage.input_tokens
-                    output_tokens = response.usage.output_tokens
                     logger.info(
-                        f"slow llm call: model={self.provider}/{self.model}, "
+                        f"slow llm call: scope=memory, model={self.provider}/{self.model}, "
                         f"input_tokens={input_tokens}, output_tokens={output_tokens}, "
                         f"time={duration:.3f}s"
                     )
 
+                if return_usage:
+                    token_usage = TokenUsage(
+                        input_tokens=input_tokens,
+                        output_tokens=output_tokens,
+                        total_tokens=total_tokens,
+                    )
+                    return result, token_usage
                 return result
 
             except json.JSONDecodeError as e:
@@ -589,6 +666,7 @@ class LLMProvider:
         max_backoff: float,
         skip_validation: bool,
         start_time: float,
+        return_usage: bool = False,
     ) -> Any:
         """
         Call Ollama using native API with JSON schema enforcement.
@@ -663,11 +741,39 @@ class LLMProvider:
                         else:
                             raise
 
+                    # Extract token usage from Ollama response
+                    # Ollama returns prompt_eval_count (input) and eval_count (output)
+                    duration = time.time() - start_time
+                    input_tokens = result.get("prompt_eval_count", 0) or 0
+                    output_tokens = result.get("eval_count", 0) or 0
+                    total_tokens = input_tokens + output_tokens
+
+                    # Record LLM metrics
+                    metrics = get_metrics_collector()
+                    metrics.record_llm_call(
+                        provider=self.provider,
+                        model=self.model,
+                        scope="memory",
+                        duration=duration,
+                        input_tokens=input_tokens,
+                        output_tokens=output_tokens,
+                        success=True,
+                    )
+
                     # Validate against Pydantic model or return raw JSON
                     if skip_validation:
-                        return json_data
+                        validated_result = json_data
                     else:
-                        return response_format.model_validate(json_data)
+                        validated_result = response_format.model_validate(json_data)
+
+                    if return_usage:
+                        token_usage = TokenUsage(
+                            input_tokens=input_tokens,
+                            output_tokens=output_tokens,
+                            total_tokens=total_tokens,
+                        )
+                        return validated_result, token_usage
+                    return validated_result
 
                 except httpx.HTTPStatusError as e:
                     last_exception = e
@@ -710,6 +816,7 @@ class LLMProvider:
         max_backoff: float,
         skip_validation: bool,
         start_time: float,
+        return_usage: bool = False,
     ) -> Any:
         """Handle Gemini-specific API calls."""
         # Convert OpenAI-style messages to Gemini format
@@ -786,16 +893,42 @@ class LLMProvider:
                 else:
                     result = content
 
-                # Log slow calls
+                # Record metrics and log slow calls
                 duration = time.time() - start_time
-                if duration > 10.0 and hasattr(response, "usage_metadata") and response.usage_metadata:
+                input_tokens = 0
+                output_tokens = 0
+                if hasattr(response, "usage_metadata") and response.usage_metadata:
                     usage = response.usage_metadata
+                    input_tokens = usage.prompt_token_count or 0
+                    output_tokens = usage.candidates_token_count or 0
+
+                # Record LLM metrics
+                metrics = get_metrics_collector()
+                metrics.record_llm_call(
+                    provider=self.provider,
+                    model=self.model,
+                    scope="memory",
+                    duration=duration,
+                    input_tokens=input_tokens,
+                    output_tokens=output_tokens,
+                    success=True,
+                )
+
+                # Log slow calls
+                if duration > 10.0 and input_tokens > 0:
                     logger.info(
-                        f"slow llm call: model={self.provider}/{self.model}, "
-                        f"input_tokens={usage.prompt_token_count}, output_tokens={usage.candidates_token_count}, "
+                        f"slow llm call: scope=memory, model={self.provider}/{self.model}, "
+                        f"input_tokens={input_tokens}, output_tokens={output_tokens}, "
                         f"time={duration:.3f}s"
                     )
 
+                if return_usage:
+                    token_usage = TokenUsage(
+                        input_tokens=input_tokens,
+                        output_tokens=output_tokens,
+                        total_tokens=input_tokens + output_tokens,
+                    )
+                    return result, token_usage
                 return result
 
             except json.JSONDecodeError as e:
@@ -837,6 +970,61 @@ class LLMProvider:
             raise last_exception
         raise RuntimeError("Gemini call failed after all retries")
 
+    async def _call_mock(
+        self,
+        messages: list[dict[str, str]],
+        response_format: Any | None,
+        scope: str,
+        return_usage: bool,
+    ) -> Any:
+        """
+        Handle mock provider calls for testing.
+
+        Records the call and returns a configurable mock response.
+        """
+        # Record the call for test verification
+        call_record = {
+            "provider": self.provider,
+            "model": self.model,
+            "messages": messages,
+            "response_format": response_format.__name__
+            if response_format and hasattr(response_format, "__name__")
+            else str(response_format),
+            "scope": scope,
+        }
+        self._mock_calls.append(call_record)
+        logger.debug(f"Mock LLM call recorded: scope={scope}, model={self.model}")
+
+        # Return mock response
+        if self._mock_response is not None:
+            result = self._mock_response
+        elif response_format is not None:
+            # Try to create a minimal valid instance of the response format
+            try:
+                # For Pydantic models, try to create with minimal valid data
+                result = {"mock": True}
+            except Exception:
+                result = {"mock": True}
+        else:
+            result = "mock response"
+
+        if return_usage:
+            token_usage = TokenUsage(input_tokens=10, output_tokens=5, total_tokens=15)
+            return result, token_usage
+        return result
+
+    def set_mock_response(self, response: Any) -> None:
+        """Set the response to return from mock calls."""
+        self._mock_response = response
+
+    def get_mock_calls(self) -> list[dict]:
+        """Get the list of recorded mock calls."""
+        return self._mock_calls
+
+    def clear_mock_calls(self) -> None:
+        """Clear the recorded mock calls."""
+        self._mock_calls = []
+
     @classmethod
     def for_memory(cls) -> "LLMProvider":
         """Create provider for memory operations from environment variables."""

hindsight-api/hindsight_api/engine/memory_engine.py

@@ -18,6 +18,7 @@ from datetime import UTC, datetime, timedelta
 from typing import TYPE_CHECKING, Any
 
 from ..config import get_config
+from ..metrics import get_metrics_collector
 
 # Context variable for current schema (async-safe, per-task isolation)
 _current_schema: contextvars.ContextVar[str] = contextvars.ContextVar("current_schema", default="public")
@@ -132,11 +133,18 @@ if TYPE_CHECKING:
 
 from enum import Enum
 
-from ..pg0 import EmbeddedPostgres
+from ..pg0 import EmbeddedPostgres, parse_pg0_url
 from .entity_resolver import EntityResolver
 from .llm_wrapper import LLMConfig
 from .query_analyzer import QueryAnalyzer
-from .response_models import VALID_RECALL_FACT_TYPES, EntityObservation, EntityState, MemoryFact, ReflectResult
+from .response_models import (
+    VALID_RECALL_FACT_TYPES,
+    EntityObservation,
+    EntityState,
+    MemoryFact,
+    ReflectResult,
+    TokenUsage,
+)
 from .response_models import RecallResult as RecallResultModel
 from .retain import bank_utils, embedding_utils
 from .retain.types import RetainContentDict
@@ -195,12 +203,25 @@ class MemoryEngine(MemoryEngineInterface):
         memory_llm_api_key: str | None = None,
         memory_llm_model: str | None = None,
         memory_llm_base_url: str | None = None,
+        # Per-operation LLM config (optional, falls back to memory_llm_* params)
+        retain_llm_provider: str | None = None,
+        retain_llm_api_key: str | None = None,
+        retain_llm_model: str | None = None,
+        retain_llm_base_url: str | None = None,
+        reflect_llm_provider: str | None = None,
+        reflect_llm_api_key: str | None = None,
+        reflect_llm_model: str | None = None,
+        reflect_llm_base_url: str | None = None,
         embeddings: Embeddings | None = None,
         cross_encoder: CrossEncoderModel | None = None,
         query_analyzer: QueryAnalyzer | None = None,
-        pool_min_size: int = 5,
-        pool_max_size: int = 100,
+        pool_min_size: int | None = None,
+        pool_max_size: int | None = None,
+        db_command_timeout: int | None = None,
+        db_acquire_timeout: int | None = None,
         task_backend: TaskBackend | None = None,
+        task_batch_size: int | None = None,
+        task_batch_interval: float | None = None,
         run_migrations: bool = True,
         operation_validator: "OperationValidatorExtension | None" = None,
         tenant_extension: "TenantExtension | None" = None,
@@ -220,12 +241,24 @@ class MemoryEngine(MemoryEngineInterface):
             memory_llm_api_key: API key for the LLM provider. Defaults to HINDSIGHT_API_LLM_API_KEY env var.
             memory_llm_model: Model name. Defaults to HINDSIGHT_API_LLM_MODEL env var.
             memory_llm_base_url: Base URL for the LLM API. Defaults based on provider.
+            retain_llm_provider: LLM provider for retain operations. Falls back to memory_llm_provider.
+            retain_llm_api_key: API key for retain LLM. Falls back to memory_llm_api_key.
+            retain_llm_model: Model for retain operations. Falls back to memory_llm_model.
+            retain_llm_base_url: Base URL for retain LLM. Falls back to memory_llm_base_url.
+            reflect_llm_provider: LLM provider for reflect operations. Falls back to memory_llm_provider.
+            reflect_llm_api_key: API key for reflect LLM. Falls back to memory_llm_api_key.
+            reflect_llm_model: Model for reflect operations. Falls back to memory_llm_model.
+            reflect_llm_base_url: Base URL for reflect LLM. Falls back to memory_llm_base_url.
             embeddings: Embeddings implementation. If not provided, created from env vars.
             cross_encoder: Cross-encoder model. If not provided, created from env vars.
             query_analyzer: Query analyzer implementation. If not provided, uses DateparserQueryAnalyzer.
-            pool_min_size: Minimum number of connections in the pool (default: 5)
-            pool_max_size: Maximum number of connections in the pool (default: 100)
+            pool_min_size: Minimum number of connections in the pool. Defaults to HINDSIGHT_API_DB_POOL_MIN_SIZE.
+            pool_max_size: Maximum number of connections in the pool. Defaults to HINDSIGHT_API_DB_POOL_MAX_SIZE.
+            db_command_timeout: PostgreSQL command timeout in seconds. Defaults to HINDSIGHT_API_DB_COMMAND_TIMEOUT.
+            db_acquire_timeout: Connection acquisition timeout in seconds. Defaults to HINDSIGHT_API_DB_ACQUIRE_TIMEOUT.
             task_backend: Custom task backend. If not provided, uses AsyncIOQueueBackend.
+            task_batch_size: Background task batch size. Defaults to HINDSIGHT_API_TASK_BATCH_SIZE.
+            task_batch_interval: Background task batch interval in seconds. Defaults to HINDSIGHT_API_TASK_BATCH_INTERVAL.
             run_migrations: Whether to run database migrations during initialize(). Default: True
             operation_validator: Optional extension to validate operations before execution.
                                 If provided, retain/recall/reflect operations will be validated.
@@ -252,38 +285,21 @@ class MemoryEngine(MemoryEngineInterface):
         db_url = db_url or config.database_url
         memory_llm_provider = memory_llm_provider or config.llm_provider
         memory_llm_api_key = memory_llm_api_key or config.llm_api_key
-        # Ollama doesn't require an API key
-        if not memory_llm_api_key and memory_llm_provider != "ollama":
+        # Ollama and mock don't require an API key
+        if not memory_llm_api_key and memory_llm_provider not in ("ollama", "mock"):
             raise ValueError("LLM API key is required. Set HINDSIGHT_API_LLM_API_KEY environment variable.")
         memory_llm_model = memory_llm_model or config.llm_model
         memory_llm_base_url = memory_llm_base_url or config.get_llm_base_url() or None
         # Track pg0 instance (if used)
         self._pg0: EmbeddedPostgres | None = None
-        self._pg0_instance_name: str | None = None
 
         # Initialize PostgreSQL connection URL
         # The actual URL will be set during initialize() after starting the server
         # Supports: "pg0" (default instance), "pg0://instance-name" (named instance), or regular postgresql:// URL
-        if db_url == "pg0":
-            self._use_pg0 = True
-            self._pg0_instance_name = "hindsight"
-            self._pg0_port = None  # Use default port
-            self.db_url = None
-        elif db_url.startswith("pg0://"):
-            self._use_pg0 = True
-            # Parse instance name and optional port: pg0://instance-name or pg0://instance-name:port
-            url_part = db_url[6:]  # Remove "pg0://"
-            if ":" in url_part:
-                self._pg0_instance_name, port_str = url_part.rsplit(":", 1)
-                self._pg0_port = int(port_str)
-            else:
-                self._pg0_instance_name = url_part or "hindsight"
-                self._pg0_port = None  # Use default port
+        self._use_pg0, self._pg0_instance_name, self._pg0_port = parse_pg0_url(db_url)
+        if self._use_pg0:
             self.db_url = None
         else:
-            self._use_pg0 = False
-            self._pg0_instance_name = None
-            self._pg0_port = None
             self.db_url = db_url
 
         # Set default base URL if not provided
@@ -298,8 +314,10 @@ class MemoryEngine(MemoryEngineInterface):
         # Connection pool (will be created in initialize())
         self._pool = None
         self._initialized = False
-        self._pool_min_size = pool_min_size
-        self._pool_max_size = pool_max_size
+        self._pool_min_size = pool_min_size if pool_min_size is not None else config.db_pool_min_size
+        self._pool_max_size = pool_max_size if pool_max_size is not None else config.db_pool_max_size
+        self._db_command_timeout = db_command_timeout if db_command_timeout is not None else config.db_command_timeout
+        self._db_acquire_timeout = db_acquire_timeout if db_acquire_timeout is not None else config.db_acquire_timeout
         self._run_migrations = run_migrations
 
         # Initialize entity resolver (will be created in initialize())
@@ -319,7 +337,7 @@ class MemoryEngine(MemoryEngineInterface):
 
             self.query_analyzer = DateparserQueryAnalyzer()
 
-        # Initialize LLM configuration
+        # Initialize LLM configuration (default, used as fallback)
         self._llm_config = LLMConfig(
             provider=memory_llm_provider,
             api_key=memory_llm_api_key,
@@ -331,11 +349,58 @@ class MemoryEngine(MemoryEngineInterface):
         self._llm_client = self._llm_config._client
         self._llm_model = self._llm_config.model
 
+        # Initialize per-operation LLM configs (fall back to default if not specified)
+        # Retain LLM config - for fact extraction (benefits from strong structured output)
+        retain_provider = retain_llm_provider or config.retain_llm_provider or memory_llm_provider
+        retain_api_key = retain_llm_api_key or config.retain_llm_api_key or memory_llm_api_key
+        retain_model = retain_llm_model or config.retain_llm_model or memory_llm_model
+        retain_base_url = retain_llm_base_url or config.retain_llm_base_url or memory_llm_base_url
+        # Apply provider-specific base URL defaults for retain
+        if retain_base_url is None:
+            if retain_provider.lower() == "groq":
+                retain_base_url = "https://api.groq.com/openai/v1"
+            elif retain_provider.lower() == "ollama":
+                retain_base_url = "http://localhost:11434/v1"
+            else:
+                retain_base_url = ""
+
+        self._retain_llm_config = LLMConfig(
+            provider=retain_provider,
+            api_key=retain_api_key,
+            base_url=retain_base_url,
+            model=retain_model,
+        )
+
+        # Reflect LLM config - for think/observe operations (can use lighter models)
+        reflect_provider = reflect_llm_provider or config.reflect_llm_provider or memory_llm_provider
+        reflect_api_key = reflect_llm_api_key or config.reflect_llm_api_key or memory_llm_api_key
+        reflect_model = reflect_llm_model or config.reflect_llm_model or memory_llm_model
+        reflect_base_url = reflect_llm_base_url or config.reflect_llm_base_url or memory_llm_base_url
+        # Apply provider-specific base URL defaults for reflect
+        if reflect_base_url is None:
+            if reflect_provider.lower() == "groq":
+                reflect_base_url = "https://api.groq.com/openai/v1"
+            elif reflect_provider.lower() == "ollama":
+                reflect_base_url = "http://localhost:11434/v1"
+            else:
+                reflect_base_url = ""
+
+        self._reflect_llm_config = LLMConfig(
+            provider=reflect_provider,
+            api_key=reflect_api_key,
+            base_url=reflect_base_url,
+            model=reflect_model,
+        )
+
         # Initialize cross-encoder reranker (cached for performance)
         self._cross_encoder_reranker = CrossEncoderReranker(cross_encoder=cross_encoder)
 
         # Initialize task backend
-        self._task_backend = task_backend or AsyncIOQueueBackend(batch_size=100, batch_interval=1.0)
+        _task_batch_size = task_batch_size if task_batch_size is not None else config.task_batch_size
+        _task_batch_interval = task_batch_interval if task_batch_interval is not None else config.task_batch_interval
+        self._task_backend = task_backend or AsyncIOQueueBackend(
+            batch_size=_task_batch_size, batch_interval=_task_batch_interval
+        )
 
         # Backpressure mechanism: limit concurrent searches to prevent overwhelming the database
         # Limit concurrent searches to prevent connection pool exhaustion
@@ -618,9 +683,27 @@ class MemoryEngine(MemoryEngineInterface):
             await loop.run_in_executor(None, self.query_analyzer.load)
 
         async def verify_llm():
-            """Verify LLM connection is working."""
+            """Verify LLM connections are working for all unique configs."""
             if not self._skip_llm_verification:
+                # Verify default config
                 await self._llm_config.verify_connection()
+                # Verify retain config if different from default
+                retain_is_different = (
+                    self._retain_llm_config.provider != self._llm_config.provider
+                    or self._retain_llm_config.model != self._llm_config.model
+                )
+                if retain_is_different:
+                    await self._retain_llm_config.verify_connection()
+                # Verify reflect config if different from default and retain
+                reflect_is_different = (
+                    self._reflect_llm_config.provider != self._llm_config.provider
+                    or self._reflect_llm_config.model != self._llm_config.model
+                ) and (
+                    self._reflect_llm_config.provider != self._retain_llm_config.provider
+                    or self._reflect_llm_config.model != self._retain_llm_config.model
+                )
+                if reflect_is_different:
+                    await self._reflect_llm_config.verify_connection()
 
         # Build list of initialization tasks
         init_tasks = [
@@ -662,9 +745,9 @@ class MemoryEngine(MemoryEngineInterface):
             self.db_url,
             min_size=self._pool_min_size,
             max_size=self._pool_max_size,
-            command_timeout=60,
+            command_timeout=self._db_command_timeout,
             statement_cache_size=0,  # Disable prepared statement cache
-            timeout=30,  # Connection acquisition timeout (seconds)
+            timeout=self._db_acquire_timeout,  # Connection acquisition timeout (seconds)
         )
 
         # Initialize entity resolver with pool
@@ -971,7 +1054,8 @@ class MemoryEngine(MemoryEngineInterface):
         document_id: str | None = None,
         fact_type_override: str | None = None,
         confidence_score: float | None = None,
-    ) -> list[list[str]]:
+        return_usage: bool = False,
+    ):
         """
         Store multiple content items as memory units in ONE batch operation.
 
@@ -992,9 +1076,11 @@ class MemoryEngine(MemoryEngineInterface):
                         Applies the same document_id to ALL content items that don't specify their own.
             fact_type_override: Override fact type for all facts ('world', 'experience', 'opinion')
             confidence_score: Confidence score for opinions (0.0 to 1.0)
+            return_usage: If True, returns tuple of (unit_ids, TokenUsage). Default False for backward compatibility.
 
         Returns:
-            List of lists of unit IDs (one list per content item)
+            If return_usage=False: List of lists of unit IDs (one list per content item)
+            If return_usage=True: Tuple of (unit_ids, TokenUsage)
 
         Example (new style - per-content document_id):
             unit_ids = await memory.retain_batch_async(
@@ -1021,6 +1107,8 @@ class MemoryEngine(MemoryEngineInterface):
         start_time = time.time()
 
         if not contents:
+            if return_usage:
+                return [], TokenUsage()
             return []
 
         # Authenticate tenant and set schema in context (for fq_table())
@@ -1050,6 +1138,7 @@ class MemoryEngine(MemoryEngineInterface):
         # 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()
 
         CHARS_PER_BATCH = 600_000
 
@@ -1090,7 +1179,7 @@ class MemoryEngine(MemoryEngineInterface):
                     f"Processing sub-batch {i}/{len(sub_batches)}: {len(sub_batch)} items, {sub_batch_chars:,} chars"
                 )
 
-                sub_results = await self._retain_batch_async_internal(
+                sub_results, sub_usage = await self._retain_batch_async_internal(
                     bank_id=bank_id,
                     contents=sub_batch,
                     document_id=document_id,
@@ -1099,6 +1188,7 @@ class MemoryEngine(MemoryEngineInterface):
                     confidence_score=confidence_score,
                 )
                 all_results.extend(sub_results)
+                total_usage = total_usage + sub_usage
 
             total_time = time.time() - start_time
             logger.info(
@@ -1107,7 +1197,7 @@ class MemoryEngine(MemoryEngineInterface):
             result = all_results
         else:
             # Small batch - use internal method directly
-            result = await self._retain_batch_async_internal(
+            result, total_usage = await self._retain_batch_async_internal(
                 bank_id=bank_id,
                 contents=contents,
                 document_id=document_id,
@@ -1136,6 +1226,8 @@ class MemoryEngine(MemoryEngineInterface):
             except Exception as e:
                 logger.warning(f"Post-retain hook error (non-fatal): {e}")
 
+        if return_usage:
+            return result, total_usage
         return result
 
     async def _retain_batch_async_internal(
@@ -1146,7 +1238,7 @@ class MemoryEngine(MemoryEngineInterface):
         is_first_batch: bool = True,
         fact_type_override: str | None = None,
         confidence_score: float | None = None,
-    ) -> list[list[str]]:
+    ) -> tuple[list[list[str]], "TokenUsage"]:
         """
         Internal method for batch processing without chunking logic.
 
@@ -1162,6 +1254,9 @@ class MemoryEngine(MemoryEngineInterface):
             is_first_batch: Whether this is the first batch (for chunked operations, only delete on first batch)
             fact_type_override: Override fact type for all facts
             confidence_score: Confidence score for opinions
+
+        Returns:
+            Tuple of (unit ID lists, token usage for fact extraction)
         """
         # Backpressure: limit concurrent retains to prevent database contention
         async with self._put_semaphore:
@@ -1172,7 +1267,7 @@ class MemoryEngine(MemoryEngineInterface):
             return await orchestrator.retain_batch(
                 pool=pool,
                 embeddings_model=self.embeddings,
-                llm_config=self._llm_config,
+                llm_config=self._retain_llm_config,
                 entity_resolver=self.entity_resolver,
                 task_backend=self._task_backend,
                 format_date_fn=self._format_readable_date,
@@ -2262,6 +2357,7 @@ class MemoryEngine(MemoryEngineInterface):
         bank_id: str | None = None,
         fact_type: str | None = None,
         *,
+        limit: int = 1000,
         request_context: "RequestContext",
     ):
         """
@@ -2270,10 +2366,11 @@ class MemoryEngine(MemoryEngineInterface):
         Args:
             bank_id: Filter by bank ID
             fact_type: Filter by fact type (world, experience, opinion)
+            limit: Maximum number of items to return (default: 1000)
             request_context: Request context for authentication.
 
         Returns:
-            Dict with nodes, edges, and table_rows
+            Dict with nodes, edges, table_rows, total_units, and limit
         """
         await self._authenticate_tenant(request_context)
         pool = await self._get_pool()
@@ -2295,15 +2392,29 @@ class MemoryEngine(MemoryEngineInterface):
 
             where_clause = "WHERE " + " AND ".join(query_conditions) if query_conditions else ""
 
+            # Get total count first
+            total_count_result = await conn.fetchrow(
+                f"""
+                SELECT COUNT(*) as total
+                FROM {fq_table("memory_units")}
+                {where_clause}
+            """,
+                *query_params,
+            )
+            total_count = total_count_result["total"] if total_count_result else 0
+
+            # Get units with limit
+            param_count += 1
             units = await conn.fetch(
                 f"""
                 SELECT id, text, event_date, context, occurred_start, occurred_end, mentioned_at, document_id, chunk_id, fact_type
                 FROM {fq_table("memory_units")}
                 {where_clause}
                 ORDER BY mentioned_at DESC NULLS LAST, event_date DESC
-                LIMIT 1000
+                LIMIT ${param_count}
             """,
                 *query_params,
+                limit,
             )
 
             # Get links, filtering to only include links between units of the selected agent
@@ -2440,7 +2551,7 @@ class MemoryEngine(MemoryEngineInterface):
                 }
             )
 
-        return {"nodes": nodes, "edges": edges, "table_rows": table_rows, "total_units": len(units)}
+        return {"nodes": nodes, "edges": edges, "table_rows": table_rows, "total_units": total_count, "limit": limit}
 
     async def list_memory_units(
         self,
@@ -2803,7 +2914,7 @@ Guidelines:
 - Small changes in confidence are normal; large jumps should be rare"""
 
         try:
-            result = await self._llm_config.call(
+            result = await self._reflect_llm_config.call(
                 messages=[
                     {"role": "system", "content": "You evaluate and update opinions based on new information."},
                     {"role": "user", "content": evaluation_prompt},
@@ -2913,7 +3024,7 @@ Guidelines:
                     return
 
                 # Use cached LLM config
-                if self._llm_config is None:
+                if self._reflect_llm_config is None:
                     logger.error("[REINFORCE] LLM config not available, skipping opinion reinforcement")
                     return
 
@@ -3058,7 +3169,9 @@ Guidelines:
         """
         await self._authenticate_tenant(request_context)
         pool = await self._get_pool()
-        return await bank_utils.merge_bank_background(pool, self._llm_config, bank_id, new_info, update_disposition)
+        return await bank_utils.merge_bank_background(
+            pool, self._reflect_llm_config, bank_id, new_info, update_disposition
+        )
 
     async def list_banks(
         self,
@@ -3118,7 +3231,7 @@ Guidelines:
                 - structured_output: Optional dict if response_schema was provided
         """
         # Use cached LLM config
-        if self._llm_config is None:
+        if self._reflect_llm_config is None:
             raise ValueError("Memory LLM API key not set. Set HINDSIGHT_API_LLM_API_KEY environment variable.")
 
         # Authenticate tenant and set schema in context (for fq_table())
@@ -3144,16 +3257,20 @@ Guidelines:
 
         # Steps 1-3: Run multi-fact-type search (12-way retrieval: 4 methods × 3 fact types)
         recall_start = time.time()
-        search_result = await self.recall_async(
-            bank_id=bank_id,
-            query=query,
-            budget=budget,
-            max_tokens=4096,
-            enable_trace=False,
-            fact_type=["experience", "world", "opinion"],
-            include_entities=True,
-            request_context=request_context,
-        )
+        metrics = get_metrics_collector()
+        with metrics.record_operation(
+            "recall", bank_id=bank_id, source="reflect", budget=budget.value if budget else None
+        ):
+            search_result = await self.recall_async(
+                bank_id=bank_id,
+                query=query,
+                budget=budget,
+                max_tokens=4096,
+                enable_trace=False,
+                fact_type=["experience", "world", "opinion"],
+                include_entities=True,
+                request_context=request_context,
+            )
         recall_time = time.time() - recall_start
 
         all_results = search_result.results
@@ -3209,7 +3326,7 @@ Guidelines:
             response_format = JsonSchemaWrapper(response_schema)
 
         llm_start = time.time()
-        result = await self._llm_config.call(
+        llm_result, usage = await self._reflect_llm_config.call(
             messages=messages,
             scope="memory_reflect",
             max_completion_tokens=max_tokens,
@@ -3218,17 +3335,18 @@ Guidelines:
             # Don't enforce strict_schema - not all providers support it and may retry forever
             # Soft enforcement (schema in prompt + json_object mode) is sufficient
             strict_schema=False,
+            return_usage=True,
         )
         llm_time = time.time() - llm_start
 
         # Handle response based on whether structured output was requested
         if response_schema is not None:
-            structured_output = result
+            structured_output = llm_result
             answer_text = ""  # Empty for backward compatibility
             log_buffer.append(f"[REFLECT {reflect_id}] Structured output generated")
         else:
             structured_output = None
-            answer_text = result.strip()
+            answer_text = llm_result.strip()
 
         # Submit form_opinion task for background processing
         # Pass tenant_id from request context for internal authentication in background task
@@ -3254,6 +3372,7 @@ Guidelines:
             based_on={"world": world_results, "experience": agent_results, "opinion": opinion_results},
             new_opinions=[],  # Opinions are being extracted asynchronously
             structured_output=structured_output,
+            usage=usage,
         )
 
         # Call post-operation hook if validator is configured
@@ -3293,7 +3412,9 @@ Guidelines:
         """
         try:
             # Extract opinions from the answer
-            new_opinions = await think_utils.extract_opinions_from_text(self._llm_config, text=answer_text, query=query)
+            new_opinions = await think_utils.extract_opinions_from_text(
+                self._reflect_llm_config, text=answer_text, query=query
+            )
 
             # Store new opinions
             if new_opinions:
@@ -3544,7 +3665,9 @@ Guidelines:
             )
 
         # Step 3: Extract observations using LLM (no personality)
-        observations = await observation_utils.extract_observations_from_facts(self._llm_config, entity_name, facts)
+        observations = await observation_utils.extract_observations_from_facts(
+            self._reflect_llm_config, entity_name, facts
+        )
 
         if not observations:
             return []

hindsight-api/hindsight_api/engine/response_models.py

@@ -14,6 +14,37 @@ from pydantic import BaseModel, ConfigDict, Field
 VALID_RECALL_FACT_TYPES = frozenset(["world", "experience", "opinion"])
 
 
+class TokenUsage(BaseModel):
+    """
+    Token usage metrics for LLM calls.
+
+    Tracks input/output tokens for a single request to enable
+    per-request cost tracking and monitoring.
+    """
+
+    model_config = ConfigDict(
+        json_schema_extra={
+            "example": {
+                "input_tokens": 1500,
+                "output_tokens": 500,
+                "total_tokens": 2000,
+            }
+        }
+    )
+
+    input_tokens: int = Field(default=0, description="Number of input/prompt tokens consumed")
+    output_tokens: int = Field(default=0, description="Number of output/completion tokens generated")
+    total_tokens: int = Field(default=0, description="Total tokens (input + output)")
+
+    def __add__(self, other: "TokenUsage") -> "TokenUsage":
+        """Allow aggregating token usage from multiple calls."""
+        return TokenUsage(
+            input_tokens=self.input_tokens + other.input_tokens,
+            output_tokens=self.output_tokens + other.output_tokens,
+            total_tokens=self.total_tokens + other.total_tokens,
+        )
+
+
 class DispositionTraits(BaseModel):
     """
     Disposition traits for a memory bank.
@@ -147,6 +178,7 @@ class ReflectResult(BaseModel):
                 },
                 "new_opinions": ["Machine learning has great potential in healthcare"],
                 "structured_output": {"summary": "ML in healthcare", "confidence": 0.9},
+                "usage": {"input_tokens": 1500, "output_tokens": 500, "total_tokens": 2000},
             }
         }
     )
@@ -160,6 +192,10 @@ class ReflectResult(BaseModel):
         default=None,
         description="Structured output parsed according to the provided response schema. Only present when response_schema was provided.",
     )
+    usage: TokenUsage | None = Field(
+        default=None,
+        description="Token usage metrics for the LLM calls made during this reflect operation.",
+    )
 
 
 class Opinion(BaseModel):

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

@@ -14,7 +14,9 @@ from typing import Literal
 
 from pydantic import BaseModel, ConfigDict, Field, field_validator
 
+from ...config import get_config
 from ..llm_wrapper import LLMConfig, OutputTooLongError
+from ..response_models import TokenUsage
 
 
 def _infer_temporal_date(fact_text: str, event_date: datetime) -> str | None:
@@ -109,22 +111,44 @@ class Fact(BaseModel):
 
 
 class CausalRelation(BaseModel):
-    """Causal relationship between facts."""
+    """Causal relationship from this fact to a previous fact (stored format)."""
 
-    target_fact_index: int = Field(
-        description="Index of the related fact in the facts array (0-based). "
-        "This creates a directed causal link to another fact in the extraction."
-    )
-    relation_type: Literal["causes", "caused_by", "enables", "prevents"] = Field(
-        description="Type of causal relationship: "
-        "'causes' = this fact directly causes the target fact, "
-        "'caused_by' = this fact was caused by the target fact, "
-        "'enables' = this fact enables/allows the target fact, "
-        "'prevents' = this fact prevents/blocks the target fact"
+    target_fact_index: int = Field(description="Index of the related fact in the facts array (0-based).")
+    relation_type: Literal["caused_by", "enabled_by", "prevented_by"] = Field(
+        description="How this fact relates to the target: "
+        "'caused_by' = this fact was caused by the target, "
+        "'enabled_by' = this fact was enabled by the target, "
+        "'prevented_by' = this fact was prevented by the target"
     )
     strength: float = Field(
-        description="Strength of causal relationship (0.0 to 1.0). "
-        "1.0 = direct/strong causation, 0.5 = moderate, 0.3 = weak/indirect",
+        description="Strength of relationship (0.0 to 1.0)",
+        ge=0.0,
+        le=1.0,
+        default=1.0,
+    )
+
+
+class FactCausalRelation(BaseModel):
+    """
+    Causal relationship from this fact to a PREVIOUS fact (embedded in each fact).
+
+    Uses index-based references but ONLY allows referencing facts that appear
+    BEFORE this fact in the list. This prevents hallucination of invalid indices.
+    """
+
+    target_index: int = Field(
+        description="Index of the PREVIOUS fact this relates to (0-based). "
+        "MUST be less than this fact's position in the list. "
+        "Example: if this is fact #5, target_index can only be 0, 1, 2, 3, or 4."
+    )
+    relation_type: Literal["caused_by", "enabled_by", "prevented_by"] = Field(
+        description="How this fact relates to the target fact: "
+        "'caused_by' = this fact was caused by the target fact, "
+        "'enabled_by' = this fact was enabled by the target fact, "
+        "'prevented_by' = this fact was blocked/prevented by the target fact"
+    )
+    strength: float = Field(
+        description="Strength of relationship (0.0 to 1.0). 1.0 = strong, 0.5 = moderate",
         ge=0.0,
         le=1.0,
         default=1.0,
@@ -214,8 +238,12 @@ class ExtractedFact(BaseModel):
         default=None,
         description="Named entities, objects, AND abstract concepts from the fact. Include: people names, organizations, places, significant objects (e.g., 'coffee maker', 'car'), AND abstract concepts/themes (e.g., 'friendship', 'career growth', 'loss', 'celebration'). Extract anything that could help link related facts together.",
     )
-    causal_relations: list[CausalRelation] | None = Field(
-        default=None, description="Causal links to other facts. Can be null."
+
+    # Causal relations to PREVIOUS facts only (prevents hallucination of invalid indices)
+    causal_relations: list[FactCausalRelation] | None = Field(
+        default=None,
+        description="Causal links to PREVIOUS facts only. target_index MUST be less than this fact's position. "
+        "Example: fact #3 can only reference facts 0, 1, or 2. Max 2 relations per fact.",
     )
 
     @field_validator("entities", mode="before")
@@ -226,14 +254,6 @@ class ExtractedFact(BaseModel):
             return []
         return v
 
-    @field_validator("causal_relations", mode="before")
-    @classmethod
-    def ensure_causal_relations_list(cls, v):
-        """Ensure causal_relations is always a list (convert None to empty list)."""
-        if v is None:
-            return []
-        return v
-
     def build_fact_text(self) -> str:
         """Combine all dimensions into a single comprehensive fact string."""
         parts = [self.what]
@@ -253,7 +273,7 @@ class ExtractedFact(BaseModel):
 
 
 class FactExtractionResponse(BaseModel):
-    """Response containing all extracted facts."""
+    """Response containing all extracted facts (causal relations are embedded in each fact)."""
 
     facts: list[ExtractedFact] = Field(description="List of extracted factual statements")
 
@@ -356,7 +376,7 @@ async def _extract_facts_from_chunk(
     llm_config: "LLMConfig",
     agent_name: str = None,
     extract_opinions: bool = False,
-) -> list[dict[str, str]]:
+) -> tuple[list[dict[str, str]], TokenUsage]:
     """
     Extract facts from a single chunk (internal helper for parallel processing).
 
@@ -377,6 +397,9 @@ async def _extract_facts_from_chunk(
 
     prompt = f"""Extract facts from text into structured format with FOUR required dimensions - BE EXTREMELY DETAILED.
 
+LANGUAGE REQUIREMENT: Detect the language of the input text. All extracted facts, entity names, descriptions,
+and other output MUST be in the SAME language as the input. Do not translate to English if the input is in another language.
+
 {fact_types_instruction}
 
 
@@ -572,7 +595,52 @@ WHAT TO EXTRACT vs SKIP
 ══════════════════════════════════════════════════════════════════════════
 
 ✅ EXTRACT: User preferences (ALWAYS as separate facts!), feelings, plans, events, relationships, achievements
-❌ SKIP: Greetings, filler ("thanks", "cool"), purely structural statements"""
+❌ SKIP: Greetings, filler ("thanks", "cool"), purely structural statements
+
+══════════════════════════════════════════════════════════════════════════
+CAUSAL RELATIONSHIPS (EMBEDDED IN EACH FACT - REFERENCE PREVIOUS FACTS ONLY)
+══════════════════════════════════════════════════════════════════════════
+
+Each fact can have a `causal_relations` array that links to PREVIOUS facts only.
+⚠️ CRITICAL: target_index MUST be less than this fact's position in the list!
+
+If you're writing fact #5, you can only reference facts 0, 1, 2, 3, or 4.
+This ensures all references are valid.
+
+Relationship types (all describe how THIS fact relates to the target):
+- "caused_by": This fact was caused by the target fact
+- "enabled_by": This fact was enabled/allowed by the target fact
+- "prevented_by": This fact was blocked/prevented by the target fact
+
+Max 2 causal relations per fact. Only add if there's a clear causal link.
+
+Example (Event Date: March 15, 2024):
+Input: "I lost my job in January. Because of that, I couldn't pay rent. So I had to move to a cheaper apartment."
+
+Output facts:
+```json
+{{
+  "facts": [
+    {{
+      "what": "User lost their job in January due to company layoffs",
+      ...other fields...
+      "causal_relations": null  // First fact - nothing to reference
+    }},
+    {{
+      "what": "User couldn't pay rent because of job loss",
+      ...other fields...
+      "causal_relations": [{{"target_index": 0, "relation_type": "caused_by", "strength": 1.0}}]
+    }},
+    {{
+      "what": "User moved to a cheaper apartment",
+      ...other fields...
+      "causal_relations": [{{"target_index": 1, "relation_type": "caused_by", "strength": 0.9}}]
+    }}
+  ]
+}}
+```
+
+This creates: Job loss (0) ← Can't pay rent (1) ← Moved apartment (2)"""
 
     import logging
 
@@ -583,6 +651,7 @@ WHAT TO EXTRACT vs SKIP
     # Retry logic for JSON validation errors
     max_retries = 2
     last_error = None
+    config = get_config()
 
     # Sanitize input text to prevent Unicode encoding errors (e.g., unpaired surrogates)
     sanitized_chunk = _sanitize_text(chunk)
@@ -601,16 +670,19 @@ Context: {sanitized_context}
 Text:
 {sanitized_chunk}"""
 
+    usage = TokenUsage()  # Track cumulative usage across retries
     for attempt in range(max_retries):
         try:
-            extraction_response_json = await llm_config.call(
+            extraction_response_json, call_usage = await llm_config.call(
                 messages=[{"role": "system", "content": prompt}, {"role": "user", "content": user_message}],
                 response_format=FactExtractionResponse,
                 scope="memory_extract_facts",
                 temperature=0.1,
-                max_completion_tokens=65000,
+                max_completion_tokens=config.retain_max_completion_tokens,
                 skip_validation=True,  # Get raw JSON, we'll validate leniently
+                return_usage=True,
             )
+            usage = usage + call_usage  # Aggregate usage across retries
 
             # Lenient parsing of facts from raw JSON
             chunk_facts = []
@@ -628,9 +700,10 @@ Text:
                         f"LLM returned non-dict JSON after {max_retries} attempts: {type(extraction_response_json).__name__}. "
                         f"Raw: {str(extraction_response_json)[:500]}"
                     )
-                    return []
+                    return [], usage
 
             raw_facts = extraction_response_json.get("facts", [])
+
             if not raw_facts:
                 logger.debug(
                     f"LLM response missing 'facts' field or returned empty list. "
@@ -745,19 +818,41 @@ Text:
                     if validated_entities:
                         fact_data["entities"] = validated_entities
 
-                # Add causal relations if present (validate as CausalRelation objects)
-                # Filter out invalid relations (missing required fields)
-                causal_relations = get_value("causal_relations")
-                if causal_relations:
-                    validated_relations = []
-                    for rel in causal_relations:
-                        if isinstance(rel, dict) and "target_fact_index" in rel and "relation_type" in rel:
-                            try:
-                                validated_relations.append(CausalRelation.model_validate(rel))
-                            except Exception as e:
-                                logger.warning(f"Invalid causal relation {rel}: {e}")
-                    if validated_relations:
-                        fact_data["causal_relations"] = validated_relations
+                # Add per-fact causal relations (new schema: target_index must be < current fact index)
+                validated_relations = []
+                causal_relations_raw = get_value("causal_relations")
+                if causal_relations_raw:
+                    for rel in causal_relations_raw:
+                        if not isinstance(rel, dict):
+                            continue
+                        # New schema uses target_index
+                        target_idx = rel.get("target_index")
+                        relation_type = rel.get("relation_type")
+                        strength = rel.get("strength", 1.0)
+
+                        if target_idx is None or relation_type is None:
+                            continue
+
+                        # Validate: target_index must be < current fact index
+                        if target_idx < 0 or target_idx >= i:
+                            logger.debug(
+                                f"Invalid target_index {target_idx} for fact {i} (must be 0 to {i - 1}). Skipping."
+                            )
+                            continue
+
+                        try:
+                            validated_relations.append(
+                                CausalRelation(
+                                    target_fact_index=target_idx,
+                                    relation_type=relation_type,
+                                    strength=strength,
+                                )
+                            )
+                        except Exception as e:
+                            logger.debug(f"Invalid causal relation {rel}: {e}")
+
+                if validated_relations:
+                    fact_data["causal_relations"] = validated_relations
 
                 # Always set mentioned_at to the event_date (when the conversation/document occurred)
                 fact_data["mentioned_at"] = event_date.isoformat()
@@ -778,7 +873,7 @@ Text:
                 )
                 continue
 
-            return chunk_facts
+            return chunk_facts, usage
 
         except BadRequestError as e:
             last_error = e
@@ -805,7 +900,7 @@ async def _extract_facts_with_auto_split(
     llm_config: LLMConfig,
     agent_name: str = None,
     extract_opinions: bool = False,
-) -> list[dict[str, str]]:
+) -> tuple[list[dict[str, str]], TokenUsage]:
     """
     Extract facts from a chunk with automatic splitting if output exceeds token limits.
 
@@ -823,7 +918,7 @@ async def _extract_facts_with_auto_split(
         extract_opinions: If True, extract ONLY opinions. If False, extract world and agent facts (no opinions)
 
     Returns:
-        List of fact dictionaries extracted from the chunk (possibly from sub-chunks)
+        Tuple of (facts list, token usage) extracted from the chunk (possibly from sub-chunks)
     """
     import logging
 
@@ -902,12 +997,14 @@ async def _extract_facts_with_auto_split(
 
         # Combine results from both halves
         all_facts = []
-        for sub_result in sub_results:
-            all_facts.extend(sub_result)
+        total_usage = TokenUsage()
+        for sub_facts, sub_usage in sub_results:
+            all_facts.extend(sub_facts)
+            total_usage = total_usage + sub_usage
 
         logger.info(f"Successfully extracted {len(all_facts)} facts from split chunk {chunk_index + 1}")
 
-        return all_facts
+        return all_facts, total_usage
 
 
 async def extract_facts_from_text(
@@ -917,7 +1014,7 @@ async def extract_facts_from_text(
     agent_name: str,
     context: str = "",
     extract_opinions: bool = False,
-) -> tuple[list[Fact], list[tuple[str, int]]]:
+) -> tuple[list[Fact], list[tuple[str, int]], TokenUsage]:
     """
     Extract semantic facts from conversational or narrative text using LLM.
 
@@ -936,11 +1033,13 @@ async def extract_facts_from_text(
         extract_opinions: If True, extract ONLY opinions. If False, extract world and bank facts (no opinions)
 
     Returns:
-        Tuple of (facts, chunks) where:
+        Tuple of (facts, chunks, usage) where:
         - facts: List of Fact model instances
         - chunks: List of tuples (chunk_text, fact_count) for each chunk
+        - usage: Aggregated token usage across all LLM calls
     """
-    chunks = chunk_text(text, max_chars=3000)
+    config = get_config()
+    chunks = chunk_text(text, max_chars=config.retain_chunk_size)
     tasks = [
         _extract_facts_with_auto_split(
             chunk=chunk,
@@ -957,10 +1056,12 @@ async def extract_facts_from_text(
     chunk_results = await asyncio.gather(*tasks)
     all_facts = []
     chunk_metadata = []  # [(chunk_text, fact_count), ...]
-    for chunk, chunk_facts in zip(chunks, chunk_results):
+    total_usage = TokenUsage()
+    for chunk, (chunk_facts, chunk_usage) in zip(chunks, chunk_results):
         all_facts.extend(chunk_facts)
         chunk_metadata.append((chunk, len(chunk_facts)))
-    return all_facts, chunk_metadata
+        total_usage = total_usage + chunk_usage
+    return all_facts, chunk_metadata, total_usage
 
 
 # ============================================================================
@@ -981,7 +1082,7 @@ SECONDS_PER_FACT = 10
 
 async def extract_facts_from_contents(
     contents: list[RetainContent], llm_config, agent_name: str, extract_opinions: bool = False
-) -> tuple[list[ExtractedFactType], list[ChunkMetadata]]:
+) -> tuple[list[ExtractedFactType], list[ChunkMetadata], TokenUsage]:
     """
     Extract facts from multiple content items in parallel.
 
@@ -998,10 +1099,10 @@ async def extract_facts_from_contents(
         extract_opinions: If True, extract only opinions; otherwise world/bank facts
 
     Returns:
-        Tuple of (extracted_facts, chunks_metadata)
+        Tuple of (extracted_facts, chunks_metadata, usage)
     """
     if not contents:
-        return [], []
+        return [], [], TokenUsage()
 
     # Step 1: Create parallel fact extraction tasks
     fact_extraction_tasks = []
@@ -1024,11 +1125,15 @@ async def extract_facts_from_contents(
     # Step 3: Flatten and convert to typed objects
     extracted_facts: list[ExtractedFactType] = []
     chunks_metadata: list[ChunkMetadata] = []
+    total_usage = TokenUsage()
 
     global_chunk_idx = 0
     global_fact_idx = 0
 
-    for content_index, (content, (facts_from_llm, chunks_from_llm)) in enumerate(zip(contents, all_fact_results)):
+    for content_index, (content, (facts_from_llm, chunks_from_llm, content_usage)) in enumerate(
+        zip(contents, all_fact_results)
+    ):
+        total_usage = total_usage + content_usage
         chunk_start_idx = global_chunk_idx
 
         # Convert chunk tuples to ChunkMetadata objects
@@ -1082,7 +1187,7 @@ async def extract_facts_from_contents(
     # Step 4: Add time offsets to preserve ordering within each content
     _add_temporal_offsets(extracted_facts, contents)
 
-    return extracted_facts, chunks_metadata
+    return extracted_facts, chunks_metadata, total_usage
 
 
 def _parse_datetime(date_str: str):

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

@@ -18,6 +18,7 @@ def utcnow():
     return datetime.now(UTC)
 
 
+from ..response_models import TokenUsage
 from . import (
     chunk_storage,
     deduplication,
@@ -47,7 +48,7 @@ async def retain_batch(
     is_first_batch: bool = True,
     fact_type_override: str | None = None,
     confidence_score: float | None = None,
-) -> list[list[str]]:
+) -> tuple[list[list[str]], TokenUsage]:
     """
     Process a batch of content through the retain pipeline.
 
@@ -67,7 +68,7 @@ async def retain_batch(
         confidence_score: Confidence score for opinions
 
     Returns:
-        List of unit ID lists (one list per content item)
+        Tuple of (unit ID lists, token usage for fact extraction)
     """
     start_time = time.time()
     total_chars = sum(len(item.get("content", "")) for item in contents_dicts)
@@ -99,7 +100,7 @@ async def retain_batch(
     step_start = time.time()
     extract_opinions = fact_type_override == "opinion"
 
-    extracted_facts, chunks = await fact_extraction.extract_facts_from_contents(
+    extracted_facts, chunks, usage = await fact_extraction.extract_facts_from_contents(
         contents, llm_config, agent_name, extract_opinions
     )
     log_buffer.append(
@@ -164,7 +165,7 @@ async def retain_batch(
         logger.info(
             f"RETAIN_BATCH COMPLETE: 0 facts extracted from {len(contents)} contents in {total_time:.3f}s (document tracked, no facts)"
         )
-        return [[] for _ in contents]
+        return [[] for _ in contents], usage
 
     # Apply fact_type_override if provided
     if fact_type_override:
@@ -344,7 +345,7 @@ async def retain_batch(
             non_duplicate_facts = deduplication.filter_duplicates(processed_facts, is_duplicate_flags)
 
             if not non_duplicate_facts:
-                return [[] for _ in contents]
+                return [[] for _ in contents], usage
 
             # Insert facts (document_id is now stored per-fact)
             step_start = time.time()
@@ -415,7 +416,7 @@ async def retain_batch(
 
         logger.info("\n" + "\n".join(log_buffer) + "\n")
 
-        return result_unit_ids
+        return result_unit_ids, usage
 
 
 def _map_results_to_contents(

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

@@ -172,7 +172,7 @@ def get_system_message(disposition: DispositionTraits) -> str:
         " ".join(instructions) if instructions else "Balance your disposition traits when interpreting information."
     )
 
-    return f"You are a person with your own thoughts, experiences, opinions, and disposition. When asked a question, respond naturally like a human would - share what you genuinely think based on what you know and have experienced. {disposition_instruction} Be direct, express your views confidently, and use 'I think', 'I believe', 'in my view', etc. Respond in plain text without markdown formatting."
+    return f"You are a person with your own thoughts, experiences, opinions, and disposition. When asked a question, respond naturally like a human would - share what you genuinely think based on what you know and have experienced. {disposition_instruction} Be direct, express your views confidently, and use 'I think', 'I believe', 'in my view', etc. Respond in plain text without markdown formatting. IMPORTANT: Detect the language of the question and respond in the SAME language. Do not translate to English if the question is in another language."
 
 
 async def extract_opinions_from_text(llm_config, text: str, query: str) -> list[Opinion]:

hindsight-api/hindsight_api/engine/utils.py

@@ -49,7 +49,7 @@ async def extract_facts(
     if not text or not text.strip():
         return [], []
 
-    facts, chunks = await extract_facts_from_text(
+    facts, chunks, _ = await extract_facts_from_text(
         text,
         event_date,
         context=context,

hindsight-api/hindsight_api/main.py

@@ -171,6 +171,14 @@ def main():
             llm_base_url=config.llm_base_url,
             llm_max_concurrent=config.llm_max_concurrent,
             llm_timeout=config.llm_timeout,
+            retain_llm_provider=config.retain_llm_provider,
+            retain_llm_api_key=config.retain_llm_api_key,
+            retain_llm_model=config.retain_llm_model,
+            retain_llm_base_url=config.retain_llm_base_url,
+            reflect_llm_provider=config.reflect_llm_provider,
+            reflect_llm_api_key=config.reflect_llm_api_key,
+            reflect_llm_model=config.reflect_llm_model,
+            reflect_llm_base_url=config.reflect_llm_base_url,
             embeddings_provider=config.embeddings_provider,
             embeddings_local_model=config.embeddings_local_model,
             embeddings_tei_url=config.embeddings_tei_url,
@@ -184,8 +192,17 @@ def main():
             graph_retriever=config.graph_retriever,
             observation_min_facts=config.observation_min_facts,
             observation_top_entities=config.observation_top_entities,
+            retain_max_completion_tokens=config.retain_max_completion_tokens,
+            retain_chunk_size=config.retain_chunk_size,
             skip_llm_verification=config.skip_llm_verification,
             lazy_reranker=config.lazy_reranker,
+            run_migrations_on_startup=config.run_migrations_on_startup,
+            db_pool_min_size=config.db_pool_min_size,
+            db_pool_max_size=config.db_pool_max_size,
+            db_command_timeout=config.db_command_timeout,
+            db_acquire_timeout=config.db_acquire_timeout,
+            task_batch_size=config.task_batch_size,
+            task_batch_interval=config.task_batch_interval,
         )
     config.configure_logging()
     if not args.daemon:
@@ -211,7 +228,11 @@ def main():
         logging.info(f"Loaded tenant extension: {tenant_extension.__class__.__name__}")
 
     # Create MemoryEngine (reads configuration from environment)
-    _memory = MemoryEngine(operation_validator=operation_validator, tenant_extension=tenant_extension)
+    _memory = MemoryEngine(
+        operation_validator=operation_validator,
+        tenant_extension=tenant_extension,
+        run_migrations=config.run_migrations_on_startup,
+    )
 
     # Set extension context on tenant extension (needed for schema provisioning)
     if tenant_extension:

hindsight-api/hindsight_api/metrics.py

@@ -5,6 +5,7 @@ This module provides metrics for:
 - Operation latency (retain, recall, reflect) with percentiles
 - Token usage (input/output) per operation
 - Per-bank granularity via labels
+- LLM call latency and token usage with scope dimension
 """
 
 import logging
@@ -14,8 +15,54 @@ from contextlib import contextmanager
 from opentelemetry import metrics
 from opentelemetry.exporter.prometheus import PrometheusMetricReader
 from opentelemetry.sdk.metrics import MeterProvider
+from opentelemetry.sdk.metrics.view import ExplicitBucketHistogramAggregation, View
 from opentelemetry.sdk.resources import Resource
 
+# Custom bucket boundaries for operation duration (in seconds)
+# Fine granularity in 0-30s range where most operations complete
+DURATION_BUCKETS = (0.1, 0.25, 0.5, 0.75, 1.0, 2.0, 3.0, 5.0, 7.5, 10.0, 15.0, 20.0, 30.0, 60.0, 120.0)
+
+# LLM duration buckets (finer granularity for faster LLM calls)
+LLM_DURATION_BUCKETS = (0.1, 0.25, 0.5, 1.0, 2.0, 3.0, 5.0, 10.0, 15.0, 30.0, 60.0, 120.0)
+
+
+def get_token_bucket(token_count: int) -> str:
+    """
+    Convert a token count to a bucket label for use as a dimension.
+
+    This allows analyzing token usage patterns without high-cardinality issues.
+
+    Buckets:
+    - "0-100": Very small requests/responses
+    - "100-500": Small requests/responses
+    - "500-1k": Medium requests/responses
+    - "1k-5k": Large requests/responses
+    - "5k-10k": Very large requests/responses
+    - "10k-50k": Huge requests/responses
+    - "50k+": Extremely large requests/responses
+
+    Args:
+        token_count: Number of tokens
+
+    Returns:
+        Bucket label string
+    """
+    if token_count < 100:
+        return "0-100"
+    elif token_count < 500:
+        return "100-500"
+    elif token_count < 1000:
+        return "500-1k"
+    elif token_count < 5000:
+        return "1k-5k"
+    elif token_count < 10000:
+        return "5k-10k"
+    elif token_count < 50000:
+        return "10k-50k"
+    else:
+        return "50k+"
+
+
 logger = logging.getLogger(__name__)
 
 # Global meter instance
@@ -48,8 +95,22 @@ def initialize_metrics(service_name: str = "hindsight-api", service_version: str
     # Create Prometheus metric reader
     prometheus_reader = PrometheusMetricReader()
 
-    # Create meter provider with Prometheus exporter
-    provider = MeterProvider(resource=resource, metric_readers=[prometheus_reader])
+    # Create view with custom bucket boundaries for duration histogram
+    duration_view = View(
+        instrument_name="hindsight.operation.duration",
+        aggregation=ExplicitBucketHistogramAggregation(boundaries=DURATION_BUCKETS),
+    )
+
+    # Create view with custom bucket boundaries for LLM duration histogram
+    llm_duration_view = View(
+        instrument_name="hindsight.llm.duration",
+        aggregation=ExplicitBucketHistogramAggregation(boundaries=LLM_DURATION_BUCKETS),
+    )
+
+    # Create meter provider with Prometheus exporter and custom views
+    provider = MeterProvider(
+        resource=resource, metric_readers=[prometheus_reader], views=[duration_view, llm_duration_view]
+    )
 
     # Set the global meter provider
     metrics.set_meter_provider(provider)
@@ -71,20 +132,39 @@ class MetricsCollectorBase:
     """Base class for metrics collectors."""
 
     @contextmanager
-    def record_operation(self, operation: str, bank_id: str, budget: str | None = None, max_tokens: int | None = None):
-        """Context manager to record operation duration and status."""
-        raise NotImplementedError
-
-    def record_tokens(
+    def record_operation(
         self,
         operation: str,
         bank_id: str,
-        input_tokens: int = 0,
-        output_tokens: int = 0,
+        source: str = "api",
         budget: str | None = None,
         max_tokens: int | None = None,
     ):
-        """Record token usage for an operation."""
+        """Context manager to record operation duration and status."""
+        raise NotImplementedError
+
+    def record_llm_call(
+        self,
+        provider: str,
+        model: str,
+        scope: str,
+        duration: float,
+        input_tokens: int = 0,
+        output_tokens: int = 0,
+        success: bool = True,
+    ):
+        """
+        Record metrics for an LLM call.
+
+        Args:
+            provider: LLM provider name (openai, anthropic, gemini, groq, ollama, lmstudio)
+            model: Model name
+            scope: Scope identifier (e.g., "memory", "reflect", "entity_observation")
+            duration: Call duration in seconds
+            input_tokens: Number of input/prompt tokens
+            output_tokens: Number of output/completion tokens
+            success: Whether the call was successful
+        """
         raise NotImplementedError
 
 
@@ -92,20 +172,28 @@ class NoOpMetricsCollector(MetricsCollectorBase):
     """No-op metrics collector that does nothing. Used when metrics are disabled."""
 
     @contextmanager
-    def record_operation(self, operation: str, bank_id: str, budget: str | None = None, max_tokens: int | None = None):
-        """No-op context manager."""
-        yield
-
-    def record_tokens(
+    def record_operation(
         self,
         operation: str,
         bank_id: str,
-        input_tokens: int = 0,
-        output_tokens: int = 0,
+        source: str = "api",
         budget: str | None = None,
         max_tokens: int | None = None,
     ):
-        """No-op token recording."""
+        """No-op context manager."""
+        yield
+
+    def record_llm_call(
+        self,
+        provider: str,
+        model: str,
+        scope: str,
+        duration: float,
+        input_tokens: int = 0,
+        output_tokens: int = 0,
+        success: bool = True,
+    ):
+        """No-op LLM call recording."""
         pass
 
 
@@ -125,33 +213,52 @@ class MetricsCollector(MetricsCollectorBase):
             name="hindsight.operation.duration", description="Duration of Hindsight operations in seconds", unit="s"
         )
 
-        # Token usage counters
-        self.tokens_input = self.meter.create_counter(
-            name="hindsight.tokens.input", description="Number of input tokens consumed", unit="tokens"
-        )
-
-        self.tokens_output = self.meter.create_counter(
-            name="hindsight.tokens.output", description="Number of output tokens generated", unit="tokens"
-        )
-
         # Operation counter (success/failure)
         self.operation_total = self.meter.create_counter(
             name="hindsight.operation.total", description="Total number of operations executed", unit="operations"
         )
 
+        # LLM call latency histogram (in seconds)
+        # Records duration of LLM API calls with provider, model, and scope dimensions
+        self.llm_duration = self.meter.create_histogram(
+            name="hindsight.llm.duration", description="Duration of LLM API calls in seconds", unit="s"
+        )
+
+        # LLM token usage counters with bucket labels
+        self.llm_tokens_input = self.meter.create_counter(
+            name="hindsight.llm.tokens.input", description="Number of input tokens for LLM calls", unit="tokens"
+        )
+
+        self.llm_tokens_output = self.meter.create_counter(
+            name="hindsight.llm.tokens.output", description="Number of output tokens from LLM calls", unit="tokens"
+        )
+
+        # LLM call counter (success/failure)
+        self.llm_calls_total = self.meter.create_counter(
+            name="hindsight.llm.calls.total", description="Total number of LLM API calls", unit="calls"
+        )
+
     @contextmanager
-    def record_operation(self, operation: str, bank_id: str, budget: str | None = None, max_tokens: int | None = None):
+    def record_operation(
+        self,
+        operation: str,
+        bank_id: str,
+        source: str = "api",
+        budget: str | None = None,
+        max_tokens: int | None = None,
+    ):
         """
         Context manager to record operation duration and status.
 
         Usage:
-            with metrics.record_operation("recall", bank_id="user123", budget="mid", max_tokens=4096):
+            with metrics.record_operation("recall", bank_id="user123", source="api", budget="mid", max_tokens=4096):
                 # ... perform operation
                 pass
 
         Args:
-            operation: Operation name (retain, recall, reflect)
+            operation: Operation name (retain, recall, reflect, entity_observation)
             bank_id: Memory bank ID
+            source: Source of the operation (api, reflect, internal)
             budget: Optional budget level (low, mid, high)
             max_tokens: Optional max tokens for the operation
         """
@@ -159,6 +266,7 @@ class MetricsCollector(MetricsCollectorBase):
         attributes = {
             "operation": operation,
             "bank_id": bank_id,
+            "source": source,
         }
         if budget:
             attributes["budget"] = budget
@@ -181,40 +289,56 @@ class MetricsCollector(MetricsCollectorBase):
             # Record operation count
             self.operation_total.add(1, attributes)
 
-    def record_tokens(
+    def record_llm_call(
         self,
-        operation: str,
-        bank_id: str,
+        provider: str,
+        model: str,
+        scope: str,
+        duration: float,
         input_tokens: int = 0,
         output_tokens: int = 0,
-        budget: str | None = None,
-        max_tokens: int | None = None,
+        success: bool = True,
     ):
         """
-        Record token usage for an operation.
+        Record metrics for an LLM call.
 
         Args:
-            operation: Operation name (retain, recall, reflect)
-            bank_id: Memory bank ID
-            input_tokens: Number of input tokens
-            output_tokens: Number of output tokens
-            budget: Optional budget level
-            max_tokens: Optional max tokens for the operation
+            provider: LLM provider name (openai, anthropic, gemini, groq, ollama, lmstudio)
+            model: Model name
+            scope: Scope identifier (e.g., "memory", "reflect", "entity_observation")
+            duration: Call duration in seconds
+            input_tokens: Number of input/prompt tokens
+            output_tokens: Number of output/completion tokens
+            success: Whether the call was successful
         """
-        attributes = {
-            "operation": operation,
-            "bank_id": bank_id,
+        # Base attributes for all metrics
+        base_attributes = {
+            "provider": provider,
+            "model": model,
+            "scope": scope,
+            "success": str(success).lower(),
         }
-        if budget:
-            attributes["budget"] = budget
-        if max_tokens:
-            attributes["max_tokens"] = str(max_tokens)
 
+        # Record duration
+        self.llm_duration.record(duration, base_attributes)
+
+        # Record call count
+        self.llm_calls_total.add(1, base_attributes)
+
+        # Record tokens with bucket labels for cardinality control
         if input_tokens > 0:
-            self.tokens_input.add(input_tokens, attributes)
+            input_attributes = {
+                **base_attributes,
+                "token_bucket": get_token_bucket(input_tokens),
+            }
+            self.llm_tokens_input.add(input_tokens, input_attributes)
 
         if output_tokens > 0:
-            self.tokens_output.add(output_tokens, attributes)
+            output_attributes = {
+                **base_attributes,
+                "token_bucket": get_token_bucket(output_tokens),
+            }
+            self.llm_tokens_output.add(output_tokens, output_attributes)
 
 
 # Global metrics collector instance (defaults to no-op)

hindsight-api/hindsight_api/pg0.py

@@ -132,3 +132,56 @@ async def stop_embedded_postgres() -> None:
     global _default_instance
     if _default_instance:
         await _default_instance.stop()
+
+
+def parse_pg0_url(db_url: str) -> tuple[bool, str | None, int | None]:
+    """
+    Parse a database URL and check if it's a pg0:// embedded database URL.
+
+    Supports:
+    - "pg0" -> default instance "hindsight"
+    - "pg0://instance-name" -> named instance
+    - "pg0://instance-name:port" -> named instance with explicit port
+    - Any other URL (e.g., postgresql://) -> not a pg0 URL
+
+    Args:
+        db_url: The database URL to parse
+
+    Returns:
+        Tuple of (is_pg0, instance_name, port)
+        - is_pg0: True if this is a pg0 URL
+        - instance_name: The instance name (or None if not pg0)
+        - port: The explicit port (or None for auto-assign)
+    """
+    if db_url == "pg0":
+        return True, "hindsight", None
+
+    if db_url.startswith("pg0://"):
+        url_part = db_url[6:]  # Remove "pg0://"
+        if ":" in url_part:
+            instance_name, port_str = url_part.rsplit(":", 1)
+            return True, instance_name or "hindsight", int(port_str)
+        else:
+            return True, url_part or "hindsight", None
+
+    return False, None, None
+
+
+async def resolve_database_url(db_url: str) -> str:
+    """
+    Resolve a database URL, handling pg0:// embedded database URLs.
+
+    If the URL is a pg0:// URL, starts the embedded PostgreSQL and returns
+    the actual postgresql:// connection URL. Otherwise, returns the URL unchanged.
+
+    Args:
+        db_url: Database URL (pg0://, pg0, or postgresql://)
+
+    Returns:
+        The resolved postgresql:// connection URL
+    """
+    is_pg0, instance_name, port = parse_pg0_url(db_url)
+    if is_pg0:
+        pg0 = EmbeddedPostgres(name=instance_name, port=port)
+        return await pg0.ensure_running()
+    return db_url

hindsight-api/pyproject.toml

@@ -38,6 +38,8 @@ dependencies = [
     "dateparser>=1.2.2",
     "google-genai>=1.0.0",
     "anthropic>=0.40.0",
+    "typer>=0.9.0",
+    "cohere>=5.0.0",
 ]
 
 [project.optional-dependencies]
@@ -52,6 +54,7 @@ test = [
 [project.scripts]
 hindsight-api = "hindsight_api.main:main"
 hindsight-local-mcp = "hindsight_api.mcp_local:main"
+hindsight-admin = "hindsight_api.admin.cli:main"
 
 [tool.hatch.build.targets.wheel]
 packages = ["hindsight_api"]
@@ -75,7 +78,7 @@ log_cli = true
 log_cli_level = "INFO"
 log_cli_format = "%(asctime)s - %(levelname)s - %(name)s - %(message)s"
 log_cli_date_format = "%Y-%m-%d %H:%M:%S"
-addopts = "--timeout 120 -n 8 --durations=10 -v"
+addopts = "--timeout 120 -n 8 --dist loadgroup --durations=10 -v"
 asyncio_mode = "auto"
 asyncio_default_fixture_loop_scope = "function"
 log_auto_indent = true

hindsight-api/tests/test_admin_backup_restore.py

@@ -0,0 +1,292 @@
+"""
+Tests for admin backup and restore functionality.
+
+These tests use an isolated schema to avoid interfering with other tests.
+The backup/restore operations truncate tables, which would cause deadlocks
+and race conditions if run against the shared public schema.
+"""
+
+import tempfile
+import uuid
+import zipfile
+from pathlib import Path
+
+import asyncpg
+import pytest
+import pytest_asyncio
+
+from hindsight_api.admin.cli import _backup, _restore, BACKUP_TABLES
+from hindsight_api.migrations import run_migrations
+
+
+# Run these tests sequentially since they do full DB backup/restore
+pytestmark = pytest.mark.xdist_group(name="backup_restore")
+
+
+@pytest_asyncio.fixture(scope="function")
+async def backup_test_schema(pg0_db_url, embeddings):
+    """Create an isolated schema for backup/restore tests.
+
+    Uses a unique schema name per test invocation to avoid conflicts with
+    parallel test runs or leftover state from interrupted runs.
+
+    Returns a tuple of (db_url, schema_name, fq_helper, embeddings).
+    """
+    # Initialize embeddings if not already done
+    await embeddings.initialize()
+
+    # Use unique schema name to avoid conflicts
+    schema_name = f"backup_test_{uuid.uuid4().hex[:8]}"
+
+    def _fq(table: str) -> str:
+        """Get fully-qualified table name in test schema."""
+        return f"{schema_name}.{table}"
+
+    conn = await asyncpg.connect(pg0_db_url)
+    try:
+        await conn.execute(f"CREATE SCHEMA {schema_name}")
+    finally:
+        await conn.close()
+
+    # Run migrations on the isolated schema
+    run_migrations(pg0_db_url, schema=schema_name)
+
+    yield pg0_db_url, schema_name, _fq, embeddings
+
+    # Cleanup after test
+    conn = await asyncpg.connect(pg0_db_url)
+    try:
+        await conn.execute(f"DROP SCHEMA IF EXISTS {schema_name} CASCADE")
+    finally:
+        await conn.close()
+
+
+@pytest.mark.asyncio
+async def test_backup_restore_roundtrip(backup_test_schema):
+    """Test that backup and restore preserves all data correctly."""
+    db_url, schema_name, _fq, embeddings = backup_test_schema
+    bank_id = f"test-backup-{uuid.uuid4().hex[:8]}"
+    conn = await asyncpg.connect(db_url)
+
+    try:
+        # Create a bank
+        await conn.execute(
+            f"INSERT INTO {_fq('banks')} (bank_id) VALUES ($1) ON CONFLICT DO NOTHING",
+            bank_id,
+        )
+
+        # Create some test memory units with embeddings
+        # Convert embedding list to pgvector format string
+        embedding_list = embeddings.encode(["Test content about Alice"])[0]
+        embedding_str = "[" + ",".join(str(x) for x in embedding_list) + "]"
+        for text in [
+            "Alice is a software engineer who loves Python.",
+            "Bob works with Alice on the backend team.",
+            "The team uses PostgreSQL for their database.",
+        ]:
+            await conn.execute(
+                f"""INSERT INTO {_fq('memory_units')}
+                    (bank_id, text, fact_type, embedding, event_date)
+                    VALUES ($1, $2, 'world', $3::vector, NOW())""",
+                bank_id,
+                text,
+                embedding_str,
+            )
+
+        # Get counts before backup
+        counts_before = {}
+        for table in BACKUP_TABLES:
+            counts_before[table] = await conn.fetchval(f"SELECT COUNT(*) FROM {_fq(table)}")
+
+        # Verify we have data
+        assert counts_before["banks"] > 0
+        assert counts_before["memory_units"] > 0
+
+    finally:
+        await conn.close()
+
+    # Backup to a temp file
+    with tempfile.NamedTemporaryFile(suffix=".zip", delete=False) as f:
+        backup_path = Path(f.name)
+
+    try:
+        manifest = await _backup(db_url, backup_path, schema=schema_name)
+
+        # Verify backup file exists and is valid
+        assert backup_path.exists()
+        assert backup_path.stat().st_size > 0
+
+        # Verify manifest
+        assert manifest["version"] == "1"
+        assert "created_at" in manifest
+        for table in BACKUP_TABLES:
+            assert table in manifest["tables"]
+            assert manifest["tables"][table]["rows"] == counts_before[table]
+
+        # Verify zip contents
+        with zipfile.ZipFile(backup_path, "r") as zf:
+            assert "manifest.json" in zf.namelist()
+            for table in BACKUP_TABLES:
+                assert f"{table}.bin" in zf.namelist()
+
+        # Clear all data
+        conn = await asyncpg.connect(db_url)
+        try:
+            for table in reversed(BACKUP_TABLES):
+                await conn.execute(f"TRUNCATE TABLE {_fq(table)} CASCADE")
+
+            # Verify data is gone
+            for table in BACKUP_TABLES:
+                count = await conn.fetchval(f"SELECT COUNT(*) FROM {_fq(table)}")
+                assert count == 0, f"Table {table} should be empty after truncate"
+        finally:
+            await conn.close()
+
+        # Restore from backup
+        await _restore(db_url, backup_path, schema=schema_name)
+
+        # Verify counts match original
+        conn = await asyncpg.connect(db_url)
+        try:
+            for table in BACKUP_TABLES:
+                count = await conn.fetchval(f"SELECT COUNT(*) FROM {_fq(table)}")
+                assert count == counts_before[table], f"Table {table} count mismatch after restore"
+
+            # Verify data content is preserved
+            texts = await conn.fetch(
+                f"SELECT text FROM {_fq('memory_units')} WHERE bank_id = $1",
+                bank_id,
+            )
+            text_content = " ".join(r["text"] for r in texts)
+            assert "Alice" in text_content or "software" in text_content
+        finally:
+            await conn.close()
+
+    finally:
+        # Cleanup
+        if backup_path.exists():
+            backup_path.unlink()
+
+
+@pytest.mark.asyncio
+async def test_backup_restore_preserves_all_column_types(backup_test_schema):
+    """Test that all column types are preserved: vectors, UUIDs, timestamps, JSONB."""
+    db_url, schema_name, _fq, embeddings = backup_test_schema
+    bank_id = f"test-types-{uuid.uuid4().hex[:8]}"
+    conn = await asyncpg.connect(db_url)
+
+    try:
+        # Create a bank
+        await conn.execute(
+            f"INSERT INTO {_fq('banks')} (bank_id) VALUES ($1) ON CONFLICT DO NOTHING",
+            bank_id,
+        )
+
+        # Create a memory unit with all column types
+        # Convert embedding list to pgvector format string
+        embedding_list = embeddings.encode(["John Smith engineer"])[0]
+        embedding_str = "[" + ",".join(str(x) for x in embedding_list) + "]"
+        await conn.execute(
+            f"""INSERT INTO {_fq('memory_units')}
+                (bank_id, text, fact_type, embedding, event_date, metadata)
+                VALUES ($1, $2, 'world', $3::vector, NOW(), $4)""",
+            bank_id,
+            "John Smith is a senior engineer at Acme Corp since 2020.",
+            embedding_str,
+            '{"key": "value"}',
+        )
+
+        # Create an entity
+        await conn.execute(
+            f"""INSERT INTO {_fq('entities')}
+                (bank_id, canonical_name, metadata)
+                VALUES ($1, $2, $3)""",
+            bank_id,
+            "John Smith",
+            '{"role": "engineer"}',
+        )
+
+        # Get original data
+        original_unit = await conn.fetchrow(
+            f"""SELECT id, embedding, event_date, created_at, metadata, text
+               FROM {_fq('memory_units')} WHERE bank_id = $1 LIMIT 1""",
+            bank_id,
+        )
+        original_entity = await conn.fetchrow(
+            f"""SELECT id, first_seen, last_seen, metadata, canonical_name
+               FROM {_fq('entities')} WHERE bank_id = $1 LIMIT 1""",
+            bank_id,
+        )
+        original_bank = await conn.fetchrow(
+            f"SELECT bank_id, created_at, updated_at FROM {_fq('banks')} WHERE bank_id = $1",
+            bank_id,
+        )
+    finally:
+        await conn.close()
+
+    assert original_unit is not None, "Should have created memory units"
+    assert original_unit["embedding"] is not None, "Should have embedding"
+    assert original_unit["id"] is not None, "Should have UUID"
+    assert original_entity is not None, "Should have created entities"
+
+    with tempfile.NamedTemporaryFile(suffix=".zip", delete=False) as f:
+        backup_path = Path(f.name)
+
+    try:
+        await _backup(db_url, backup_path, schema=schema_name)
+
+        # Clear all data
+        conn = await asyncpg.connect(db_url)
+        try:
+            for table in reversed(BACKUP_TABLES):
+                await conn.execute(f"TRUNCATE TABLE {_fq(table)} CASCADE")
+        finally:
+            await conn.close()
+
+        await _restore(db_url, backup_path, schema=schema_name)
+
+        # Verify all column types are preserved exactly
+        conn = await asyncpg.connect(db_url)
+        try:
+            restored_unit = await conn.fetchrow(
+                f"""SELECT id, embedding, event_date, created_at, metadata, text
+                   FROM {_fq('memory_units')} WHERE bank_id = $1 LIMIT 1""",
+                bank_id,
+            )
+            restored_entity = await conn.fetchrow(
+                f"""SELECT id, first_seen, last_seen, metadata, canonical_name
+                   FROM {_fq('entities')} WHERE bank_id = $1 LIMIT 1""",
+                bank_id,
+            )
+            restored_bank = await conn.fetchrow(
+                f"SELECT bank_id, created_at, updated_at FROM {_fq('banks')} WHERE bank_id = $1",
+                bank_id,
+            )
+        finally:
+            await conn.close()
+
+        # Verify memory_units
+        assert restored_unit is not None, "Should have restored memory unit"
+        assert restored_unit["id"] == original_unit["id"], "UUID should match exactly"
+        assert restored_unit["text"] == original_unit["text"], "Text should match"
+        assert list(restored_unit["embedding"]) == list(original_unit["embedding"]), "Vector embedding should match exactly"
+        assert restored_unit["event_date"] == original_unit["event_date"], "Timestamp should match exactly"
+        assert restored_unit["created_at"] == original_unit["created_at"], "Created timestamp should match"
+        assert restored_unit["metadata"] == original_unit["metadata"], "JSONB metadata should match"
+
+        # Verify entities
+        assert restored_entity is not None, "Should have restored entity"
+        assert restored_entity["id"] == original_entity["id"], "Entity UUID should match"
+        assert restored_entity["canonical_name"] == original_entity["canonical_name"], "Entity name should match"
+        assert restored_entity["first_seen"] == original_entity["first_seen"], "Entity first_seen should match"
+        assert restored_entity["last_seen"] == original_entity["last_seen"], "Entity last_seen should match"
+        assert restored_entity["metadata"] == original_entity["metadata"], "Entity metadata should match"
+
+        # Verify banks
+        assert restored_bank is not None, "Should have restored bank"
+        assert restored_bank["bank_id"] == original_bank["bank_id"], "Bank ID should match"
+        assert restored_bank["created_at"] == original_bank["created_at"], "Bank created_at should match"
+
+    finally:
+        if backup_path.exists():
+            backup_path.unlink()

hindsight-api/tests/test_causal_relations.py

@@ -0,0 +1,223 @@
+"""
+Test suite for causal relations extraction and validation.
+
+Tests that:
+1. Causal relations only reference previous facts (target_index < current fact index)
+2. Invalid causal relation indices are rejected
+3. The new per-fact causal relations schema works correctly
+"""
+
+from datetime import datetime
+
+import pytest
+
+from hindsight_api import LLMConfig
+from hindsight_api.engine.retain.fact_extraction import extract_facts_from_text
+
+
+class TestCausalRelationsValidation:
+    """Tests for causal relations index validation."""
+
+    @pytest.mark.asyncio
+    async def test_causal_relations_only_reference_previous_facts(self):
+        """
+        Test that causal relations can only reference facts that appear before them.
+
+        This test verifies the new schema that prevents hallucination of invalid
+        fact indices by constraining target_index to be less than the current fact's index.
+        """
+        # Text with clear causal chain
+        text = """
+        I lost my job in January due to company layoffs.
+        Because I lost my job, I couldn't pay my rent.
+        Since I couldn't afford rent, I had to move to a cheaper apartment.
+        After moving, I started looking for a new job.
+        """
+
+        context = "Personal life update"
+        llm_config = LLMConfig.for_memory()
+        event_date = datetime(2024, 3, 15)
+
+        facts, _, usage = await extract_facts_from_text(
+            text=text,
+            event_date=event_date,
+            context=context,
+            llm_config=llm_config,
+            agent_name="TestUser",
+        )
+
+        assert len(facts) > 0, "Should extract at least one fact"
+
+        # Verify all causal relations reference valid previous facts
+        for i, fact in enumerate(facts):
+            if fact.causal_relations:
+                for rel in fact.causal_relations:
+                    assert rel.target_fact_index < i, (
+                        f"Fact {i} has causal relation to fact {rel.target_fact_index}, "
+                        f"but target_index must be < current index ({i})"
+                    )
+                    assert rel.target_fact_index >= 0, (
+                        f"Fact {i} has negative causal relation index: {rel.target_fact_index}"
+                    )
+                    assert rel.relation_type in ["caused_by", "enabled_by", "prevented_by"], (
+                        f"Invalid relation_type: {rel.relation_type}"
+                    )
+
+    @pytest.mark.asyncio
+    async def test_first_fact_has_no_causal_relations(self):
+        """
+        Test that the first fact (index 0) cannot have causal relations.
+
+        Since causal relations can only reference previous facts,
+        and there are no facts before index 0, the first fact should
+        have no causal relations.
+        """
+        text = """
+        The user started a new machine learning project.
+        The project requires learning TensorFlow.
+        Learning TensorFlow is challenging but rewarding.
+        """
+
+        context = "Project update"
+        llm_config = LLMConfig.for_memory()
+        event_date = datetime(2024, 6, 1)
+
+        facts, _, _ = await extract_facts_from_text(
+            text=text,
+            event_date=event_date,
+            context=context,
+            llm_config=llm_config,
+            agent_name="TestUser",
+        )
+
+        assert len(facts) > 0, "Should extract at least one fact"
+
+        # First fact should have no causal relations (nothing to reference)
+        if facts[0].causal_relations:
+            # If there are causal relations on the first fact, they should be empty
+            # or the validation should have filtered them out
+            for rel in facts[0].causal_relations:
+                # This should never happen due to validation
+                assert False, (
+                    f"First fact should not have causal relations, "
+                    f"but found: target_index={rel.target_fact_index}"
+                )
+
+    @pytest.mark.asyncio
+    async def test_causal_chain_extraction(self):
+        """
+        Test that a clear causal chain is extracted with valid relations.
+        """
+        text = """
+        Emily got promoted to senior engineer last month.
+        Because of her promotion, she received a significant salary increase.
+        With the extra money, she decided to buy a new car.
+        """
+
+        context = "Personal achievement story"
+        llm_config = LLMConfig.for_memory()
+        event_date = datetime(2024, 7, 15)
+
+        facts, _, _ = await extract_facts_from_text(
+            text=text,
+            event_date=event_date,
+            context=context,
+            llm_config=llm_config,
+            agent_name="TestUser",
+        )
+
+        assert len(facts) > 0, "Should extract facts about the causal chain"
+
+        # Collect all causal relations
+        all_relations = []
+        for i, fact in enumerate(facts):
+            if fact.causal_relations:
+                for rel in fact.causal_relations:
+                    all_relations.append({
+                        "from_fact": i,
+                        "to_fact": rel.target_fact_index,
+                        "type": rel.relation_type,
+                    })
+
+        # If causal relations were extracted, verify they form a valid chain
+        if all_relations:
+            for rel in all_relations:
+                assert rel["to_fact"] < rel["from_fact"], (
+                    f"Causal relation from fact {rel['from_fact']} to fact {rel['to_fact']} "
+                    f"is invalid (target must be < source)"
+                )
+
+    @pytest.mark.asyncio
+    async def test_token_efficiency_with_causal_relations(self):
+        """
+        Test that causal relations don't cause excessive output tokens.
+
+        This test verifies that the new schema (per-fact causal relations
+        with index constraints) doesn't waste tokens on invalid relations.
+        """
+        text = """
+        The company announced budget cuts in Q1.
+        Due to the budget cuts, the marketing team was reduced.
+        The reduced team meant fewer campaigns could be run.
+        With fewer campaigns, lead generation dropped.
+        Lower leads resulted in decreased sales.
+        """
+
+        context = "Business impact analysis"
+        llm_config = LLMConfig.for_memory()
+        event_date = datetime(2024, 4, 1)
+
+        facts, _, usage = await extract_facts_from_text(
+            text=text,
+            event_date=event_date,
+            context=context,
+            llm_config=llm_config,
+            agent_name="TestUser",
+        )
+
+        assert len(facts) > 0, "Should extract facts"
+
+        # Calculate output/input ratio
+        if usage.input_tokens > 0:
+            ratio = usage.output_tokens / usage.input_tokens
+            # The ratio should be reasonable (< 5x) with the new schema
+            # Previously it could be 7-10x due to hallucinated indices
+            assert ratio < 6, (
+                f"Output/input token ratio {ratio:.2f}x is too high. "
+                f"Input: {usage.input_tokens}, Output: {usage.output_tokens}"
+            )
+
+    @pytest.mark.asyncio
+    async def test_relation_types_are_backward_looking(self):
+        """
+        Test that all relation types describe how the current fact
+        relates to a previous fact (caused_by, enabled_by, prevented_by).
+        """
+        text = """
+        Alice learned Python programming.
+        Because she knew Python, she got a job as a data scientist.
+        Her data science skills enabled her to lead the analytics team.
+        """
+
+        context = "Career progression"
+        llm_config = LLMConfig.for_memory()
+        event_date = datetime(2024, 5, 1)
+
+        facts, _, _ = await extract_facts_from_text(
+            text=text,
+            event_date=event_date,
+            context=context,
+            llm_config=llm_config,
+            agent_name="TestUser",
+        )
+
+        # Verify relation types are all backward-looking
+        valid_types = {"caused_by", "enabled_by", "prevented_by"}
+
+        for i, fact in enumerate(facts):
+            if fact.causal_relations:
+                for rel in fact.causal_relations:
+                    assert rel.relation_type in valid_types, (
+                        f"Invalid relation_type '{rel.relation_type}'. "
+                        f"Must be one of: {valid_types}"
+                    )

hindsight-api/tests/test_causal_relationships.py

@@ -0,0 +1,202 @@
+"""
+Test suite for causal relationship extraction.
+
+Tests that the fact extraction system correctly identifies and validates
+causal relationships between facts, with valid indices.
+"""
+
+from datetime import datetime
+
+import pytest
+
+from hindsight_api import LLMConfig
+from hindsight_api.engine.retain.fact_extraction import extract_facts_from_text
+
+
+class TestCausalRelationships:
+    """Tests for causal relationship extraction and validation."""
+
+    @pytest.mark.asyncio
+    async def test_causal_chain_extraction(self):
+        """
+        Test that a clear causal chain is extracted with valid relationships.
+
+        Story: Lost job -> couldn't pay rent -> had to move -> found new apartment
+
+        This is a 4-fact causal chain where each fact causes the next.
+        The extracted causal relations should have valid indices (0-3).
+        """
+        text = """
+I lost my job at the tech company in January because of layoffs.
+Because I lost my job, I couldn't pay my rent anymore.
+Since I couldn't afford rent, I had to move out of my apartment.
+After searching for weeks, I finally found a cheaper apartment in Brooklyn.
+"""
+
+        context = "Personal story about housing change"
+        llm_config = LLMConfig.for_memory()
+
+        facts, _, _ = await extract_facts_from_text(
+            text=text, event_date=datetime(2024, 3, 15), context=context, llm_config=llm_config, agent_name="TestUser"
+        )
+
+        assert len(facts) >= 3, f"Should extract at least 3 facts from the causal chain. Got {len(facts)}"
+
+        # Collect all causal relations from all facts
+        all_causal_relations = []
+        for i, fact in enumerate(facts):
+            if fact.causal_relations:
+                for rel in fact.causal_relations:
+                    all_causal_relations.append(
+                        {
+                            "from_fact_index": i,
+                            "to_fact_index": rel.target_fact_index,
+                            "relation_type": rel.relation_type,
+                            "strength": rel.strength,
+                            "from_fact_text": fact.fact[:50],
+                        }
+                    )
+
+        # Verify that ALL causal relation indices are valid
+        # New constraint: target_index must be < from_fact_index (can only reference PREVIOUS facts)
+        num_facts = len(facts)
+        invalid_relations = []
+        for rel in all_causal_relations:
+            # Must be non-negative and less than the current fact's index
+            if rel["to_fact_index"] < 0 or rel["to_fact_index"] >= rel["from_fact_index"]:
+                invalid_relations.append(rel)
+
+        assert len(invalid_relations) == 0, (
+            f"Found {len(invalid_relations)} causal relations with invalid indices! "
+            f"Each target_fact_index must be < from_fact_index (can only reference previous facts). "
+            f"Invalid relations: {invalid_relations}"
+        )
+
+        # Should have at least some causal relations extracted
+        assert len(all_causal_relations) >= 2, (
+            f"Should extract at least 2 causal relationships from this clear chain. "
+            f"Got {len(all_causal_relations)}: {all_causal_relations}"
+        )
+
+        # Verify relation types are valid (passive only - facts reference PREVIOUS facts)
+        valid_types = {"caused_by", "enabled_by", "prevented_by"}
+        for rel in all_causal_relations:
+            assert rel["relation_type"] in valid_types, (
+                f"Invalid relation_type '{rel['relation_type']}'. Must be one of {valid_types}"
+            )
+
+    @pytest.mark.asyncio
+    async def test_complex_causal_web(self):
+        """
+        Test a more complex scenario with multiple interconnected causes.
+
+        This tests the LLM's ability to identify multiple causal links and
+        ensure all referenced indices exist.
+        """
+        text = """
+The heavy rain caused flooding in the basement.
+The flooding damaged the electrical system.
+Because of the electrical damage, we had to call an electrician.
+The electrician found that the wiring was old and needed replacement.
+We decided to renovate the entire basement while fixing the wiring.
+The renovation took three months and cost $15,000.
+"""
+
+        context = "Home repair story"
+        llm_config = LLMConfig.for_memory()
+
+        facts, _, _ = await extract_facts_from_text(
+            text=text, event_date=datetime(2024, 6, 1), context=context, llm_config=llm_config, agent_name="TestUser"
+        )
+
+        assert len(facts) >= 4, f"Should extract at least 4 facts. Got {len(facts)}"
+
+        # Validate all causal relation indices (must reference PREVIOUS facts only)
+        for i, fact in enumerate(facts):
+            if fact.causal_relations:
+                for rel in fact.causal_relations:
+                    assert 0 <= rel.target_fact_index < i, (
+                        f"Fact {i} has causal relation to invalid index {rel.target_fact_index}. "
+                        f"Must reference previous facts only (valid range: 0 to {i - 1}). "
+                        f"Fact text: {fact.fact[:80]}..."
+                    )
+
+    @pytest.mark.asyncio
+    async def test_no_self_referencing_causal_relations(self):
+        """
+        Test that facts don't have causal relations pointing to themselves.
+        """
+        text = """
+I started learning Python because I wanted to automate my work tasks.
+Learning Python led me to discover machine learning.
+Machine learning fascinated me so much that I changed my career to data science.
+"""
+
+        context = "Career change story"
+        llm_config = LLMConfig.for_memory()
+
+        facts, _, _ = await extract_facts_from_text(
+            text=text, event_date=datetime(2024, 1, 1), context=context, llm_config=llm_config, agent_name="TestUser"
+        )
+
+        # Check no fact references itself
+        for i, fact in enumerate(facts):
+            if fact.causal_relations:
+                for rel in fact.causal_relations:
+                    assert rel.target_fact_index != i, (
+                        f"Fact {i} has a self-referencing causal relation! Fact text: {fact.fact}"
+                    )
+
+    @pytest.mark.asyncio
+    async def test_bidirectional_causal_relationships(self):
+        """
+        Test that bidirectional causal relationships (causes and caused_by)
+        are handled correctly.
+        """
+        text = """
+My promotion at work caused me to move to New York.
+Moving to New York was caused by my promotion at work.
+The new role enabled me to lead a team of engineers.
+"""
+
+        context = "Work promotion story"
+        llm_config = LLMConfig.for_memory()
+
+        facts, _, _ = await extract_facts_from_text(
+            text=text, event_date=datetime(2024, 2, 15), context=context, llm_config=llm_config, agent_name="TestUser"
+        )
+
+        # Validate all indices (must reference PREVIOUS facts only)
+        for i, fact in enumerate(facts):
+            if fact.causal_relations:
+                for rel in fact.causal_relations:
+                    assert 0 <= rel.target_fact_index < i, (
+                        f"Invalid target_fact_index {rel.target_fact_index} in fact {i}. "
+                        f"Must reference previous facts only (valid range: 0 to {i - 1})"
+                    )
+
+    @pytest.mark.asyncio
+    async def test_causal_relation_strength_values(self):
+        """
+        Test that causal relation strength values are within valid range [0.0, 1.0].
+        """
+        text = """
+The stock market crash directly caused the company to lay off employees.
+The layoffs indirectly led to reduced consumer spending in the area.
+Reduced spending somewhat affected local businesses.
+"""
+
+        context = "Economic impact story"
+        llm_config = LLMConfig.for_memory()
+
+        facts, _, _ = await extract_facts_from_text(
+            text=text, event_date=datetime(2024, 4, 1), context=context, llm_config=llm_config, agent_name="TestUser"
+        )
+
+        for i, fact in enumerate(facts):
+            if fact.causal_relations:
+                for rel in fact.causal_relations:
+                    assert 0.0 <= rel.strength <= 1.0, (
+                        f"Causal relation strength {rel.strength} is outside valid range [0.0, 1.0]. "
+                        f"Fact {i}: {fact.fact[:50]}..."
+                    )

hindsight-api/tests/test_custom_embedding_dimension.py

@@ -14,8 +14,8 @@ from datetime import datetime
 from sqlalchemy import create_engine, text
 
 from hindsight_api import MemoryEngine, RequestContext
-from hindsight_api.engine.embeddings import LocalSTEmbeddings, OpenAIEmbeddings
-from hindsight_api.engine.cross_encoder import LocalSTCrossEncoder
+from hindsight_api.engine.embeddings import LocalSTEmbeddings, OpenAIEmbeddings, CohereEmbeddings
+from hindsight_api.engine.cross_encoder import LocalSTCrossEncoder, CohereCrossEncoder
 from hindsight_api.engine.query_analyzer import DateparserQueryAnalyzer
 from hindsight_api.extensions import TenantExtension, TenantContext
 from hindsight_api.migrations import run_migrations, ensure_embedding_dimension
@@ -426,3 +426,177 @@ class TestOpenAIEmbeddings:
                     await memory.close()
             except Exception:
                 pass
+
+
+# =============================================================================
+# Cohere Embeddings Tests
+# =============================================================================
+
+
+def has_cohere_api_key() -> bool:
+    """Check if Cohere API key is available."""
+    return bool(os.environ.get("COHERE_API_KEY"))
+
+
+def get_cohere_api_key() -> str:
+    """Get Cohere API key from environment."""
+    return os.environ.get("COHERE_API_KEY", "")
+
+
+@pytest.fixture(scope="module")
+def cohere_embeddings():
+    """Create Cohere embeddings instance."""
+    if not has_cohere_api_key():
+        pytest.skip("Cohere API key not available (set COHERE_API_KEY)")
+
+    embeddings = CohereEmbeddings(
+        api_key=get_cohere_api_key(),
+        model="embed-english-v3.0",
+    )
+    loop = asyncio.new_event_loop()
+    try:
+        loop.run_until_complete(embeddings.initialize())
+    finally:
+        loop.close()
+    return embeddings
+
+
+@pytest.fixture(scope="module")
+def cohere_cross_encoder():
+    """Create Cohere cross-encoder instance."""
+    if not has_cohere_api_key():
+        pytest.skip("Cohere API key not available (set COHERE_API_KEY)")
+
+    cross_encoder = CohereCrossEncoder(
+        api_key=get_cohere_api_key(),
+        model="rerank-english-v3.0",
+    )
+    loop = asyncio.new_event_loop()
+    try:
+        loop.run_until_complete(cross_encoder.initialize())
+    finally:
+        loop.close()
+    return cross_encoder
+
+
+@pytest.fixture(scope="module")
+def cohere_test_schema(pg0_db_url, worker_id, cohere_embeddings):
+    """Create an isolated schema for Cohere embedding tests."""
+    schema_name = get_test_schema("test_cohere_embed", worker_id)
+    create_isolated_schema(pg0_db_url, schema_name, dimension=cohere_embeddings.dimension)
+    yield pg0_db_url, schema_name
+    drop_schema(pg0_db_url, schema_name)
+
+
+class TestCohereEmbeddings:
+    """Tests for Cohere embeddings provider."""
+
+    def test_cohere_embeddings_initialization(self, cohere_embeddings):
+        """Test that Cohere embeddings initializes correctly."""
+        assert cohere_embeddings.dimension == 1024
+        assert cohere_embeddings.provider_name == "cohere"
+
+    def test_cohere_embeddings_encode(self, cohere_embeddings):
+        """Test that Cohere embeddings can encode text."""
+        texts = ["Hello, world!", "This is a test."]
+        embeddings = cohere_embeddings.encode(texts)
+
+        assert len(embeddings) == 2
+        assert len(embeddings[0]) == 1024
+        assert len(embeddings[1]) == 1024
+        assert all(isinstance(x, float) for x in embeddings[0])
+
+
+class TestCohereCrossEncoder:
+    """Tests for Cohere cross-encoder/reranker."""
+
+    def test_cohere_cross_encoder_initialization(self, cohere_cross_encoder):
+        """Test that Cohere cross-encoder initializes correctly."""
+        assert cohere_cross_encoder.provider_name == "cohere"
+
+    def test_cohere_cross_encoder_predict(self, cohere_cross_encoder):
+        """Test that Cohere cross-encoder can score pairs."""
+        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 = 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"
+
+
+class TestCohereIntegration:
+    """Integration tests for Cohere embeddings with memory engine."""
+
+    @pytest.mark.asyncio
+    async def test_cohere_embeddings_retain_recall(
+        self,
+        cohere_test_schema,
+        cohere_embeddings,
+        cohere_cross_encoder,
+        query_analyzer,
+        request_context,
+    ):
+        """Test retain and recall operations with Cohere embeddings."""
+        db_url, schema_name = cohere_test_schema
+        test_bank_id = f"cohere_test_{datetime.now().timestamp()}"
+
+        memory = MemoryEngine(
+            db_url=db_url,
+            memory_llm_provider=os.getenv("HINDSIGHT_API_LLM_PROVIDER", "groq"),
+            memory_llm_api_key=os.getenv("HINDSIGHT_API_LLM_API_KEY"),
+            memory_llm_model=os.getenv("HINDSIGHT_API_LLM_MODEL", "openai/gpt-oss-120b"),
+            memory_llm_base_url=os.getenv("HINDSIGHT_API_LLM_BASE_URL") or None,
+            embeddings=cohere_embeddings,
+            cross_encoder=cohere_cross_encoder,
+            query_analyzer=query_analyzer,
+            pool_min_size=1,
+            pool_max_size=3,
+            run_migrations=False,
+            tenant_extension=SchemaTenantExtension(schema_name),
+        )
+
+        try:
+            await memory.initialize()
+
+            # Store some memories
+            await memory.retain_async(
+                bank_id=test_bank_id,
+                content="Alice works as a software engineer at Google.",
+                context="career discussion",
+                request_context=request_context,
+            )
+
+            await memory.retain_async(
+                bank_id=test_bank_id,
+                content="Bob is a data scientist specializing in machine learning.",
+                context="team introductions",
+                request_context=request_context,
+            )
+
+            # Recall memories
+            result = await memory.recall_async(
+                bank_id=test_bank_id,
+                query="Who works in technology?",
+                request_context=request_context,
+            )
+
+            assert result is not None
+            assert len(result.results) > 0
+
+            memory_texts = [m.text for m in result.results]
+            assert any(
+                "Alice" in text or "Bob" in text or "software" in text or "data scientist" in text
+                for text in memory_texts
+            ), f"Expected to find relevant memories, got: {memory_texts}"
+
+        finally:
+            try:
+                if memory._pool and not memory._pool._closing:
+                    await memory.close()
+            except Exception:
+                pass

hindsight-api/tests/test_fact_extraction_quality.py

@@ -43,7 +43,7 @@ Marcus felt anxious about the upcoming interview.
         context = "Personal journal entry"
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=datetime(2024, 11, 13),
             context=context,
@@ -75,7 +75,7 @@ The music was so loud I could barely hear myself think.
         context = "Personal experience"
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=datetime(2024, 11, 13),
             context=context,
@@ -108,7 +108,7 @@ Maybe we should reconsider the timeline.
         context = "Team discussion"
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=datetime(2024, 11, 13),
             context=context,
@@ -141,7 +141,7 @@ I'm unable to attend the conference due to scheduling conflicts.
         context = "Personal profile discussion"
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=datetime(2024, 11, 13),
             context=context,
@@ -173,7 +173,7 @@ Unlike last year, we're ahead of schedule.
         context = "Project review"
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=datetime(2024, 11, 13),
             context=context,
@@ -206,7 +206,7 @@ She's enthusiastic about the opportunity.
         context = "Team meeting"
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=datetime(2024, 11, 13),
             context=context,
@@ -239,7 +239,7 @@ I'm planning to switch careers because I'm not fulfilled in my current role.
         context = "Personal goals discussion"
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=datetime(2024, 11, 13),
             context=context,
@@ -276,7 +276,7 @@ Family is the most important thing to her.
         context = "Personal values discussion"
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=datetime(2024, 11, 13),
             context=context,
@@ -310,7 +310,7 @@ I prefer presenting in person rather than virtually because I can read the room
 
         event_date = datetime(2024, 11, 13)
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=event_date,
             context=context,
@@ -366,7 +366,7 @@ I'm planning to visit Tokyo next month.
 
         event_date = datetime(2024, 11, 13)
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=event_date,
             context=context,
@@ -419,7 +419,7 @@ with a concert surrounded by music, joy and the warm summer breeze.
 
         for attempt in range(max_retries):
             try:
-                facts, _ = await extract_facts_from_text(
+                facts, _, _ = await extract_facts_from_text(
                     text=text,
                     event_date=event_date,
                     context=context,
@@ -488,7 +488,7 @@ Yesterday I went for a morning jog for the first time in a nearby park.
 
         event_date = datetime(2024, 11, 13)
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=event_date,
             context=context,
@@ -537,7 +537,7 @@ Yesterday I went for a morning jog for the first time in a nearby park.
         This morning I had coffee with Alice.
         """
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=reference_date,
             llm_config=llm_config,
@@ -567,7 +567,7 @@ Yesterday I went for a morning jog for the first time in a nearby park.
 
         text = "Alice works at Google. She loves Python programming."
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=reference_date,
             llm_config=llm_config,
@@ -594,7 +594,7 @@ Yesterday I went for a morning jog for the first time in a nearby park.
         Bob will start his vacation on April 1st.
         """
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=reference_date,
             llm_config=llm_config,
@@ -645,7 +645,7 @@ great time! Every time I see it, I can't help but smile.
 
         event_date = datetime(2023, 2, 23)
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=event_date,
             context=context,
@@ -695,7 +695,7 @@ I've learned so much from it.
         context = "Personal update"
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=datetime(2024, 11, 13),
             context=context,
@@ -758,7 +758,7 @@ Jamie: Congratulations! I'd love to read it.
 
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=transcript,
             event_date=datetime(2024, 11, 13),
             llm_config=llm_config,
@@ -803,7 +803,7 @@ We presented our findings to the team yesterday.
 
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=text,
             event_date=datetime(2024, 11, 13),
             llm_config=llm_config,
@@ -838,7 +838,7 @@ Jamie: [teasing] We'll see who's right, my Niners pick is solid.
 
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=transcript,
             event_date=datetime(2024, 11, 14),
             context=context,
@@ -897,7 +897,7 @@ so the algorithm learns to box out. See you next week!
 
         llm_config = LLMConfig.for_memory()
 
-        facts, _ = await extract_facts_from_text(
+        facts, _, _ = await extract_facts_from_text(
             text=transcript,
             event_date=datetime(2024, 11, 13),
             llm_config=llm_config,

hindsight-api/tests/test_http_api_integration.py

@@ -832,3 +832,134 @@ async def test_reflect_with_max_tokens(api_client):
     # Verify response has text
     assert "text" in result
     assert len(result["text"]) > 0
+
+
+@pytest.mark.asyncio
+async def test_reflect_returns_token_usage(api_client):
+    """Test that reflect endpoint returns token usage metrics.
+
+    The usage field should contain input_tokens, output_tokens, and total_tokens
+    from the LLM call made during reflection.
+    """
+    test_bank_id = f"reflect_usage_test_{datetime.now().timestamp()}"
+
+    # Store a memory to reflect on
+    response = await api_client.post(
+        f"/v1/default/banks/{test_bank_id}/memories",
+        json={
+            "items": [
+                {
+                    "content": "The capital of France is Paris.",
+                    "context": "geography"
+                }
+            ]
+        }
+    )
+    assert response.status_code == 200
+
+    # Call reflect
+    response = await api_client.post(
+        f"/v1/default/banks/{test_bank_id}/reflect",
+        json={
+            "query": "What is the capital of France?"
+        }
+    )
+    assert response.status_code == 200
+    result = response.json()
+
+    # Verify response has text
+    assert "text" in result
+    assert len(result["text"]) > 0
+
+    # Verify usage field exists and has expected structure
+    assert "usage" in result, "Response should include 'usage' field"
+    usage = result["usage"]
+    assert usage is not None, "Usage should not be None for reflect"
+    assert "input_tokens" in usage, "Usage should have 'input_tokens'"
+    assert "output_tokens" in usage, "Usage should have 'output_tokens'"
+    assert "total_tokens" in usage, "Usage should have 'total_tokens'"
+
+    # Verify token counts are valid
+    assert usage["input_tokens"] > 0, f"Expected input_tokens > 0, got {usage['input_tokens']}"
+    assert usage["output_tokens"] >= 0, f"Expected output_tokens >= 0, got {usage['output_tokens']}"
+    assert usage["total_tokens"] == usage["input_tokens"] + usage["output_tokens"]
+
+    print(f"Reflect token usage: input={usage['input_tokens']}, output={usage['output_tokens']}, total={usage['total_tokens']}")
+
+
+@pytest.mark.asyncio
+async def test_retain_returns_token_usage(api_client):
+    """Test that retain endpoint returns token usage metrics for synchronous operations.
+
+    The usage field should contain input_tokens, output_tokens, and total_tokens
+    from the LLM calls made during fact extraction.
+    """
+    test_bank_id = f"retain_usage_test_{datetime.now().timestamp()}"
+
+    # Store memory synchronously (async=false is default)
+    response = await api_client.post(
+        f"/v1/default/banks/{test_bank_id}/memories",
+        json={
+            "items": [
+                {
+                    "content": "Alice is a software engineer at TechCorp. She specializes in machine learning.",
+                    "context": "team introduction"
+                }
+            ]
+        }
+    )
+    assert response.status_code == 200
+    result = response.json()
+
+    # Verify basic response
+    assert result["success"] is True
+    assert result["items_count"] == 1
+    assert result["async"] is False
+
+    # Verify usage field exists and has expected structure
+    assert "usage" in result, "Response should include 'usage' field"
+    usage = result["usage"]
+    assert usage is not None, "Usage should not be None for synchronous retain"
+    assert "input_tokens" in usage, "Usage should have 'input_tokens'"
+    assert "output_tokens" in usage, "Usage should have 'output_tokens'"
+    assert "total_tokens" in usage, "Usage should have 'total_tokens'"
+
+    # Verify token counts are valid
+    assert usage["input_tokens"] > 0, f"Expected input_tokens > 0, got {usage['input_tokens']}"
+    assert usage["output_tokens"] >= 0, f"Expected output_tokens >= 0, got {usage['output_tokens']}"
+    assert usage["total_tokens"] == usage["input_tokens"] + usage["output_tokens"]
+
+    print(f"Retain token usage: input={usage['input_tokens']}, output={usage['output_tokens']}, total={usage['total_tokens']}")
+
+
+@pytest.mark.asyncio
+async def test_retain_async_no_usage(api_client):
+    """Test that async retain does not return usage (as it's processed in background).
+
+    When async=true, the usage field should be None since the actual
+    fact extraction happens asynchronously.
+    """
+    test_bank_id = f"retain_async_no_usage_test_{datetime.now().timestamp()}"
+
+    # Store memory asynchronously
+    response = await api_client.post(
+        f"/v1/default/banks/{test_bank_id}/memories",
+        json={
+            "async": True,
+            "items": [
+                {
+                    "content": "Bob is a data scientist.",
+                    "context": "team introduction"
+                }
+            ]
+        }
+    )
+    assert response.status_code == 200
+    result = response.json()
+
+    # Verify async response
+    assert result["success"] is True
+    assert result["async"] is True
+
+    # Usage should be None for async operations
+    assert result.get("usage") is None, "Async retain should not include usage"

hindsight-api/tests/test_llm_token_metrics.py

@@ -0,0 +1,245 @@
+"""
+Test that LLM calls record token metrics via the metrics collector.
+"""
+import os
+from unittest.mock import MagicMock, patch
+import pytest
+from hindsight_api.engine.llm_wrapper import LLMProvider
+from hindsight_api.metrics import (
+    MetricsCollector,
+    NoOpMetricsCollector,
+    get_metrics_collector,
+)
+
+
+def get_groq_api_key() -> str | None:
+    """Get Groq API key from environment."""
+    return os.getenv("GROQ_API_KEY")
+
+
+@pytest.mark.asyncio
+async def test_llm_metrics_recorded_for_groq():
+    """
+    Test that LLM metrics are recorded when making LLM calls via Groq.
+    Uses openai/gpt-oss-20b as recommended by Hindsight.
+    """
+    api_key = get_groq_api_key()
+    if not api_key:
+        pytest.skip("Skipping: GROQ_API_KEY not set")
+
+    # Create a mock metrics collector to track record_llm_call calls
+    mock_collector = MagicMock(spec=MetricsCollector)
+
+    with patch("hindsight_api.engine.llm_wrapper.get_metrics_collector", return_value=mock_collector):
+        llm = LLMProvider(
+            provider="groq",
+            api_key=api_key,
+            base_url="",
+            model="openai/gpt-oss-20b",
+        )
+
+        # Make an LLM call with clear instruction
+        response = await llm.call(
+            messages=[
+                {"role": "system", "content": "You are a helpful assistant. Always respond."},
+                {"role": "user", "content": "What is 2+2? Reply with just the number."}
+            ],
+            max_completion_tokens=50,
+            scope="test_metrics",
+        )
+
+        # Verify record_llm_call was called - this is the main test
+        assert mock_collector.record_llm_call.called, "record_llm_call should have been called"
+
+        # Get the call arguments
+        call_kwargs = mock_collector.record_llm_call.call_args.kwargs
+
+        # Verify the call had correct structure
+        assert call_kwargs["provider"] == "groq", f"Expected provider='groq', got {call_kwargs}"
+        assert call_kwargs["model"] == "openai/gpt-oss-20b", f"Expected model='openai/gpt-oss-20b', got {call_kwargs}"
+        assert call_kwargs["scope"] == "test_metrics", f"Expected scope='test_metrics', got {call_kwargs}"
+        assert call_kwargs["duration"] > 0, f"Expected duration > 0, got {call_kwargs['duration']}"
+        assert call_kwargs["input_tokens"] > 0, f"Expected input_tokens > 0, got {call_kwargs['input_tokens']}"
+        assert call_kwargs["output_tokens"] >= 0, f"Expected output_tokens >= 0, got {call_kwargs['output_tokens']}"
+        assert call_kwargs["success"] is True, f"Expected success=True, got {call_kwargs['success']}"
+
+        print(f"\nLLM metrics recorded:")
+        print(f"  provider: {call_kwargs['provider']}")
+        print(f"  model: {call_kwargs['model']}")
+        print(f"  scope: {call_kwargs['scope']}")
+        print(f"  duration: {call_kwargs['duration']:.3f}s")
+        print(f"  input_tokens: {call_kwargs['input_tokens']}")
+        print(f"  output_tokens: {call_kwargs['output_tokens']}")
+        print(f"  response: {response}")
+
+
+@pytest.mark.asyncio
+async def test_llm_metrics_recorded_for_structured_output():
+    """
+    Test that LLM metrics are recorded for structured output (JSON) calls.
+    """
+    api_key = get_groq_api_key()
+    if not api_key:
+        pytest.skip("Skipping: GROQ_API_KEY not set")
+
+    from pydantic import BaseModel
+
+    class SimpleResponse(BaseModel):
+        greeting: str
+        language: str
+
+    mock_collector = MagicMock(spec=MetricsCollector)
+
+    with patch("hindsight_api.engine.llm_wrapper.get_metrics_collector", return_value=mock_collector):
+        llm = LLMProvider(
+            provider="groq",
+            api_key=api_key,
+            base_url="",
+            model="openai/gpt-oss-20b",
+        )
+
+        # Make a structured output call
+        response = await llm.call(
+            messages=[{"role": "user", "content": "Say hello in French. Return greeting and language."}],
+            response_format=SimpleResponse,
+            max_completion_tokens=100,
+            scope="structured_output_test",
+        )
+
+        # Verify structured response
+        assert isinstance(response, SimpleResponse)
+        assert response.greeting is not None
+        assert response.language is not None
+
+        # Verify record_llm_call was called
+        assert mock_collector.record_llm_call.called, "record_llm_call should have been called"
+
+        call_kwargs = mock_collector.record_llm_call.call_args.kwargs
+        assert call_kwargs["input_tokens"] > 0
+        assert call_kwargs["output_tokens"] > 0
+
+        print(f"\nStructured output LLM metrics:")
+        print(f"  greeting: {response.greeting}")
+        print(f"  language: {response.language}")
+        print(f"  input_tokens: {call_kwargs['input_tokens']}")
+        print(f"  output_tokens: {call_kwargs['output_tokens']}")
+
+
+@pytest.mark.asyncio
+async def test_noop_collector_when_metrics_disabled():
+    """
+    Test that NoOpMetricsCollector is returned when metrics are not initialized.
+    This verifies the fallback behavior doesn't break LLM calls.
+    """
+    api_key = get_groq_api_key()
+    if not api_key:
+        pytest.skip("Skipping: GROQ_API_KEY not set")
+
+    # Without initializing metrics, get_metrics_collector returns NoOpMetricsCollector
+    collector = get_metrics_collector()
+    assert isinstance(collector, NoOpMetricsCollector), "Should return NoOpMetricsCollector when not initialized"
+
+    # Make an LLM call - should work fine with NoOp collector
+    llm = LLMProvider(
+        provider="groq",
+        api_key=api_key,
+        base_url="",
+        model="openai/gpt-oss-20b",
+    )
+
+    response = await llm.call(
+        messages=[{"role": "user", "content": "Say 'test' in one word."}],
+        max_completion_tokens=50,
+    )
+
+    assert response is not None
+    print(f"\nLLM call succeeded with NoOpMetricsCollector: {response}")
+
+
+@pytest.mark.asyncio
+async def test_return_usage_returns_tuple():
+    """
+    Test that return_usage=True returns (result, TokenUsage) tuple.
+    """
+    from hindsight_api.engine.response_models import TokenUsage
+
+    api_key = get_groq_api_key()
+    if not api_key:
+        pytest.skip("Skipping: GROQ_API_KEY not set")
+
+    llm = LLMProvider(
+        provider="groq",
+        api_key=api_key,
+        base_url="",
+        model="openai/gpt-oss-20b",
+    )
+
+    # Call with return_usage=True
+    result, usage = await llm.call(
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": "What is 2+2? Reply with just the number."}
+        ],
+        max_completion_tokens=50,
+        return_usage=True,
+    )
+
+    # Verify result is the response text
+    assert result is not None
+    assert isinstance(result, str)
+
+    # Verify usage is TokenUsage model with valid counts
+    assert isinstance(usage, TokenUsage)
+    assert usage.input_tokens > 0, f"Expected input_tokens > 0, got {usage.input_tokens}"
+    assert usage.output_tokens >= 0, f"Expected output_tokens >= 0, got {usage.output_tokens}"
+    assert usage.total_tokens == usage.input_tokens + usage.output_tokens
+
+    print(f"\nreturn_usage=True test:")
+    print(f"  result: {result}")
+    print(f"  usage: {usage}")
+
+
+@pytest.mark.asyncio
+async def test_return_usage_with_structured_output():
+    """
+    Test that return_usage=True works with structured output (JSON).
+    """
+    from pydantic import BaseModel
+    from hindsight_api.engine.response_models import TokenUsage
+
+    api_key = get_groq_api_key()
+    if not api_key:
+        pytest.skip("Skipping: GROQ_API_KEY not set")
+
+    class MathAnswer(BaseModel):
+        answer: int
+        explanation: str
+
+    llm = LLMProvider(
+        provider="groq",
+        api_key=api_key,
+        base_url="",
+        model="openai/gpt-oss-20b",
+    )
+
+    # Call with return_usage=True and structured output
+    result, usage = await llm.call(
+        messages=[{"role": "user", "content": "What is 5+3? Return the answer and a brief explanation."}],
+        response_format=MathAnswer,
+        max_completion_tokens=100,
+        return_usage=True,
+    )
+
+    # Verify result is the parsed response
+    assert isinstance(result, MathAnswer)
+    assert result.answer == 8
+    assert result.explanation is not None
+
+    # Verify usage is TokenUsage model
+    assert isinstance(usage, TokenUsage)
+    assert usage.input_tokens > 0
+    assert usage.output_tokens > 0
+
+    print(f"\nStructured output with return_usage=True:")
+    print(f"  result: {result}")
+    print(f"  usage: {usage}")

hindsight-api/tests/test_mcp_routing.py

@@ -9,6 +9,7 @@ def mock_memory():
     """Create a mock MemoryEngine."""
     memory = MagicMock()
     memory.retain_batch_async = AsyncMock()
+    memory.submit_async_retain = AsyncMock(return_value={"operation_id": "test-op-123"})
     memory.recall_async = AsyncMock(return_value=MagicMock(results=[]))
     return memory
 
@@ -44,11 +45,11 @@ async def test_mcp_tools_use_context_bank_id(mock_memory):
     assert "retain" in tools
     assert "recall" in tools
 
-    # Test retain with bank_id from context
+    # Test retain with bank_id from context (use async_processing=False for synchronous test)
     token = _current_bank_id.set("context-bank-id")
     try:
         retain_tool = tools["retain"]
-        result = await retain_tool.fn(content="test content", context="test_context")
+        result = await retain_tool.fn(content="test content", context="test_context", async_processing=False)
         assert "successfully" in result.lower()
 
         # Verify the memory was called with the context bank_id

hindsight-api/tests/test_metrics.py

@@ -0,0 +1,391 @@
+"""Tests for metrics instrumentation."""
+import pytest
+from unittest.mock import MagicMock, patch
+
+from hindsight_api.metrics import (
+    MetricsCollector,
+    MetricsCollectorBase,
+    NoOpMetricsCollector,
+    get_metrics_collector,
+    get_token_bucket,
+    create_metrics_collector,
+    initialize_metrics,
+)
+
+
+class TestNoOpMetricsCollector:
+    """Tests for the no-op metrics collector."""
+
+    def test_record_operation_is_noop(self):
+        """Test that record_operation does nothing."""
+        collector = NoOpMetricsCollector()
+
+        # Should not raise any exception
+        with collector.record_operation("recall", bank_id="test_bank", source="api"):
+            pass
+
+    def test_nested_contexts_work(self):
+        """Test that nested context managers work correctly."""
+        collector = NoOpMetricsCollector()
+
+        # Nested contexts should work without issues
+        with collector.record_operation("reflect", bank_id="test_bank", source="api"):
+            with collector.record_operation("recall", bank_id="test_bank", source="reflect"):
+                pass
+
+    def test_exception_propagates(self):
+        """Test that exceptions inside context are propagated."""
+        collector = NoOpMetricsCollector()
+
+        with pytest.raises(ValueError, match="test error"):
+            with collector.record_operation("recall", bank_id="test_bank"):
+                raise ValueError("test error")
+
+    def test_record_llm_call_is_noop(self):
+        """Test that record_llm_call does nothing."""
+        collector = NoOpMetricsCollector()
+
+        # Should not raise any exception
+        collector.record_llm_call(
+            provider="openai",
+            model="gpt-4",
+            scope="memory",
+            duration=1.5,
+            input_tokens=100,
+            output_tokens=50,
+            success=True,
+        )
+
+
+class TestMetricsCollector:
+    """Tests for the real metrics collector."""
+
+    @pytest.fixture
+    def mock_meter(self):
+        """Create a mock meter for testing."""
+        meter = MagicMock()
+        # Create separate mocks for each histogram (operation_duration, llm_duration)
+        histogram_mocks = [MagicMock(), MagicMock()]
+        meter.create_histogram.side_effect = histogram_mocks
+        # Create separate mocks for each counter
+        # (operation_total, llm_tokens_input, llm_tokens_output, llm_calls_total)
+        counter_mocks = [MagicMock() for _ in range(4)]
+        meter.create_counter.side_effect = counter_mocks
+        return meter
+
+    @pytest.fixture
+    def collector(self, mock_meter):
+        """Create a MetricsCollector with a mock meter."""
+        with patch("hindsight_api.metrics.get_meter", return_value=mock_meter):
+            return MetricsCollector()
+
+    def test_record_operation_records_duration(self, collector):
+        """Test that record_operation records duration."""
+        with collector.record_operation("recall", bank_id="test_bank", source="api"):
+            pass
+
+        # Histogram should have been called
+        collector.operation_duration.record.assert_called_once()
+        call_args = collector.operation_duration.record.call_args
+
+        # First arg is duration (should be > 0)
+        duration = call_args[0][0]
+        assert duration >= 0
+
+        # Second arg is attributes dict
+        attributes = call_args[0][1]
+        assert attributes["operation"] == "recall"
+        assert attributes["bank_id"] == "test_bank"
+        assert attributes["source"] == "api"
+        assert attributes["success"] == "true"
+
+    def test_record_operation_records_failure_on_exception(self, collector):
+        """Test that record_operation records failure when exception occurs."""
+        with pytest.raises(RuntimeError):
+            with collector.record_operation("retain", bank_id="test_bank", source="api"):
+                raise RuntimeError("Test error")
+
+        # Should have recorded with success=false
+        call_args = collector.operation_duration.record.call_args
+        attributes = call_args[0][1]
+        assert attributes["success"] == "false"
+
+    def test_record_operation_with_budget(self, collector):
+        """Test that budget is included in attributes when provided."""
+        with collector.record_operation("recall", bank_id="test_bank", source="api", budget="mid"):
+            pass
+
+        call_args = collector.operation_duration.record.call_args
+        attributes = call_args[0][1]
+        assert attributes["budget"] == "mid"
+
+    def test_record_operation_with_max_tokens(self, collector):
+        """Test that max_tokens is included in attributes when provided."""
+        with collector.record_operation("recall", bank_id="test_bank", source="api", max_tokens=4096):
+            pass
+
+        call_args = collector.operation_duration.record.call_args
+        attributes = call_args[0][1]
+        assert attributes["max_tokens"] == "4096"
+
+    def test_record_operation_source_values(self, collector):
+        """Test different source values: api, reflect, internal."""
+        sources = ["api", "reflect", "internal"]
+
+        for source in sources:
+            collector.operation_duration.record.reset_mock()
+
+            with collector.record_operation("recall", bank_id="test_bank", source=source):
+                pass
+
+            call_args = collector.operation_duration.record.call_args
+            attributes = call_args[0][1]
+            assert attributes["source"] == source
+
+    def test_nested_contexts_track_separately(self, collector):
+        """Test that nested operations are tracked separately with different sources."""
+        # Simulate reflect (api) calling recall (reflect)
+        with collector.record_operation("reflect", bank_id="test_bank", source="api"):
+            with collector.record_operation("recall", bank_id="test_bank", source="reflect"):
+                pass
+
+        # Should have 2 calls to record
+        assert collector.operation_duration.record.call_count == 2
+        assert collector.operation_total.add.call_count == 2
+
+        # Check the calls
+        calls = collector.operation_duration.record.call_args_list
+
+        # First call should be recall (inner context exits first)
+        recall_attrs = calls[0][0][1]
+        assert recall_attrs["operation"] == "recall"
+        assert recall_attrs["source"] == "reflect"
+
+        # Second call should be reflect (outer context exits last)
+        reflect_attrs = calls[1][0][1]
+        assert reflect_attrs["operation"] == "reflect"
+        assert reflect_attrs["source"] == "api"
+
+
+class TestGetMetricsCollector:
+    """Tests for the get_metrics_collector function."""
+
+    def test_returns_noop_by_default(self):
+        """Test that get_metrics_collector returns NoOpMetricsCollector by default."""
+        # Reset global state
+        import hindsight_api.metrics as metrics_module
+        original_collector = metrics_module._metrics_collector
+
+        try:
+            metrics_module._metrics_collector = NoOpMetricsCollector()
+            collector = get_metrics_collector()
+            assert isinstance(collector, NoOpMetricsCollector)
+        finally:
+            metrics_module._metrics_collector = original_collector
+
+
+class TestMetricsCollectorBase:
+    """Tests for the MetricsCollectorBase abstract class."""
+
+    def test_is_abstract(self):
+        """Test that MetricsCollectorBase methods are abstract."""
+        # Create a class that inherits but doesn't implement
+        class IncompleteCollector(MetricsCollectorBase):
+            pass
+
+        collector = IncompleteCollector()
+
+        # Abstract methods should raise NotImplementedError
+        with pytest.raises(NotImplementedError):
+            with collector.record_operation("test", "test"):
+                pass
+
+        with pytest.raises(NotImplementedError):
+            collector.record_llm_call("test", "test", "test", 1.0)
+
+
+class TestGetTokenBucket:
+    """Tests for the get_token_bucket function."""
+
+    def test_bucket_0_100(self):
+        """Test tokens < 100 return '0-100' bucket."""
+        assert get_token_bucket(0) == "0-100"
+        assert get_token_bucket(50) == "0-100"
+        assert get_token_bucket(99) == "0-100"
+
+    def test_bucket_100_500(self):
+        """Test tokens 100-499 return '100-500' bucket."""
+        assert get_token_bucket(100) == "100-500"
+        assert get_token_bucket(250) == "100-500"
+        assert get_token_bucket(499) == "100-500"
+
+    def test_bucket_500_1k(self):
+        """Test tokens 500-999 return '500-1k' bucket."""
+        assert get_token_bucket(500) == "500-1k"
+        assert get_token_bucket(750) == "500-1k"
+        assert get_token_bucket(999) == "500-1k"
+
+    def test_bucket_1k_5k(self):
+        """Test tokens 1000-4999 return '1k-5k' bucket."""
+        assert get_token_bucket(1000) == "1k-5k"
+        assert get_token_bucket(2500) == "1k-5k"
+        assert get_token_bucket(4999) == "1k-5k"
+
+    def test_bucket_5k_10k(self):
+        """Test tokens 5000-9999 return '5k-10k' bucket."""
+        assert get_token_bucket(5000) == "5k-10k"
+        assert get_token_bucket(7500) == "5k-10k"
+        assert get_token_bucket(9999) == "5k-10k"
+
+    def test_bucket_10k_50k(self):
+        """Test tokens 10000-49999 return '10k-50k' bucket."""
+        assert get_token_bucket(10000) == "10k-50k"
+        assert get_token_bucket(25000) == "10k-50k"
+        assert get_token_bucket(49999) == "10k-50k"
+
+    def test_bucket_50k_plus(self):
+        """Test tokens >= 50000 return '50k+' bucket."""
+        assert get_token_bucket(50000) == "50k+"
+        assert get_token_bucket(100000) == "50k+"
+        assert get_token_bucket(1000000) == "50k+"
+
+
+class TestLLMMetrics:
+    """Tests for LLM-specific metrics recording."""
+
+    @pytest.fixture
+    def mock_meter(self):
+        """Create a mock meter for testing."""
+        meter = MagicMock()
+        # Create separate mocks for each histogram (operation_duration, llm_duration)
+        histogram_mocks = [MagicMock(), MagicMock()]
+        meter.create_histogram.side_effect = histogram_mocks
+        # Create separate mocks for each counter
+        # (operation_total, llm_tokens_input, llm_tokens_output, llm_calls_total)
+        counter_mocks = [MagicMock() for _ in range(4)]
+        meter.create_counter.side_effect = counter_mocks
+        return meter
+
+    @pytest.fixture
+    def collector(self, mock_meter):
+        """Create a MetricsCollector with a mock meter."""
+        with patch("hindsight_api.metrics.get_meter", return_value=mock_meter):
+            return MetricsCollector()
+
+    def test_record_llm_call_records_duration(self, collector):
+        """Test that record_llm_call records duration."""
+        collector.record_llm_call(
+            provider="openai",
+            model="gpt-4",
+            scope="memory",
+            duration=1.5,
+            input_tokens=100,
+            output_tokens=50,
+            success=True,
+        )
+
+        # LLM duration histogram should be called
+        collector.llm_duration.record.assert_called_once()
+        call_args = collector.llm_duration.record.call_args
+
+        # First arg is duration
+        assert call_args[0][0] == 1.5
+
+        # Second arg is attributes dict
+        attributes = call_args[0][1]
+        assert attributes["provider"] == "openai"
+        assert attributes["model"] == "gpt-4"
+        assert attributes["scope"] == "memory"
+        assert attributes["success"] == "true"
+
+    def test_record_llm_call_records_failure(self, collector):
+        """Test that record_llm_call records failure status."""
+        collector.record_llm_call(
+            provider="anthropic",
+            model="claude-3",
+            scope="reflect",
+            duration=0.5,
+            success=False,
+        )
+
+        # Check success is false
+        call_args = collector.llm_duration.record.call_args
+        attributes = call_args[0][1]
+        assert attributes["success"] == "false"
+
+    def test_record_llm_call_records_tokens_with_buckets(self, collector):
+        """Test that record_llm_call records tokens with bucket labels."""
+        collector.record_llm_call(
+            provider="openai",
+            model="gpt-4",
+            scope="memory",
+            duration=1.0,
+            input_tokens=2500,  # Should be "1k-5k" bucket
+            output_tokens=150,  # Should be "100-500" bucket
+            success=True,
+        )
+
+        # Input tokens should be recorded with bucket
+        collector.llm_tokens_input.add.assert_called_once()
+        input_call = collector.llm_tokens_input.add.call_args
+        assert input_call[0][0] == 2500
+        assert input_call[0][1]["token_bucket"] == "1k-5k"
+
+        # Output tokens should be recorded with bucket
+        collector.llm_tokens_output.add.assert_called_once()
+        output_call = collector.llm_tokens_output.add.call_args
+        assert output_call[0][0] == 150
+        assert output_call[0][1]["token_bucket"] == "100-500"
+
+    def test_record_llm_call_skips_zero_tokens(self, collector):
+        """Test that zero token values don't record."""
+        collector.record_llm_call(
+            provider="openai",
+            model="gpt-4",
+            scope="memory",
+            duration=1.0,
+            input_tokens=0,
+            output_tokens=0,
+            success=True,
+        )
+
+        # Token counters should not be called
+        collector.llm_tokens_input.add.assert_not_called()
+        collector.llm_tokens_output.add.assert_not_called()
+
+    def test_record_llm_call_increments_call_counter(self, collector):
+        """Test that record_llm_call increments the call counter."""
+        collector.record_llm_call(
+            provider="gemini",
+            model="gemini-pro",
+            scope="entity_observation",
+            duration=2.0,
+            success=True,
+        )
+
+        # Call counter should be incremented
+        collector.llm_calls_total.add.assert_called_once()
+        call_args = collector.llm_calls_total.add.call_args
+        assert call_args[0][0] == 1
+        assert call_args[0][1]["provider"] == "gemini"
+        assert call_args[0][1]["model"] == "gemini-pro"
+        assert call_args[0][1]["scope"] == "entity_observation"
+
+    def test_record_llm_call_different_scopes(self, collector):
+        """Test recording LLM calls with different scopes."""
+        scopes = ["memory", "reflect", "entity_observation", "answer"]
+
+        for scope in scopes:
+            collector.llm_duration.record.reset_mock()
+
+            collector.record_llm_call(
+                provider="openai",
+                model="gpt-4",
+                scope=scope,
+                duration=1.0,
+                success=True,
+            )
+
+            call_args = collector.llm_duration.record.call_args
+            attributes = call_args[0][1]
+            assert attributes["scope"] == scope

hindsight-api/tests/test_multilingual.py

@@ -0,0 +1,286 @@
+"""
+Test multilingual support for retain and reflect operations.
+
+Tests that the system correctly handles non-English input and produces
+output in the same language as the input.
+"""
+
+import pytest
+import logging
+from datetime import datetime, timezone
+from hindsight_api.engine.memory_engine import Budget
+from hindsight_api import RequestContext
+
+logger = logging.getLogger(__name__)
+
+
+@pytest.mark.asyncio
+async def test_retain_chinese_content(memory, request_context):
+    """
+    Test that retain correctly extracts facts from Chinese content
+    and keeps the output in Chinese.
+
+    This test verifies:
+    1. Facts are extracted from Chinese text
+    2. The extracted facts contain Chinese characters
+    3. Entity names are preserved in Chinese
+    """
+    bank_id = f"test_chinese_retain_{datetime.now(timezone.utc).timestamp()}"
+
+    try:
+        # Chinese content about a person and their activities
+        chinese_content = """
+        张伟是一位资深软件工程师，在腾讯工作了五年。他专门研究分布式系统，
+        并领导了公司微服务架构的开发。他以编写干净、文档完善的代码而闻名。
+
+        李明上个月加入团队担任初级开发人员。他正在学习React和Node.js。
+        李明很有热情，在代码审查中提出很好的问题。他最近完成了他的第一个功能，
+        这是一个用户认证流程。
+
+        团队使用Kubernetes进行容器编排，并部署到阿里云。他们遵循敏捷方法论，
+        采用两周冲刺周期。合并前必须进行代码审查。
+        """
+
+        # Retain the Chinese content
+        unit_ids = await memory.retain_async(
+            bank_id=bank_id,
+            content=chinese_content,
+            context="团队概述",  # Chinese context
+            event_date=datetime(2024, 1, 15, tzinfo=timezone.utc),
+            request_context=request_context,
+        )
+
+        logger.info(f"Retained {len(unit_ids)} facts from Chinese content")
+        assert len(unit_ids) > 0, "Should have extracted and stored facts from Chinese content"
+
+        # Recall the facts with a Chinese query
+        result = await memory.recall_async(
+            bank_id=bank_id,
+            query="告诉我关于张伟的信息",  # "Tell me about Zhang Wei"
+            budget=Budget.MID,
+            max_tokens=1000,
+            fact_type=["world"],
+            request_context=request_context,
+        )
+
+        logger.info(f"Recalled {len(result.results)} facts")
+        assert len(result.results) > 0, "Should recall facts about Zhang Wei"
+
+        # Verify that the facts contain Chinese characters
+        # At least one fact should mention 张伟 (Zhang Wei) or related Chinese content
+        chinese_facts_found = 0
+        for fact in result.results:
+            logger.info(f"Fact: {fact.text[:100]}...")
+            # Check for common Chinese characters or the name
+            if any(
+                char in fact.text
+                for char in ["张", "伟", "腾讯", "软件", "工程师", "分布式", "系统", "代码"]
+            ):
+                chinese_facts_found += 1
+
+        logger.info(f"Found {chinese_facts_found} facts with Chinese content")
+        assert chinese_facts_found > 0, (
+            f"Expected facts to contain Chinese characters, but none found. "
+            f"Facts: {[f.text for f in result.results]}"
+        )
+
+        logger.info("Chinese retain test passed - facts preserved in Chinese")
+
+    finally:
+        await memory.delete_bank(bank_id, request_context=request_context)
+
+
+@pytest.mark.asyncio
+async def test_reflect_chinese_content(memory, request_context):
+    """
+    Test that reflect correctly generates responses in Chinese
+    when given Chinese facts and a Chinese query.
+
+    This test verifies:
+    1. Reflection produces a response in Chinese
+    2. The response references the Chinese facts
+    3. Opinions are formed and expressed in Chinese
+    """
+    bank_id = f"test_chinese_reflect_{datetime.now(timezone.utc).timestamp()}"
+
+    try:
+        # Store some Chinese facts to give context for opinion formation
+        await memory.retain_async(
+            bank_id=bank_id,
+            content="张伟是一位优秀的软件工程师，完成了五个重大项目。他总是按时交付，代码整洁有良好的文档。",
+            context="绩效评估",  # "Performance review"
+            event_date=datetime(2024, 1, 15, tzinfo=timezone.utc),
+            request_context=request_context,
+        )
+
+        await memory.retain_async(
+            bank_id=bank_id,
+            content="李明最近加入团队。他错过了第一个截止日期，代码有很多bug。",
+            context="绩效评估",
+            event_date=datetime(2024, 2, 1, tzinfo=timezone.utc),
+            request_context=request_context,
+        )
+
+        # Reflect with a Chinese query
+        query = "谁是更可靠的工程师？"  # "Who is a more reliable engineer?"
+        result = await memory.reflect_async(
+            bank_id=bank_id,
+            query=query,
+            budget=Budget.LOW,
+            request_context=request_context,
+        )
+
+        logger.info(f"Reflection answer: {result.text}")
+
+        # Verify we got an answer
+        assert result.text, "Reflection should return an answer"
+
+        # Check that the response contains Chinese characters
+        # The response should be in Chinese, not English
+        chinese_chars_found = sum(1 for char in result.text if "\u4e00" <= char <= "\u9fff")
+        total_chars = len(result.text.replace(" ", "").replace("\n", ""))
+
+        logger.info(f"Chinese characters: {chinese_chars_found}, Total characters: {total_chars}")
+
+        # At least 30% of characters should be Chinese (allowing for numbers, punctuation)
+        chinese_ratio = chinese_chars_found / max(total_chars, 1)
+        assert chinese_ratio > 0.3, (
+            f"Expected response to be in Chinese (>30% Chinese characters), "
+            f"but only {chinese_ratio:.1%} are Chinese. Response: {result.text}"
+        )
+
+        # Check that Chinese names are mentioned
+        assert "张伟" in result.text or "李明" in result.text, (
+            f"Expected response to mention Chinese names 张伟 or 李明. Response: {result.text}"
+        )
+
+        logger.info("Chinese reflect test passed - response generated in Chinese")
+
+    finally:
+        await memory.delete_bank(bank_id, request_context=request_context)
+
+
+@pytest.mark.asyncio
+async def test_retain_japanese_content(memory, request_context):
+    """
+    Test that retain correctly handles Japanese content.
+
+    This test verifies multilingual support extends beyond Chinese
+    to other non-Latin languages.
+    """
+    bank_id = f"test_japanese_retain_{datetime.now(timezone.utc).timestamp()}"
+
+    try:
+        # Japanese content about a developer
+        japanese_content = """
+        田中さんはソフトウェアエンジニアで、東京のスタートアップで働いています。
+        彼女はPythonとTypeScriptが得意で、毎日コードレビューをしています。
+        先週、新しいAPIを完成させました。
+        """
+
+        unit_ids = await memory.retain_async(
+            bank_id=bank_id,
+            content=japanese_content,
+            context="チームプロフィール",  # "Team profile"
+            event_date=datetime(2024, 1, 15, tzinfo=timezone.utc),
+            request_context=request_context,
+        )
+
+        logger.info(f"Retained {len(unit_ids)} facts from Japanese content")
+        assert len(unit_ids) > 0, "Should have extracted facts from Japanese content"
+
+        # Recall with Japanese query
+        result = await memory.recall_async(
+            bank_id=bank_id,
+            query="田中さんについて教えてください",  # "Tell me about Tanaka-san"
+            budget=Budget.MID,
+            max_tokens=1000,
+            fact_type=["world"],
+            request_context=request_context,
+        )
+
+        assert len(result.results) > 0, "Should recall facts about Tanaka"
+
+        # Check for Japanese content in facts
+        japanese_facts_found = 0
+        for fact in result.results:
+            logger.info(f"Fact: {fact.text[:100]}...")
+            # Check for Japanese characters (hiragana, katakana, or kanji)
+            if any(
+                ("\u3040" <= char <= "\u309f")  # Hiragana
+                or ("\u30a0" <= char <= "\u30ff")  # Katakana
+                or ("\u4e00" <= char <= "\u9fff")  # Kanji
+                for char in fact.text
+            ):
+                japanese_facts_found += 1
+
+        assert japanese_facts_found > 0, (
+            f"Expected facts to contain Japanese characters. "
+            f"Facts: {[f.text for f in result.results]}"
+        )
+
+        logger.info("Japanese retain test passed - facts preserved in Japanese")
+
+    finally:
+        await memory.delete_bank(bank_id, request_context=request_context)
+
+
+@pytest.mark.asyncio
+async def test_mixed_language_entities(memory, request_context):
+    """
+    Test that entity extraction works correctly with mixed language content.
+
+    Some entities (like company names) might be in English while the
+    description is in Chinese.
+    """
+    bank_id = f"test_mixed_lang_{datetime.now(timezone.utc).timestamp()}"
+
+    try:
+        # Mixed language content - Chinese with English company names
+        mixed_content = """
+        王芳在Google北京办公室工作，她是一名高级产品经理。
+        之前她在Microsoft和Amazon工作过。
+        她负责管理YouTube在中国市场的推广策略。
+        """
+
+        unit_ids = await memory.retain_async(
+            bank_id=bank_id,
+            content=mixed_content,
+            context="员工资料",
+            event_date=datetime(2024, 1, 15, tzinfo=timezone.utc),
+            request_context=request_context,
+        )
+
+        assert len(unit_ids) > 0, "Should extract facts from mixed language content"
+
+        # Recall and check entities
+        result = await memory.recall_async(
+            bank_id=bank_id,
+            query="王芳在哪里工作？",  # "Where does Wang Fang work?"
+            budget=Budget.MID,
+            max_tokens=1000,
+            fact_type=["world"],
+            include_entities=True,
+            request_context=request_context,
+        )
+
+        assert len(result.results) > 0, "Should recall facts about Wang Fang"
+
+        # Check that both Chinese and English entities are preserved
+        all_text = " ".join(f.text for f in result.results)
+        logger.info(f"Combined facts: {all_text}")
+
+        # Should contain Chinese name and/or English company names
+        has_chinese_name = "王芳" in all_text
+        has_english_company = any(
+            company in all_text for company in ["Google", "Microsoft", "Amazon", "YouTube"]
+        )
+
+        assert has_chinese_name or has_english_company, (
+            f"Expected mixed language entities. Facts: {all_text}"
+        )
+
+        logger.info("Mixed language entity test passed")
+
+    finally:
+        await memory.delete_bank(bank_id, request_context=request_context)

hindsight-api/tests/test_per_operation_llm_config.py

@@ -0,0 +1,277 @@
+"""
+Tests for per-operation LLM configuration.
+
+Verifies that retain and reflect operations use their respective LLM configs.
+"""
+
+import os
+
+import pytest
+
+
+@pytest.fixture(autouse=True)
+def setup_test_env():
+    """Set up environment for each test, restoring original values after."""
+    from hindsight_api.config import clear_config_cache
+
+    # Save original environment values
+    env_vars_to_set = {
+        "HINDSIGHT_API_SKIP_LLM_VERIFICATION": "true",
+        "HINDSIGHT_API_LAZY_RERANKER": "true",
+        "HINDSIGHT_API_LLM_PROVIDER": "mock",
+        "HINDSIGHT_API_LLM_MODEL": "default-model",
+        "HINDSIGHT_API_RETAIN_LLM_PROVIDER": "mock",
+        "HINDSIGHT_API_RETAIN_LLM_MODEL": "retain-model",
+        "HINDSIGHT_API_REFLECT_LLM_PROVIDER": "mock",
+        "HINDSIGHT_API_REFLECT_LLM_MODEL": "reflect-model",
+    }
+
+    # Save original values
+    original_values = {}
+    for key in env_vars_to_set:
+        original_values[key] = os.environ.get(key)
+
+    # Set test values
+    for key, value in env_vars_to_set.items():
+        os.environ[key] = value
+
+    clear_config_cache()
+
+    yield
+
+    # Restore original environment
+    for key, original_value in original_values.items():
+        if original_value is None:
+            os.environ.pop(key, None)
+        else:
+            os.environ[key] = original_value
+
+    clear_config_cache()
+
+
+class TestPerOperationLLMConfig:
+    """Test that per-operation LLM configs are correctly applied."""
+
+    def test_config_loads_per_operation_settings(self):
+        """Test that config correctly loads per-operation LLM settings."""
+        from hindsight_api.config import get_config
+
+        config = get_config()
+
+        # Default config
+        assert config.llm_provider == "mock"
+        assert config.llm_model == "default-model"
+
+        # Retain config
+        assert config.retain_llm_provider == "mock"
+        assert config.retain_llm_model == "retain-model"
+
+        # Reflect config
+        assert config.reflect_llm_provider == "mock"
+        assert config.reflect_llm_model == "reflect-model"
+
+    def test_memory_engine_creates_separate_llm_configs(self):
+        """Test that MemoryEngine creates separate LLM configs for each operation."""
+        from hindsight_api import MemoryEngine
+
+        engine = MemoryEngine(
+            skip_llm_verification=True,
+            lazy_reranker=True,
+        )
+
+        # Verify default config
+        assert engine._llm_config.provider == "mock"
+        assert engine._llm_config.model == "default-model"
+
+        # Verify retain config
+        assert engine._retain_llm_config.provider == "mock"
+        assert engine._retain_llm_config.model == "retain-model"
+
+        # Verify reflect config
+        assert engine._reflect_llm_config.provider == "mock"
+        assert engine._reflect_llm_config.model == "reflect-model"
+
+    def test_memory_engine_with_explicit_params(self):
+        """Test that explicit params override env config."""
+        from hindsight_api import MemoryEngine
+
+        engine = MemoryEngine(
+            memory_llm_provider="mock",
+            memory_llm_model="explicit-default",
+            retain_llm_provider="mock",
+            retain_llm_model="explicit-retain",
+            reflect_llm_provider="mock",
+            reflect_llm_model="explicit-reflect",
+            skip_llm_verification=True,
+            lazy_reranker=True,
+        )
+
+        assert engine._llm_config.model == "explicit-default"
+        assert engine._retain_llm_config.model == "explicit-retain"
+        assert engine._reflect_llm_config.model == "explicit-reflect"
+
+    def test_memory_engine_fallback_when_no_per_operation_config(self):
+        """Test that per-operation configs fall back to default when not set."""
+        from hindsight_api.config import clear_config_cache as clear_cache
+
+        # Temporarily clear per-operation env vars
+        retain_provider = os.environ.pop("HINDSIGHT_API_RETAIN_LLM_PROVIDER", None)
+        retain_model = os.environ.pop("HINDSIGHT_API_RETAIN_LLM_MODEL", None)
+        reflect_provider = os.environ.pop("HINDSIGHT_API_REFLECT_LLM_PROVIDER", None)
+        reflect_model = os.environ.pop("HINDSIGHT_API_REFLECT_LLM_MODEL", None)
+
+        try:
+            clear_cache()
+            from hindsight_api import MemoryEngine
+
+            engine = MemoryEngine(
+                skip_llm_verification=True,
+                lazy_reranker=True,
+            )
+
+            # All should fall back to default
+            assert engine._llm_config.model == "default-model"
+            assert engine._retain_llm_config.model == "default-model"
+            assert engine._reflect_llm_config.model == "default-model"
+        finally:
+            # Restore env vars
+            if retain_provider:
+                os.environ["HINDSIGHT_API_RETAIN_LLM_PROVIDER"] = retain_provider
+            if retain_model:
+                os.environ["HINDSIGHT_API_RETAIN_LLM_MODEL"] = retain_model
+            if reflect_provider:
+                os.environ["HINDSIGHT_API_REFLECT_LLM_PROVIDER"] = reflect_provider
+            if reflect_model:
+                os.environ["HINDSIGHT_API_REFLECT_LLM_MODEL"] = reflect_model
+            clear_cache()
+
+
+class TestMockLLMProvider:
+    """Test the mock LLM provider functionality."""
+
+    def test_mock_provider_records_calls(self):
+        """Test that mock provider records calls."""
+        from hindsight_api.engine.llm_wrapper import LLMProvider
+
+        provider = LLMProvider(
+            provider="mock",
+            api_key="",
+            base_url="",
+            model="test-model",
+        )
+
+        import asyncio
+
+        async def make_call():
+            return await provider.call(
+                messages=[{"role": "user", "content": "test"}],
+                scope="test_scope",
+            )
+
+        result = asyncio.get_event_loop().run_until_complete(make_call())
+
+        # Verify call was recorded
+        calls = provider.get_mock_calls()
+        assert len(calls) == 1
+        assert calls[0]["model"] == "test-model"
+        assert calls[0]["scope"] == "test_scope"
+        assert calls[0]["messages"] == [{"role": "user", "content": "test"}]
+
+    def test_mock_provider_returns_custom_response(self):
+        """Test that mock provider can return custom responses."""
+        from hindsight_api.engine.llm_wrapper import LLMProvider
+
+        provider = LLMProvider(
+            provider="mock",
+            api_key="",
+            base_url="",
+            model="test-model",
+        )
+
+        provider.set_mock_response({"custom": "response"})
+
+        import asyncio
+
+        async def make_call():
+            return await provider.call(
+                messages=[{"role": "user", "content": "test"}],
+            )
+
+        result = asyncio.get_event_loop().run_until_complete(make_call())
+        assert result == {"custom": "response"}
+
+    def test_mock_provider_returns_usage_when_requested(self):
+        """Test that mock provider returns token usage."""
+        from hindsight_api.engine.llm_wrapper import LLMProvider
+
+        provider = LLMProvider(
+            provider="mock",
+            api_key="",
+            base_url="",
+            model="test-model",
+        )
+
+        import asyncio
+
+        async def make_call():
+            return await provider.call(
+                messages=[{"role": "user", "content": "test"}],
+                return_usage=True,
+            )
+
+        result, usage = asyncio.get_event_loop().run_until_complete(make_call())
+        assert usage.input_tokens == 10
+        assert usage.output_tokens == 5
+        assert usage.total_tokens == 15
+
+
+class TestRetainUsesRetainLLMConfig:
+    """Test that retain operations use the retain LLM config."""
+
+    def test_retain_llm_config_is_passed_to_orchestrator(self):
+        """Verify retain operation is configured to use _retain_llm_config."""
+        from hindsight_api import MemoryEngine
+
+        engine = MemoryEngine(
+            memory_llm_provider="mock",
+            memory_llm_model="default-model",
+            retain_llm_provider="mock",
+            retain_llm_model="retain-specific-model",
+            reflect_llm_provider="mock",
+            reflect_llm_model="reflect-specific-model",
+            skip_llm_verification=True,
+            lazy_reranker=True,
+        )
+
+        # Verify the retain LLM config is set correctly
+        assert engine._retain_llm_config.model == "retain-specific-model"
+        assert engine._retain_llm_config.provider == "mock"
+
+        # Verify it's different from the reflect config
+        assert engine._retain_llm_config.model != engine._reflect_llm_config.model
+
+
+class TestReflectUsesReflectLLMConfig:
+    """Test that reflect operations use the reflect LLM config."""
+
+    def test_reflect_llm_config_is_set_correctly(self):
+        """Verify reflect/think operation is configured to use _reflect_llm_config."""
+        from hindsight_api import MemoryEngine
+
+        engine = MemoryEngine(
+            memory_llm_provider="mock",
+            memory_llm_model="default-model",
+            retain_llm_provider="mock",
+            retain_llm_model="retain-specific-model",
+            reflect_llm_provider="mock",
+            reflect_llm_model="reflect-specific-model",
+            skip_llm_verification=True,
+            lazy_reranker=True,
+        )
+
+        # Verify the reflect LLM config is set correctly
+        assert engine._reflect_llm_config.model == "reflect-specific-model"
+        assert engine._reflect_llm_config.provider == "mock"
+
+        # Verify it's different from the retain config
+        assert engine._reflect_llm_config.model != engine._retain_llm_config.model

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

@@ -51,6 +51,7 @@ hindsight_client_api/models/reflect_request.py
 hindsight_client_api/models/reflect_response.py
 hindsight_client_api/models/retain_request.py
 hindsight_client_api/models/retain_response.py
+hindsight_client_api/models/token_usage.py
 hindsight_client_api/models/update_disposition_request.py
 hindsight_client_api/models/validation_error.py
 hindsight_client_api/models/validation_error_loc_inner.py

hindsight-clients/python/hindsight_client/hindsight_client.py

@@ -74,6 +74,8 @@ class Hindsight:
         """
         config = hindsight_client_api.Configuration(host=base_url, access_token=api_key)
         self._api_client = hindsight_client_api.ApiClient(config)
+        if api_key:
+            self._api_client.set_default_header("Authorization", f"Bearer {api_key}")
         self._memory_api = memory_api.MemoryApi(self._api_client)
         self._banks_api = banks_api.BanksApi(self._api_client)
 

hindsight-clients/python/hindsight_client_api/__init__.py

@@ -76,6 +76,7 @@ from hindsight_client_api.models.reflect_request import ReflectRequest
 from hindsight_client_api.models.reflect_response import ReflectResponse
 from hindsight_client_api.models.retain_request import RetainRequest
 from hindsight_client_api.models.retain_response import RetainResponse
+from hindsight_client_api.models.token_usage import TokenUsage
 from hindsight_client_api.models.update_disposition_request import UpdateDispositionRequest
 from hindsight_client_api.models.validation_error import ValidationError
 from hindsight_client_api.models.validation_error_loc_inner import ValidationErrorLocInner

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

@@ -347,6 +347,7 @@ class MemoryApi:
         self,
         bank_id: StrictStr,
         type: Optional[StrictStr] = None,
+        limit: Optional[StrictInt] = None,
         authorization: Optional[StrictStr] = None,
         _request_timeout: Union[
             None,
@@ -363,12 +364,14 @@ class MemoryApi:
     ) -> GraphDataResponse:
         """Get memory graph data
 
-        Retrieve graph data for visualization, optionally filtered by type (world/experience/opinion). Limited to 1000 most recent items.
+        Retrieve graph data for visualization, optionally filtered by type (world/experience/opinion).
 
         :param bank_id: (required)
         :type bank_id: str
         :param type:
         :type type: str
+        :param limit:
+        :type limit: int
         :param authorization:
         :type authorization: str
         :param _request_timeout: timeout setting for this request. If one
@@ -396,6 +399,7 @@ class MemoryApi:
         _param = self._get_graph_serialize(
             bank_id=bank_id,
             type=type,
+            limit=limit,
             authorization=authorization,
             _request_auth=_request_auth,
             _content_type=_content_type,
@@ -423,6 +427,7 @@ class MemoryApi:
         self,
         bank_id: StrictStr,
         type: Optional[StrictStr] = None,
+        limit: Optional[StrictInt] = None,
         authorization: Optional[StrictStr] = None,
         _request_timeout: Union[
             None,
@@ -439,12 +444,14 @@ class MemoryApi:
     ) -> ApiResponse[GraphDataResponse]:
         """Get memory graph data
 
-        Retrieve graph data for visualization, optionally filtered by type (world/experience/opinion). Limited to 1000 most recent items.
+        Retrieve graph data for visualization, optionally filtered by type (world/experience/opinion).
 
         :param bank_id: (required)
         :type bank_id: str
         :param type:
         :type type: str
+        :param limit:
+        :type limit: int
         :param authorization:
         :type authorization: str
         :param _request_timeout: timeout setting for this request. If one
@@ -472,6 +479,7 @@ class MemoryApi:
         _param = self._get_graph_serialize(
             bank_id=bank_id,
             type=type,
+            limit=limit,
             authorization=authorization,
             _request_auth=_request_auth,
             _content_type=_content_type,
@@ -499,6 +507,7 @@ class MemoryApi:
         self,
         bank_id: StrictStr,
         type: Optional[StrictStr] = None,
+        limit: Optional[StrictInt] = None,
         authorization: Optional[StrictStr] = None,
         _request_timeout: Union[
             None,
@@ -515,12 +524,14 @@ class MemoryApi:
     ) -> RESTResponseType:
         """Get memory graph data
 
-        Retrieve graph data for visualization, optionally filtered by type (world/experience/opinion). Limited to 1000 most recent items.
+        Retrieve graph data for visualization, optionally filtered by type (world/experience/opinion).
 
         :param bank_id: (required)
         :type bank_id: str
         :param type:
         :type type: str
+        :param limit:
+        :type limit: int
         :param authorization:
         :type authorization: str
         :param _request_timeout: timeout setting for this request. If one
@@ -548,6 +559,7 @@ class MemoryApi:
         _param = self._get_graph_serialize(
             bank_id=bank_id,
             type=type,
+            limit=limit,
             authorization=authorization,
             _request_auth=_request_auth,
             _content_type=_content_type,
@@ -570,6 +582,7 @@ class MemoryApi:
         self,
         bank_id,
         type,
+        limit,
         authorization,
         _request_auth,
         _content_type,
@@ -599,6 +612,10 @@ class MemoryApi:
             
             _query_params.append(('type', type))
             
+        if limit is not None:
+            
+            _query_params.append(('limit', limit))
+            
         # process the header parameters
         if authorization is not None:
             _header_params['authorization'] = authorization

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

@@ -54,6 +54,7 @@ from hindsight_client_api.models.reflect_request import ReflectRequest
 from hindsight_client_api.models.reflect_response import ReflectResponse
 from hindsight_client_api.models.retain_request import RetainRequest
 from hindsight_client_api.models.retain_response import RetainResponse
+from hindsight_client_api.models.token_usage import TokenUsage
 from hindsight_client_api.models.update_disposition_request import UpdateDispositionRequest
 from hindsight_client_api.models.validation_error import ValidationError
 from hindsight_client_api.models.validation_error_loc_inner import ValidationErrorLocInner

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

@@ -30,7 +30,8 @@ class GraphDataResponse(BaseModel):
     edges: List[Dict[str, Any]]
     table_rows: List[Dict[str, Any]]
     total_units: StrictInt
-    __properties: ClassVar[List[str]] = ["nodes", "edges", "table_rows", "total_units"]
+    limit: StrictInt
+    __properties: ClassVar[List[str]] = ["nodes", "edges", "table_rows", "total_units", "limit"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -86,7 +87,8 @@ class GraphDataResponse(BaseModel):
             "nodes": obj.get("nodes"),
             "edges": obj.get("edges"),
             "table_rows": obj.get("table_rows"),
-            "total_units": obj.get("total_units")
+            "total_units": obj.get("total_units"),
+            "limit": obj.get("limit")
         })
         return _obj
 

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

@@ -20,6 +20,7 @@ import json
 from pydantic import BaseModel, ConfigDict, StrictStr
 from typing import Any, ClassVar, Dict, List, Optional
 from hindsight_client_api.models.reflect_fact import ReflectFact
+from hindsight_client_api.models.token_usage import TokenUsage
 from typing import Optional, Set
 from typing_extensions import Self
 
@@ -30,7 +31,8 @@ class ReflectResponse(BaseModel):
     text: StrictStr
     based_on: Optional[List[ReflectFact]] = None
     structured_output: Optional[Dict[str, Any]] = None
-    __properties: ClassVar[List[str]] = ["text", "based_on", "structured_output"]
+    usage: Optional[TokenUsage] = None
+    __properties: ClassVar[List[str]] = ["text", "based_on", "structured_output", "usage"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -78,11 +80,19 @@ class ReflectResponse(BaseModel):
                 if _item_based_on:
                     _items.append(_item_based_on.to_dict())
             _dict['based_on'] = _items
+        # override the default output from pydantic by calling `to_dict()` of usage
+        if self.usage:
+            _dict['usage'] = self.usage.to_dict()
         # set to None if structured_output (nullable) is None
         # and model_fields_set contains the field
         if self.structured_output is None and "structured_output" in self.model_fields_set:
             _dict['structured_output'] = None
 
+        # set to None if usage (nullable) is None
+        # and model_fields_set contains the field
+        if self.usage is None and "usage" in self.model_fields_set:
+            _dict['usage'] = None
+
         return _dict
 
     @classmethod
@@ -97,7 +107,8 @@ class ReflectResponse(BaseModel):
         _obj = cls.model_validate({
             "text": obj.get("text"),
             "based_on": [ReflectFact.from_dict(_item) for _item in obj["based_on"]] if obj.get("based_on") is not None else None,
-            "structured_output": obj.get("structured_output")
+            "structured_output": obj.get("structured_output"),
+            "usage": TokenUsage.from_dict(obj["usage"]) if obj.get("usage") is not None else None
         })
         return _obj
 

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

@@ -18,7 +18,8 @@ import re  # noqa: F401
 import json
 
 from pydantic import BaseModel, ConfigDict, Field, StrictBool, StrictInt, StrictStr
-from typing import Any, ClassVar, Dict, List
+from typing import Any, ClassVar, Dict, List, Optional
+from hindsight_client_api.models.token_usage import TokenUsage
 from typing import Optional, Set
 from typing_extensions import Self
 
@@ -30,7 +31,8 @@ class RetainResponse(BaseModel):
     bank_id: StrictStr
     items_count: StrictInt
     var_async: StrictBool = Field(description="Whether the operation was processed asynchronously", alias="async")
-    __properties: ClassVar[List[str]] = ["success", "bank_id", "items_count", "async"]
+    usage: Optional[TokenUsage] = None
+    __properties: ClassVar[List[str]] = ["success", "bank_id", "items_count", "async", "usage"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -71,6 +73,14 @@ class RetainResponse(BaseModel):
             exclude=excluded_fields,
             exclude_none=True,
         )
+        # override the default output from pydantic by calling `to_dict()` of usage
+        if self.usage:
+            _dict['usage'] = self.usage.to_dict()
+        # set to None if usage (nullable) is None
+        # and model_fields_set contains the field
+        if self.usage is None and "usage" in self.model_fields_set:
+            _dict['usage'] = None
+
         return _dict
 
     @classmethod
@@ -86,7 +96,8 @@ class RetainResponse(BaseModel):
             "success": obj.get("success"),
             "bank_id": obj.get("bank_id"),
             "items_count": obj.get("items_count"),
-            "async": obj.get("async")
+            "async": obj.get("async"),
+            "usage": TokenUsage.from_dict(obj["usage"]) if obj.get("usage") is not None else None
         })
         return _obj
 

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

@@ -0,0 +1,91 @@
+# coding: utf-8
+
+"""
+    Hindsight HTTP API
+
+    HTTP API for Hindsight
+
+    The version of the OpenAPI document: 0.1.0
+    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, Field, StrictInt
+from typing import Any, ClassVar, Dict, List, Optional
+from typing import Optional, Set
+from typing_extensions import Self
+
+class TokenUsage(BaseModel):
+    """
+    Token usage metrics for LLM calls.  Tracks input/output tokens for a single request to enable per-request cost tracking and monitoring.
+    """ # noqa: E501
+    input_tokens: Optional[StrictInt] = Field(default=0, description="Number of input/prompt tokens consumed")
+    output_tokens: Optional[StrictInt] = Field(default=0, description="Number of output/completion tokens generated")
+    total_tokens: Optional[StrictInt] = Field(default=0, description="Total tokens (input + output)")
+    __properties: ClassVar[List[str]] = ["input_tokens", "output_tokens", "total_tokens"]
+
+    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 TokenUsage 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,
+        )
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of TokenUsage from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "input_tokens": obj.get("input_tokens") if obj.get("input_tokens") is not None else 0,
+            "output_tokens": obj.get("output_tokens") if obj.get("output_tokens") is not None else 0,
+            "total_tokens": obj.get("total_tokens") if obj.get("total_tokens") is not None else 0
+        })
+        return _obj
+
+

hindsight-clients/rust/Cargo.lock

@@ -284,9 +284,9 @@ dependencies = [
 
 [[package]]
 name = "h2"
-version = "0.4.12"
+version = "0.4.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f3c0b69cfcb4e1b9f1bf2f53f95f766e4661169728ec61cd3fe5a0166f2d1386"
+checksum = "2f44da3a8150a6703ed5d34e164b875fd14c2cdab9af1252a9a1020bde2bdc54"
 dependencies = [
  "atomic-waker",
  "bytes",
@@ -840,9 +840,9 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.104"
+version = "1.0.105"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9695f8df41bb4f3d222c95a67532365f569318332d03d5f3f67f37b20e6ebdf0"
+checksum = "535d180e0ecab6268a3e718bb9fd44db66bbbc256257165fc699dadf70d16fe7"
 dependencies = [
  "unicode-ident",
 ]
@@ -915,9 +915,9 @@ dependencies = [
 
 [[package]]
 name = "quote"
-version = "1.0.42"
+version = "1.0.43"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a338cc41d27e6cc6dce6cefc13a0729dfbb81c262b1f519331575dd80ef3067f"
+checksum = "dc74d9a594b72ae6656596548f56f667211f8a97b3d4c3d467150794690dc40a"
 dependencies = [
  "proc-macro2",
 ]
@@ -1048,9 +1048,9 @@ dependencies = [
 
 [[package]]
 name = "rustls"
-version = "0.23.35"
+version = "0.23.36"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "533f54bc6a7d4f647e46ad909549eda97bf5afc1585190ef692b4286b198bd8f"
+checksum = "c665f33d38cea657d9614f766881e4d510e0eda4239891eea56b4cadcf01801b"
 dependencies = [
  "once_cell",
  "rustls-pki-types",
@@ -1208,9 +1208,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.148"
+version = "1.0.149"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3084b546a1dd6289475996f182a22aba973866ea8e8b02c51d9f46b1336a22da"
+checksum = "83fc039473c5595ace860d8c4fafa220ff474b3fc6bfdb4293327f1a37e94d86"
 dependencies = [
  "itoa",
  "memchr",
@@ -1641,9 +1641,9 @@ checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1"
 
 [[package]]
 name = "url"
-version = "2.5.7"
+version = "2.5.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "08bc136a29a3d1758e07a9cca267be308aeebf5cfd5a10f3f67ab2097683ef5b"
+checksum = "ff67a8a4397373c3ef660812acab3268222035010ab8680ec4215f38ba3d0eed"
 dependencies = [
  "form_urlencoded",
  "idna",
@@ -2102,6 +2102,6 @@ dependencies = [
 
 [[package]]
 name = "zmij"
-version = "1.0.10"
+version = "1.0.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "30e0d8dffbae3d840f64bda38e28391faef673a7b5a6017840f2a106c8145868"
+checksum = "2fc5a66a20078bf1251bde995aa2fdcc4b800c70b5d92dd2c62abc5c60f679f8"

hindsight-clients/typescript/.prettierrc

@@ -0,0 +1,8 @@
+{
+  "tabWidth": 2,
+  "useTabs": false,
+  "semi": true,
+  "singleQuote": false,
+  "trailingComma": "all",
+  "printWidth": 80
+}

hindsight-clients/typescript/generated/sdk.gen.ts

@@ -123,7 +123,7 @@ export const metricsEndpointMetricsGet = <ThrowOnError extends boolean = false>(
 /**
  * Get memory graph data
  *
- * Retrieve graph data for visualization, optionally filtered by type (world/experience/opinion). Limited to 1000 most recent items.
+ * Retrieve graph data for visualization, optionally filtered by type (world/experience/opinion).
  */
 export const getGraph = <ThrowOnError extends boolean = false>(
   options: Options<GetGraphData, ThrowOnError>,

hindsight-clients/typescript/generated/types.gen.ts

@@ -570,6 +570,10 @@ export type GraphDataResponse = {
    * Total Units
    */
   total_units: number;
+  /**
+   * Limit
+   */
+  limit: number;
 };
 
 /**
@@ -966,6 +970,10 @@ export type ReflectResponse = {
   structured_output?: {
     [key: string]: unknown;
   } | null;
+  /**
+   * Token usage metrics for LLM calls during reflection.
+   */
+  usage?: TokenUsage | null;
 };
 
 /**
@@ -1010,6 +1018,39 @@ export type RetainResponse = {
    * Whether the operation was processed asynchronously
    */
   async: boolean;
+  /**
+   * Token usage metrics for LLM calls during fact extraction (only present for synchronous operations)
+   */
+  usage?: TokenUsage | null;
+};
+
+/**
+ * TokenUsage
+ *
+ * Token usage metrics for LLM calls.
+ *
+ * Tracks input/output tokens for a single request to enable
+ * per-request cost tracking and monitoring.
+ */
+export type TokenUsage = {
+  /**
+   * Input Tokens
+   *
+   * Number of input/prompt tokens consumed
+   */
+  input_tokens?: number;
+  /**
+   * Output Tokens
+   *
+   * Number of output/completion tokens generated
+   */
+  output_tokens?: number;
+  /**
+   * Total Tokens
+   *
+   * Total tokens (input + output)
+   */
+  total_tokens?: number;
 };
 
 /**
@@ -1086,6 +1127,10 @@ export type GetGraphData = {
      * Type
      */
     type?: string | null;
+    /**
+     * Limit
+     */
+    limit?: number;
   };
   url: "/v1/default/banks/{bank_id}/graph";
 };

hindsight-clients/typescript/package.json

@@ -26,7 +26,7 @@
     "directory": "hindsight-clients/typescript"
   },
   "devDependencies": {
-    "@hey-api/openapi-ts": "^0.88.0",
+    "@hey-api/openapi-ts": "0.88.0",
     "@types/jest": "^29.0.0",
     "@types/node": "^20.0.0",
     "jest": "^29.0.0",

hindsight-control-plane/src/app/api/graph/route.ts

@@ -12,12 +12,15 @@ export async function GET(request: NextRequest) {
 
     // Get optional query parameters
     const type = searchParams.get("type") || searchParams.get("fact_type") || undefined;
+    const limitParam = searchParams.get("limit");
+    const limit = limitParam ? parseInt(limitParam, 10) : undefined;
 
     const response = await sdk.getGraph({
       client: lowLevelClient,
       path: { bank_id: bankId },
       query: {
         type: type,
+        limit: limit,
       },
     });
 

hindsight-control-plane/src/components/data-view.tsx

@@ -52,6 +52,9 @@ export function DataView({ factType }: DataViewProps) {
   const [selectedTableMemory, setSelectedTableMemory] = useState<any>(null);
   const itemsPerPage = 100;
 
+  // Fetch limit state - how many memories to load from the API
+  const [fetchLimit, setFetchLimit] = useState(1000);
+
   // Graph controls state
   const [showLabels, setShowLabels] = useState(true);
   const [maxNodes, setMaxNodes] = useState<number | undefined>(undefined);
@@ -93,7 +96,7 @@ export function DataView({ factType }: DataViewProps) {
     }
   };
 
-  const loadData = async () => {
+  const loadData = async (limit?: number) => {
     if (!currentBank) return;
 
     setLoading(true);
@@ -101,6 +104,7 @@ export function DataView({ factType }: DataViewProps) {
       const graphData: any = await client.getGraph({
         bank_id: currentBank,
         type: factType,
+        limit: limit ?? fetchLimit,
       });
       setData(graphData);
     } catch (error) {
@@ -265,9 +269,25 @@ export function DataView({ factType }: DataViewProps) {
 
           <div className="flex items-center justify-between mb-6">
             <div className="text-sm text-muted-foreground">
-              {searchQuery
-                ? `${filteredTableRows.length} of ${data.total_units} memories`
-                : `${data.total_units} total memories`}
+              {searchQuery ? (
+                `${filteredTableRows.length} of ${data.table_rows?.length ?? 0} loaded memories`
+              ) : data.table_rows?.length < data.total_units ? (
+                <span>
+                  Showing {data.table_rows?.length ?? 0} of {data.total_units} total memories
+                  <button
+                    onClick={() => {
+                      const newLimit = Math.min(data.total_units, fetchLimit + 1000);
+                      setFetchLimit(newLimit);
+                      loadData(newLimit);
+                    }}
+                    className="ml-2 text-primary hover:underline"
+                  >
+                    Load more
+                  </button>
+                </span>
+              ) : (
+                `${data.total_units} total memories`
+              )}
             </div>
             <div className="flex items-center gap-2 bg-muted rounded-lg p-1">
               <button

hindsight-control-plane/src/lib/api.ts

@@ -109,10 +109,11 @@ export class ControlPlaneClient {
   /**
    * Get graph data
    */
-  async getGraph(params: { bank_id: string; type?: string }) {
+  async getGraph(params: { bank_id: string; type?: string; limit?: number }) {
     const queryParams = new URLSearchParams();
     queryParams.append("bank_id", params.bank_id);
     if (params.type) queryParams.append("type", params.type);
+    if (params.limit) queryParams.append("limit", params.limit.toString());
     return this.fetchApi(`/api/graph?${queryParams}`);
   }
 

hindsight-docs/docs/changelog/index.md

@@ -8,6 +8,12 @@ This changelog highlights user-facing changes only. Internal maintenance, CI/CD,
 
 For full release details, see [GitHub Releases](https://github.com/vectorize-io/hindsight/releases).
 
+## [Unreleased]
+
+**Features**
+
+- Add per-request token usage tracking to retain and reflect endpoints for cost monitoring and billing integration.
+
 ## [0.2.0](https://github.com/vectorize-io/hindsight/releases/tag/v0.2.0)
 
 **Features**

hindsight-docs/docs/developer/admin-cli.md

@@ -0,0 +1,145 @@
+# Admin CLI
+
+The `hindsight-admin` CLI provides administrative commands for managing your Hindsight deployment, including database migrations, backup, and restore operations.
+
+## Installation
+
+The admin CLI is included with the `hindsight-api` package:
+
+```bash
+pip install hindsight-api
+# or
+uv add hindsight-api
+```
+
+## Commands
+
+### run-db-migration
+
+Run database migrations to the latest version. This is useful when you want to run migrations separately from API startup (e.g., in CI/CD pipelines or before deploying a new version).
+
+```bash
+hindsight-admin run-db-migration [OPTIONS]
+```
+
+**Options:**
+
+| Option | Description | Default |
+|--------|-------------|---------|
+| `--schema`, `-s` | Database schema to run migrations on | `public` |
+
+**Examples:**
+
+```bash
+# Run migrations on the default public schema
+hindsight-admin run-db-migration
+
+# Run migrations on a specific tenant schema
+hindsight-admin run-db-migration --schema tenant_acme
+```
+
+:::tip Disabling Auto-Migrations
+To disable automatic migrations on API startup, set `HINDSIGHT_API_RUN_MIGRATIONS_ON_STARTUP=false`. This is useful when you want to run migrations as a separate step in your deployment pipeline.
+:::
+
+---
+
+### backup
+
+Create a backup of all Hindsight data to a zip file.
+
+```bash
+hindsight-admin backup OUTPUT [OPTIONS]
+```
+
+**Arguments:**
+
+| Argument | Description |
+|----------|-------------|
+| `OUTPUT` | Output file path (will add `.zip` extension if not present) |
+
+**Options:**
+
+| Option | Description | Default |
+|--------|-------------|---------|
+| `--schema`, `-s` | Database schema to backup | `public` |
+
+**Examples:**
+
+```bash
+# Backup to a file
+hindsight-admin backup /backups/hindsight-2024-01-15.zip
+
+# Backup a specific tenant schema
+hindsight-admin backup /backups/tenant-acme.zip --schema tenant_acme
+```
+
+The backup includes:
+- Memory banks and their configuration
+- Documents and chunks
+- Entities and their relationships
+- Memory units (facts, experiences, opinions, observations)
+- Entity cooccurrences and memory links
+
+:::note Consistency
+Backups are created within a database transaction with `REPEATABLE READ` isolation, ensuring a consistent snapshot across all tables.
+:::
+
+---
+
+### restore
+
+Restore data from a backup file. **Warning: This deletes all existing data in the target schema.**
+
+```bash
+hindsight-admin restore INPUT [OPTIONS]
+```
+
+**Arguments:**
+
+| Argument | Description |
+|----------|-------------|
+| `INPUT` | Input backup file (.zip) |
+
+**Options:**
+
+| Option | Description | Default |
+|--------|-------------|---------|
+| `--schema`, `-s` | Database schema to restore to | `public` |
+| `--yes`, `-y` | Skip confirmation prompt | `false` |
+
+**Examples:**
+
+```bash
+# Restore with confirmation prompt
+hindsight-admin restore /backups/hindsight-2024-01-15.zip
+
+# Restore without confirmation (for scripts)
+hindsight-admin restore /backups/hindsight-2024-01-15.zip --yes
+
+# Restore to a specific tenant schema
+hindsight-admin restore /backups/tenant-acme.zip --schema tenant_acme --yes
+```
+
+:::warning Data Loss
+Restore will **delete all existing data** in the target schema before importing the backup. Always verify you have a recent backup before performing a restore.
+:::
+
+---
+
+## Environment Variables
+
+The admin CLI uses the same environment variables as the API service. The most important one is:
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `HINDSIGHT_API_DATABASE_URL` | PostgreSQL connection string | `pg0` (embedded) |
+
+**Example:**
+
+```bash
+# Use a specific database
+export HINDSIGHT_API_DATABASE_URL=postgresql://user:pass@localhost:5432/hindsight
+hindsight-admin backup /backups/mybackup.zip
+```
+

hindsight-docs/docs/developer/api/reflect.mdx

@@ -55,6 +55,20 @@ Make sure you've completed the [Quick Start](./quickstart) to install the client
 | `max_tokens` | int | 4096 | Maximum tokens for the response |
 | `response_schema` | object | None | JSON Schema for [structured output](#structured-output) |
 
+### Response Fields
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `text` | string | The generated answer text |
+| `based_on` | array | Facts used to generate the response |
+| `structured_output` | object | Parsed structured output (when `response_schema` provided) |
+| `usage` | TokenUsage | Token usage metrics for the LLM call |
+
+The `usage` field contains:
+- `input_tokens`: Number of input/prompt tokens consumed
+- `output_tokens`: Number of output/completion tokens generated
+- `total_tokens`: Sum of input and output tokens
+
 <Tabs>
 <TabItem value="python" label="Python">
 <CodeSnippet code={reflectPy} section="reflect-with-params" language="python" />

hindsight-docs/docs/developer/api/retain.mdx

@@ -66,6 +66,25 @@ Always provide context and event dates for optimal memory extraction:
 
 The `timestamp` defaults to the current time if not specified. Providing explicit timestamps enables temporal queries like "What happened last spring?"
 
+### Response Fields
+
+The retain response includes:
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `success` | bool | Whether the operation succeeded |
+| `bank_id` | string | The memory bank ID |
+| `items_count` | int | Number of items processed |
+| `async` | bool | Whether processed asynchronously |
+| `usage` | TokenUsage | Token usage metrics for LLM calls (synchronous only) |
+
+The `usage` field contains token metrics for cost tracking:
+- `input_tokens`: Tokens consumed by prompts
+- `output_tokens`: Tokens generated by the LLM
+- `total_tokens`: Sum of input and output tokens
+
+Note: `usage` is only present for synchronous operations. Async operations (`async: true`) do not return usage metrics.
+
 ## Batch Ingestion
 
 Store multiple items in a single request. **Batch ingestion is the recommended approach** as it significantly improves performance by reducing network overhead and allowing Hindsight to optimize the memory extraction process across related content.

hindsight-docs/docs/developer/configuration.md

@@ -20,9 +20,29 @@ The API service handles all memory operations (retain, recall, reflect).
 | Variable | Description | Default |
 |----------|-------------|---------|
 | `HINDSIGHT_API_DATABASE_URL` | PostgreSQL connection string | `pg0` (embedded) |
+| `HINDSIGHT_API_RUN_MIGRATIONS_ON_STARTUP` | Run database migrations on API startup | `true` |
 
 If not provided, the server uses embedded `pg0` — convenient for development but not recommended for production.
 
+### Database Connection Pool
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `HINDSIGHT_API_DB_POOL_MIN_SIZE` | Minimum connections in the pool | `5` |
+| `HINDSIGHT_API_DB_POOL_MAX_SIZE` | Maximum connections in the pool | `100` |
+| `HINDSIGHT_API_DB_COMMAND_TIMEOUT` | PostgreSQL command timeout in seconds | `60` |
+| `HINDSIGHT_API_DB_ACQUIRE_TIMEOUT` | Connection acquisition timeout in seconds | `30` |
+
+For high-concurrency workloads, increase `DB_POOL_MAX_SIZE`. Each concurrent recall/think operation can use 2-4 connections.
+
+To run migrations manually (e.g., before starting the API), use the admin CLI:
+
+```bash
+hindsight-admin run-db-migration
+# Or for a specific schema:
+hindsight-admin run-db-migration --schema tenant_acme
+```
+
 ### LLM Provider
 
 | Variable | Description | Default |
@@ -77,15 +97,55 @@ export HINDSIGHT_API_LLM_API_KEY=your-api-key
 export HINDSIGHT_API_LLM_MODEL=your-model-name
 ```
 
+### Per-Operation LLM Configuration
+
+Different memory operations have different requirements. **Retain** (fact extraction) benefits from models with strong structured output capabilities, while **Reflect** (reasoning/response generation) can use lighter, faster models. Configure separate LLM models for each operation to optimize for cost and performance.
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `HINDSIGHT_API_RETAIN_LLM_PROVIDER` | LLM provider for retain operations | Falls back to `HINDSIGHT_API_LLM_PROVIDER` |
+| `HINDSIGHT_API_RETAIN_LLM_API_KEY` | API key for retain LLM | Falls back to `HINDSIGHT_API_LLM_API_KEY` |
+| `HINDSIGHT_API_RETAIN_LLM_MODEL` | Model for retain operations | Falls back to `HINDSIGHT_API_LLM_MODEL` |
+| `HINDSIGHT_API_RETAIN_LLM_BASE_URL` | Base URL for retain LLM | Falls back to `HINDSIGHT_API_LLM_BASE_URL` |
+| `HINDSIGHT_API_REFLECT_LLM_PROVIDER` | LLM provider for reflect operations | Falls back to `HINDSIGHT_API_LLM_PROVIDER` |
+| `HINDSIGHT_API_REFLECT_LLM_API_KEY` | API key for reflect LLM | Falls back to `HINDSIGHT_API_LLM_API_KEY` |
+| `HINDSIGHT_API_REFLECT_LLM_MODEL` | Model for reflect operations | Falls back to `HINDSIGHT_API_LLM_MODEL` |
+| `HINDSIGHT_API_REFLECT_LLM_BASE_URL` | Base URL for reflect LLM | Falls back to `HINDSIGHT_API_LLM_BASE_URL` |
+
+:::tip When to Use Per-Operation Config
+- **Retain**: Use models with strong structured output (e.g., GPT-4o, Claude) for accurate fact extraction
+- **Reflect**: Use faster/cheaper models (e.g., GPT-4o-mini, Groq) for reasoning and response generation
+- **Recall**: Does not use LLM (pure retrieval), so no configuration needed
+:::
+
+**Example: Separate Models for Retain and Reflect**
+
+```bash
+# Default LLM (used as fallback)
+export HINDSIGHT_API_LLM_PROVIDER=openai
+export HINDSIGHT_API_LLM_API_KEY=sk-xxxxxxxxxxxx
+export HINDSIGHT_API_LLM_MODEL=gpt-4o
+
+# Use GPT-4o for retain (strong structured output)
+export HINDSIGHT_API_RETAIN_LLM_MODEL=gpt-4o
+
+# Use faster/cheaper model for reflect
+export HINDSIGHT_API_REFLECT_LLM_PROVIDER=groq
+export HINDSIGHT_API_REFLECT_LLM_API_KEY=gsk_xxxxxxxxxxxx
+export HINDSIGHT_API_REFLECT_LLM_MODEL=llama-3.3-70b-versatile
+```
+
 ### Embeddings
 
 | Variable | Description | Default |
 |----------|-------------|---------|
-| `HINDSIGHT_API_EMBEDDINGS_PROVIDER` | Provider: `local`, `tei`, or `openai` | `local` |
+| `HINDSIGHT_API_EMBEDDINGS_PROVIDER` | Provider: `local`, `tei`, `openai`, or `cohere` | `local` |
 | `HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL` | Model for local provider | `BAAI/bge-small-en-v1.5` |
 | `HINDSIGHT_API_EMBEDDINGS_TEI_URL` | TEI server URL | - |
 | `HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY` | OpenAI API key (falls back to `HINDSIGHT_API_LLM_API_KEY`) | - |
 | `HINDSIGHT_API_EMBEDDINGS_OPENAI_MODEL` | OpenAI embedding model | `text-embedding-3-small` |
+| `HINDSIGHT_API_COHERE_API_KEY` | Cohere API key (shared for embeddings and reranker) | - |
+| `HINDSIGHT_API_EMBEDDINGS_COHERE_MODEL` | Cohere embedding model | `embed-english-v3.0` |
 
 ```bash
 # Local (default) - uses SentenceTransformers
@@ -100,6 +160,11 @@ export HINDSIGHT_API_EMBEDDINGS_OPENAI_MODEL=text-embedding-3-small  # 1536 dime
 # TEI - HuggingFace Text Embeddings Inference (recommended for production)
 export HINDSIGHT_API_EMBEDDINGS_PROVIDER=tei
 export HINDSIGHT_API_EMBEDDINGS_TEI_URL=http://localhost:8080
+
+# Cohere - cloud-based embeddings
+export HINDSIGHT_API_EMBEDDINGS_PROVIDER=cohere
+export HINDSIGHT_API_COHERE_API_KEY=your-api-key
+export HINDSIGHT_API_EMBEDDINGS_COHERE_MODEL=embed-english-v3.0  # 1024 dimensions
 ```
 
 #### Embedding Dimensions
@@ -122,9 +187,10 @@ Supported OpenAI embedding dimensions:
 
 | Variable | Description | Default |
 |----------|-------------|---------|
-| `HINDSIGHT_API_RERANKER_PROVIDER` | Provider: `local` or `tei` | `local` |
+| `HINDSIGHT_API_RERANKER_PROVIDER` | Provider: `local`, `tei`, or `cohere` | `local` |
 | `HINDSIGHT_API_RERANKER_LOCAL_MODEL` | Model for local provider | `cross-encoder/ms-marco-MiniLM-L-6-v2` |
 | `HINDSIGHT_API_RERANKER_TEI_URL` | TEI server URL | - |
+| `HINDSIGHT_API_RERANKER_COHERE_MODEL` | Cohere rerank model | `rerank-english-v3.0` |
 
 ```bash
 # Local (default) - uses SentenceTransformers CrossEncoder
@@ -134,6 +200,11 @@ export HINDSIGHT_API_RERANKER_LOCAL_MODEL=cross-encoder/ms-marco-MiniLM-L-6-v2
 # TEI - for high-performance inference
 export HINDSIGHT_API_RERANKER_PROVIDER=tei
 export HINDSIGHT_API_RERANKER_TEI_URL=http://localhost:8081
+
+# Cohere - cloud-based reranking
+export HINDSIGHT_API_RERANKER_PROVIDER=cohere
+export HINDSIGHT_API_COHERE_API_KEY=your-api-key  # shared with embeddings
+export HINDSIGHT_API_RERANKER_COHERE_MODEL=rerank-english-v3.0
 ```
 
 ### Server
@@ -183,6 +254,15 @@ Controls when the system generates entity observations (summaries about entities
 | `HINDSIGHT_API_OBSERVATION_MIN_FACTS` | Minimum facts about an entity before generating observations | `5` |
 | `HINDSIGHT_API_OBSERVATION_TOP_ENTITIES` | Max entities to process per retain batch | `5` |
 
+### Retain
+
+Controls the retain (memory ingestion) pipeline.
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `HINDSIGHT_API_RETAIN_MAX_COMPLETION_TOKENS` | Max completion tokens for fact extraction LLM calls | `64000` |
+| `HINDSIGHT_API_RETAIN_CHUNK_SIZE` | Max characters per chunk for fact extraction. Larger chunks extract fewer LLM calls but may lose context. | `3000` |
+
 ### Local MCP Server
 
 Configuration for the local MCP server (`hindsight-local-mcp` command).
@@ -197,6 +277,15 @@ Configuration for the local MCP server (`hindsight-local-mcp` command).
 export HINDSIGHT_API_MCP_INSTRUCTIONS="Also store every action you take, including tool calls and decisions made."
 ```
 
+### Background Tasks
+
+Controls background task processing for async operations like opinion formation and entity observations.
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `HINDSIGHT_API_TASK_BATCH_SIZE` | Max tasks to process in one batch | `10` |
+| `HINDSIGHT_API_TASK_BATCH_INTERVAL` | Interval between batch processing in seconds | `1.0` |
+
 ### Performance Optimization
 
 | Variable | Description | Default |

hindsight-docs/docs/developer/metrics.md

@@ -12,17 +12,51 @@ curl http://localhost:8888/metrics
 
 | Metric | Type | Labels | Description |
 |--------|------|--------|-------------|
-| `hindsight.operation.duration` | Histogram | operation, bank_id, budget, max_tokens, success | Duration of operations in seconds |
-| `hindsight.operation.total` | Counter | operation, bank_id, budget, max_tokens, success | Total number of operations executed |
+| `hindsight.operation.duration` | Histogram | operation, bank_id, source, budget, max_tokens, success | Duration of operations in seconds |
+| `hindsight.operation.total` | Counter | operation, bank_id, source, budget, max_tokens, success | Total number of operations executed |
 
-The `operation` label values are: `retain`, `recall`, `reflect`.
+**Labels:**
+- `operation`: Operation type (`retain`, `recall`, `reflect`)
+- `bank_id`: Memory bank identifier
+- `source`: Where the operation was triggered from (`api`, `reflect`, `internal`)
+- `budget`: Budget level if specified (`low`, `mid`, `high`)
+- `max_tokens`: Max tokens if specified
+- `success`: Whether the operation succeeded (`true`, `false`)
 
-### Token Metrics
+The `source` label allows distinguishing between:
+- `api`: Direct API calls from clients
+- `reflect`: Internal recall calls made during reflect operations
+- `internal`: Other internal operations
+
+### LLM Metrics
 
 | Metric | Type | Labels | Description |
 |--------|------|--------|-------------|
-| `hindsight.tokens.input` | Counter | operation, bank_id, budget, max_tokens | Input tokens consumed |
-| `hindsight.tokens.output` | Counter | operation, bank_id, budget, max_tokens | Output tokens generated |
+| `hindsight.llm.duration` | Histogram | provider, model, scope, success | Duration of LLM API calls in seconds |
+| `hindsight.llm.calls.total` | Counter | provider, model, scope, success | Total number of LLM API calls |
+| `hindsight.llm.tokens.input` | Counter | provider, model, scope, success, token_bucket | Input tokens for LLM calls |
+| `hindsight.llm.tokens.output` | Counter | provider, model, scope, success, token_bucket | Output tokens from LLM calls |
+
+**Labels:**
+- `provider`: LLM provider (`openai`, `anthropic`, `gemini`, `groq`, `ollama`, `lmstudio`)
+- `model`: Model name (e.g., `gpt-4`, `claude-3-sonnet`)
+- `scope`: What the LLM call is for (`memory`, `reflect`, `entity_observation`, `answer`)
+- `success`: Whether the call succeeded (`true`, `false`)
+- `token_bucket`: Token count bucket for cardinality control (`0-100`, `100-500`, `500-1k`, `1k-5k`, `5k-10k`, `10k-50k`, `50k+`)
+
+### Histogram Buckets
+
+Custom bucket boundaries are configured for better percentile accuracy:
+
+**Operation Duration Buckets (seconds):**
+```
+0.1, 0.25, 0.5, 0.75, 1.0, 2.0, 3.0, 5.0, 7.5, 10.0, 15.0, 20.0, 30.0, 60.0, 120.0
+```
+
+**LLM Duration Buckets (seconds):**
+```
+0.1, 0.25, 0.5, 1.0, 2.0, 3.0, 5.0, 10.0, 15.0, 30.0, 60.0, 120.0
+```
 
 ## Prometheus Configuration
 
@@ -32,3 +66,30 @@ scrape_configs:
     static_configs:
       - targets: ['localhost:8888']
 ```
+
+## Example Queries
+
+### Average operation latency by type
+```promql
+rate(hindsight_operation_duration_sum[5m]) / rate(hindsight_operation_duration_count[5m])
+```
+
+### LLM calls per minute by provider
+```promql
+rate(hindsight_llm_calls_total[1m]) * 60
+```
+
+### P95 LLM latency
+```promql
+histogram_quantile(0.95, rate(hindsight_llm_duration_bucket[5m]))
+```
+
+### Total tokens consumed by model
+```promql
+sum by (model) (hindsight_llm_tokens_input_total + hindsight_llm_tokens_output_total)
+```
+
+### Internal vs API recall operations
+```promql
+sum by (source) (rate(hindsight_operation_total{operation="recall"}[5m]))
+```

hindsight-docs/docs/developer/multilingual.md

@@ -0,0 +1,217 @@
+---
+sidebar_position: 5
+---
+
+# Multilingual Support
+
+Hindsight automatically detects the language of your input and responds in the same language. This means facts, entities, and reflections are preserved in their original language without translation to English.
+
+## How It Works
+
+```mermaid
+graph LR
+    A[Chinese Input] --> B[Language Detection]
+    B --> C[Extract Facts in Chinese]
+    C --> D[Chinese Entities]
+    D --> E[Chinese Response]
+```
+
+When you retain content or reflect on a query, Hindsight:
+
+1. **Detects the input language** automatically from the content
+2. **Extracts facts in the original language** - preserving nuance and meaning
+3. **Stores entities in their native script** - 张伟 stays 张伟, not "Zhang Wei"
+4. **Responds in the same language** - queries in Chinese get Chinese answers
+
+---
+
+## Retain with Non-English Content
+
+When you retain content in any language, Hindsight extracts and stores facts in that same language.
+
+### Example: Chinese Content
+
+```python
+from hindsight import Hindsight
+
+hindsight = Hindsight()
+
+# Retain Chinese content
+hindsight.retain(
+    bank_id="user-123",
+    content="""
+    张伟是一位资深软件工程师，在腾讯工作了五年。
+    他专门研究分布式系统，并领导了公司微服务架构的开发。
+    """,
+    context="团队概述"
+)
+
+# Query in Chinese - get Chinese results
+results = hindsight.recall(
+    bank_id="user-123",
+    query="告诉我关于张伟的信息"
+)
+
+# Facts are returned in Chinese:
+# - 张伟是一位资深软件工程师，在腾讯工作了五年
+# - 张伟专门研究分布式系统，并领导了公司微服务架构的开发
+```
+
+### Example: Japanese Content
+
+```python
+hindsight.retain(
+    bank_id="user-123",
+    content="""
+    田中さんはソフトウェアエンジニアで、東京のスタートアップで働いています。
+    彼女はPythonとTypeScriptが得意で、毎日コードレビューをしています。
+    """,
+    context="チームプロフィール"
+)
+
+# Query in Japanese
+results = hindsight.recall(
+    bank_id="user-123",
+    query="田中さんについて教えてください"
+)
+```
+
+---
+
+## Reflect with Non-English Queries
+
+The `reflect` operation also respects the input language, generating thoughtful responses in the same language as the query.
+
+### Example: Chinese Reflection
+
+```python
+# Store facts about team members (in Chinese)
+hindsight.retain(
+    bank_id="team-eval",
+    content="张伟是一位优秀的软件工程师，完成了五个重大项目。他总是按时交付，代码整洁有良好的文档。",
+    context="绩效评估"
+)
+
+hindsight.retain(
+    bank_id="team-eval",
+    content="李明最近加入团队。他错过了第一个截止日期，代码有很多bug。",
+    context="绩效评估"
+)
+
+# Reflect in Chinese
+result = hindsight.reflect(
+    bank_id="team-eval",
+    query="谁是更可靠的工程师？"
+)
+
+# Response is in Chinese:
+# "我认为张伟更可靠。张伟完成了五个重大项目，按时交付，代码质量高..."
+```
+
+---
+
+## Mixed Language Content
+
+Hindsight handles mixed-language content gracefully, preserving both languages where appropriate.
+
+### Example: Chinese Text with English Company Names
+
+```python
+hindsight.retain(
+    bank_id="user-123",
+    content="""
+    王芳在Google北京办公室工作，她是一名高级产品经理。
+    之前她在Microsoft和Amazon工作过。
+    她负责管理YouTube在中国市场的推广策略。
+    """,
+    context="员工资料"
+)
+
+# Facts preserve both languages:
+# - 王芳在Google北京办公室工作，担任高级产品经理
+# - 王芳曾在Microsoft和Amazon工作过
+# - 王芳负责管理YouTube在中国市场的推广策略
+```
+
+---
+
+## Supported Languages
+
+**Hindsight's multilingual support depends entirely on your LLM's language capabilities.** Hindsight instructs the LLM to detect the input language and respond in that same language. If your LLM supports a language, Hindsight will work with it.
+
+Most modern LLMs (GPT-4, Claude, Gemini, Llama 3, etc.) support dozens of languages including:
+
+- **East Asian**: Chinese (Simplified/Traditional), Japanese, Korean
+- **European**: Spanish, French, German, Italian, Portuguese, Dutch, Polish, Russian
+- **Middle Eastern**: Arabic, Hebrew, Turkish
+- **South Asian**: Hindi, Bengali, Tamil
+- **Southeast Asian**: Thai, Vietnamese, Indonesian
+
+**To verify support for your target language**, test your LLM directly with content in that language. If the LLM can understand and generate text in the language, Hindsight will preserve it correctly.
+
+---
+
+## Configuring for Multilingual Use
+
+For optimal multilingual performance, you should configure all three components of the pipeline:
+
+### 1. LLM (Required)
+Your LLM must support the target languages. Most modern LLMs do, but verify with your specific model.
+
+### 2. Embedding Model (Recommended)
+The default embedding model (`BAAI/bge-small-en-v1.5`) is **English-only**. For multilingual content, use a multilingual embedding model:
+
+```bash
+# In your .env file
+HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL=BAAI/bge-m3
+```
+
+**Recommended multilingual embedding models:**
+| Model | Languages | Notes |
+|-------|-----------|-------|
+| `BAAI/bge-m3` | 100+ | Best overall multilingual performance |
+| `intfloat/multilingual-e5-large` | 100+ | Good alternative |
+| `sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2` | 50+ | Lighter weight |
+
+### 3. Reranker Model (Recommended)
+The default reranker (`cross-encoder/ms-marco-MiniLM-L-6-v2`) is **English-only**. For multilingual content, use a multilingual reranker:
+
+```bash
+# In your .env file
+HINDSIGHT_API_RERANKER_LOCAL_MODEL=BAAI/bge-reranker-v2-m3
+```
+
+**Recommended multilingual reranker models:**
+| Model | Languages | Notes |
+|-------|-----------|-------|
+| `BAAI/bge-reranker-v2-m3` | 100+ | Best multilingual reranking |
+| `cross-encoder/mmarco-mMiniLMv2-L12-H384-v1` | 14 | Lighter alternative |
+
+---
+
+## Best Practices
+
+### 1. Use Multilingual Models for Non-English Content
+If you primarily work with non-English content, configure multilingual embedding and reranker models. English-only models will still store your content correctly, but semantic search quality will be degraded.
+
+### 2. Keep Content in One Language Per Retain Call
+While mixed content works, keeping each `retain` call in a single language produces more consistent results.
+
+### 3. Query in the Same Language as Your Content
+For best results, query using the same language as your stored content. Cross-language queries (e.g., English query for Chinese content) may work but results can vary depending on your embedding model.
+
+---
+
+## Technical Details
+
+Multilingual support is implemented through LLM prompt instructions rather than external language detection libraries. This approach:
+
+- **Requires no additional dependencies**
+- **Works with any LLM** that supports multiple languages
+- **Handles edge cases** like mixed-language content naturally
+- **Preserves semantic meaning** better than rule-based translation
+
+The LLM is instructed to:
+1. Detect the input language
+2. Extract all facts, entities, and descriptions in that same language
+3. Never translate to English unless the input is in English

hindsight-docs/sidebars.ts

@@ -27,6 +27,11 @@ const sidebars: SidebarsConfig = {
           id: 'developer/reflect',
           label: 'Reflect',
         },
+        {
+          type: 'doc',
+          id: 'developer/multilingual',
+          label: 'Multilingual',
+        },
         {
           type: 'doc',
           id: 'developer/performance',
@@ -111,6 +116,11 @@ const sidebars: SidebarsConfig = {
           id: 'developer/configuration',
           label: 'Configuration',
         },
+        {
+          type: 'doc',
+          id: 'developer/admin-cli',
+          label: 'Admin CLI',
+        },
         {
           type: 'doc',
           id: 'developer/extensions',

hindsight-docs/static/openapi.json

@@ -59,7 +59,7 @@
           "Memory"
         ],
         "summary": "Get memory graph data",
-        "description": "Retrieve graph data for visualization, optionally filtered by type (world/experience/opinion). Limited to 1000 most recent items.",
+        "description": "Retrieve graph data for visualization, optionally filtered by type (world/experience/opinion).",
         "operationId": "get_graph",
         "parameters": [
           {
@@ -87,6 +87,16 @@
               "title": "Type"
             }
           },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 1000,
+              "title": "Limit"
+            }
+          },
           {
             "name": "authorization",
             "in": "header",
@@ -2504,6 +2514,10 @@
           "total_units": {
             "type": "integer",
             "title": "Total Units"
+          },
+          "limit": {
+            "type": "integer",
+            "title": "Limit"
           }
         },
         "type": "object",
@@ -2511,7 +2525,8 @@
           "nodes",
           "edges",
           "table_rows",
-          "total_units"
+          "total_units",
+          "limit"
         ],
         "title": "GraphDataResponse",
         "description": "Response model for graph data endpoint.",
@@ -2524,6 +2539,7 @@
               "weight": 0.8
             }
           ],
+          "limit": 1000,
           "nodes": [
             {
               "id": "1",
@@ -3404,6 +3420,17 @@
             ],
             "title": "Structured Output",
             "description": "Structured output parsed according to the request's response_schema. Only present when response_schema was provided in the request."
+          },
+          "usage": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TokenUsage"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Token usage metrics for LLM calls during reflection."
           }
         },
         "type": "object",
@@ -3432,7 +3459,12 @@
             ],
             "summary": "AI is transformative"
           },
-          "text": "Based on my understanding, AI is a transformative technology..."
+          "text": "Based on my understanding, AI is a transformative technology...",
+          "usage": {
+            "input_tokens": 1500,
+            "output_tokens": 500,
+            "total_tokens": 2000
+          }
         }
       },
       "RetainRequest": {
@@ -3491,6 +3523,17 @@
             "type": "boolean",
             "title": "Async",
             "description": "Whether the operation was processed asynchronously"
+          },
+          "usage": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TokenUsage"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Token usage metrics for LLM calls during fact extraction (only present for synchronous operations)"
           }
         },
         "type": "object",
@@ -3506,7 +3549,42 @@
           "async": false,
           "bank_id": "user123",
           "items_count": 2,
-          "success": true
+          "success": true,
+          "usage": {
+            "input_tokens": 500,
+            "output_tokens": 100,
+            "total_tokens": 600
+          }
+        }
+      },
+      "TokenUsage": {
+        "properties": {
+          "input_tokens": {
+            "type": "integer",
+            "title": "Input Tokens",
+            "description": "Number of input/prompt tokens consumed",
+            "default": 0
+          },
+          "output_tokens": {
+            "type": "integer",
+            "title": "Output Tokens",
+            "description": "Number of output/completion tokens generated",
+            "default": 0
+          },
+          "total_tokens": {
+            "type": "integer",
+            "title": "Total Tokens",
+            "description": "Total tokens (input + output)",
+            "default": 0
+          }
+        },
+        "type": "object",
+        "title": "TokenUsage",
+        "description": "Token usage metrics for LLM calls.\n\nTracks input/output tokens for a single request to enable\nper-request cost tracking and monitoring.",
+        "example": {
+          "input_tokens": 1500,
+          "output_tokens": 500,
+          "total_tokens": 2000
         }
       },
       "UpdateDispositionRequest": {

package.json

@@ -8,5 +8,8 @@
   ],
   "scripts": {
     "prepare": "./scripts/setup-hooks.sh"
+  },
+  "overrides": {
+    "qs": "^6.14.1"
   }
 }

scripts/generate-clients.sh

@@ -51,16 +51,16 @@ echo "=================================================="
 
 RUST_CLIENT_DIR="$CLIENTS_DIR/rust"
 
-# Clean old generated files
+# Clean old generated files (keep Cargo.lock for reproducible builds)
 echo "Cleaning old Rust generated code..."
 rm -rf "$RUST_CLIENT_DIR/target"
-rm -f "$RUST_CLIENT_DIR/Cargo.lock"
 
 # Trigger regeneration by building
+# Use --locked to ensure reproducible builds from committed Cargo.lock
 echo "Regenerating Rust client (via build.rs)..."
 cd "$RUST_CLIENT_DIR"
 cargo clean
-cargo build --release
+cargo build --release --locked
 
 echo "✓ Rust client generated at $RUST_CLIENT_DIR"
 echo ""
@@ -324,9 +324,11 @@ rm -rf "$TYPESCRIPT_CLIENT_DIR/services"
 rm -f "$TYPESCRIPT_CLIENT_DIR/index.ts"
 
 # Generate new client using @hey-api/openapi-ts
+# Use npm run generate to use the locally installed version (pinned in package.json)
+# instead of npx --yes which would fetch the latest version
 echo "Generating from $OPENAPI_SPEC..."
 cd "$TYPESCRIPT_CLIENT_DIR"
-npx --yes @hey-api/openapi-ts
+npm run generate
 
 echo "✓ TypeScript client generated at $TYPESCRIPT_CLIENT_DIR"
 echo ""

uv.lock

@@ -593,6 +593,25 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/db/d3/9dcc0f5797f070ec8edf30fbadfb200e71d9db6b84d211e3b2085a7589a0/click-8.3.0-py3-none-any.whl", hash = "sha256:9b9f285302c6e3064f4330c05f05b81945b2a39544279343e6e7c5f27a9baddc", size = 107295 },
 ]
 
+[[package]]
+name = "cohere"
+version = "5.20.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "fastavro" },
+    { name = "httpx" },
+    { name = "pydantic" },
+    { name = "pydantic-core" },
+    { name = "requests" },
+    { name = "tokenizers" },
+    { name = "types-requests" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/4b/ed/bb02083654bdc089ae4ef1cd7691fd2233f1fd9f32bcbfacc80ff57d9775/cohere-5.20.1.tar.gz", hash = "sha256:50973f63d2c6138ff52ce37d8d6f78ccc539af4e8c43865e960d68e0bf835b6f", size = 180820 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7a/e3/94eb11ac3ebaaa3a6afb5d2ff23db95d58bc468ae538c388edf49f2f20b5/cohere-5.20.1-py3-none-any.whl", hash = "sha256:d230fd13d95ba92ae927fce3dd497599b169883afc7954fe29b39fb8d5df5fc7", size = 318973 },
+]
+
 [[package]]
 name = "colorama"
 version = "0.4.6"
@@ -836,6 +855,47 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/68/79/7f5a5e5513e6a737e5fb089d9c59c74d4d24dc24d581d3aa519b326bedda/fastapi_cloud_cli-0.3.1-py3-none-any.whl", hash = "sha256:7d1a98a77791a9d0757886b2ffbf11bcc6b3be93210dd15064be10b216bf7e00", size = 19711 },
 ]
 
+[[package]]
+name = "fastavro"
+version = "1.12.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/65/8b/fa2d3287fd2267be6261d0177c6809a7fa12c5600ddb33490c8dc29e77b2/fastavro-1.12.1.tar.gz", hash = "sha256:2f285be49e45bc047ab2f6bed040bb349da85db3f3c87880e4b92595ea093b2b", size = 1025661 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a0/e9/31c64b47cefc0951099e7c0c8c8ea1c931edd1350f34d55c27cbfbb08df1/fastavro-1.12.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:6b632b713bc5d03928a87d811fa4a11d5f25cd43e79c161e291c7d3f7aa740fd", size = 1016585 },
+    { url = "https://files.pythonhosted.org/packages/10/76/111560775b548f5d8d828c1b5285ff90e2d2745643fb80ecbf115344eea4/fastavro-1.12.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:eaa7ab3769beadcebb60f0539054c7755f63bd9cf7666e2c15e615ab605f89a8", size = 3404629 },
+    { url = "https://files.pythonhosted.org/packages/b0/07/6bb93cb963932146c2b6c5c765903a0a547ad9f0f8b769a4a9aad8c06369/fastavro-1.12.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:123fb221df3164abd93f2d042c82f538a1d5a43ce41375f12c91ce1355a9141e", size = 3428594 },
+    { url = "https://files.pythonhosted.org/packages/d1/67/8115ec36b584197ea737ec79e3499e1f1b640b288d6c6ee295edd13b80f6/fastavro-1.12.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:632a4e3ff223f834ddb746baae0cc7cee1068eb12c32e4d982c2fee8a5b483d0", size = 3344145 },
+    { url = "https://files.pythonhosted.org/packages/9e/9e/a7cebb3af967e62539539897c10138fa0821668ec92525d1be88a9cd3ee6/fastavro-1.12.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:83e6caf4e7a8717d932a3b1ff31595ad169289bbe1128a216be070d3a8391671", size = 3431942 },
+    { url = "https://files.pythonhosted.org/packages/c0/d1/7774ddfb8781c5224294c01a593ebce2ad3289b948061c9701bd1903264d/fastavro-1.12.1-cp311-cp311-win_amd64.whl", hash = "sha256:b91a0fe5a173679a6c02d53ca22dcaad0a2c726b74507e0c1c2e71a7c3f79ef9", size = 450542 },
+    { url = "https://files.pythonhosted.org/packages/7c/f0/10bd1a3d08667fa0739e2b451fe90e06df575ec8b8ba5d3135c70555c9bd/fastavro-1.12.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:509818cb24b98a804fc80be9c5fed90f660310ae3d59382fc811bfa187122167", size = 1009057 },
+    { url = "https://files.pythonhosted.org/packages/78/ad/0d985bc99e1fa9e74c636658000ba38a5cd7f5ab2708e9c62eaf736ecf1a/fastavro-1.12.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:089e155c0c76e0d418d7e79144ce000524dd345eab3bc1e9c5ae69d500f71b14", size = 3391866 },
+    { url = "https://files.pythonhosted.org/packages/0d/9e/b4951dc84ebc34aac69afcbfbb22ea4a91080422ec2bfd2c06076ff1d419/fastavro-1.12.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:44cbff7518901c91a82aab476fcab13d102e4999499df219d481b9e15f61af34", size = 3458005 },
+    { url = "https://files.pythonhosted.org/packages/af/f8/5a8df450a9f55ca8441f22ea0351d8c77809fc121498b6970daaaf667a21/fastavro-1.12.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:a275e48df0b1701bb764b18a8a21900b24cf882263cb03d35ecdba636bbc830b", size = 3295258 },
+    { url = "https://files.pythonhosted.org/packages/99/b2/40f25299111d737e58b85696e91138a66c25b7334f5357e7ac2b0e8966f8/fastavro-1.12.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:2de72d786eb38be6b16d556b27232b1bf1b2797ea09599507938cdb7a9fe3e7c", size = 3430328 },
+    { url = "https://files.pythonhosted.org/packages/e0/07/85157a7c57c5f8b95507d7829b5946561e5ee656ff80e9dd9a757f53ddaf/fastavro-1.12.1-cp312-cp312-win_amd64.whl", hash = "sha256:9090f0dee63fe022ee9cc5147483366cc4171c821644c22da020d6b48f576b4f", size = 444140 },
+    { url = "https://files.pythonhosted.org/packages/bb/57/26d5efef9182392d5ac9f253953c856ccb66e4c549fd3176a1e94efb05c9/fastavro-1.12.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:78df838351e4dff9edd10a1c41d1324131ffecbadefb9c297d612ef5363c049a", size = 1000599 },
+    { url = "https://files.pythonhosted.org/packages/33/cb/8ab55b21d018178eb126007a56bde14fd01c0afc11d20b5f2624fe01e698/fastavro-1.12.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:780476c23175d2ae457c52f45b9ffa9d504593499a36cd3c1929662bf5b7b14b", size = 3335933 },
+    { url = "https://files.pythonhosted.org/packages/fe/03/9c94ec9bf873eb1ffb0aa694f4e71940154e6e9728ddfdc46046d7e8ced4/fastavro-1.12.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0714b285160fcd515eb0455540f40dd6dac93bdeacdb03f24e8eac3d8aa51f8d", size = 3402066 },
+    { url = "https://files.pythonhosted.org/packages/75/c8/cb472347c5a584ccb8777a649ebb28278fccea39d005fc7df19996f41df8/fastavro-1.12.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:a8bc2dcec5843d499f2489bfe0747999108f78c5b29295d877379f1972a3d41a", size = 3240038 },
+    { url = "https://files.pythonhosted.org/packages/e1/77/569ce9474c40304b3a09e109494e020462b83e405545b78069ddba5f614e/fastavro-1.12.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:3b1921ac35f3d89090a5816b626cf46e67dbecf3f054131f84d56b4e70496f45", size = 3369398 },
+    { url = "https://files.pythonhosted.org/packages/4a/1f/9589e35e9ea68035385db7bdbf500d36b8891db474063fb1ccc8215ee37c/fastavro-1.12.1-cp313-cp313-win_amd64.whl", hash = "sha256:5aa777b8ee595b50aa084104cd70670bf25a7bbb9fd8bb5d07524b0785ee1699", size = 444220 },
+    { url = "https://files.pythonhosted.org/packages/6c/d2/78435fe737df94bd8db2234b2100f5453737cffd29adee2504a2b013de84/fastavro-1.12.1-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:c3d67c47f177e486640404a56f2f50b165fe892cc343ac3a34673b80cc7f1dd6", size = 1086611 },
+    { url = "https://files.pythonhosted.org/packages/b6/be/428f99b10157230ddac77ec8cc167005b29e2bd5cbe228345192bb645f30/fastavro-1.12.1-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5217f773492bac43dae15ff2931432bce2d7a80be7039685a78d3fab7df910bd", size = 3541001 },
+    { url = "https://files.pythonhosted.org/packages/16/08/a2eea4f20b85897740efe44887e1ac08f30dfa4bfc3de8962bdcbb21a5a1/fastavro-1.12.1-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:469fecb25cba07f2e1bfa4c8d008477cd6b5b34a59d48715e1b1a73f6160097d", size = 3432217 },
+    { url = "https://files.pythonhosted.org/packages/87/bb/b4c620b9eb6e9838c7f7e4b7be0762834443adf9daeb252a214e9ad3178c/fastavro-1.12.1-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:d71c8aa841ef65cfab709a22bb887955f42934bced3ddb571e98fdbdade4c609", size = 3366742 },
+    { url = "https://files.pythonhosted.org/packages/3d/d1/e69534ccdd5368350646fea7d93be39e5f77c614cca825c990bd9ca58f67/fastavro-1.12.1-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:b81fc04e85dfccf7c028e0580c606e33aa8472370b767ef058aae2c674a90746", size = 3383743 },
+    { url = "https://files.pythonhosted.org/packages/58/54/b7b4a0c3fb5fcba38128542da1b26c4e6d69933c923f493548bdfd63ab6a/fastavro-1.12.1-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:9445da127751ba65975d8e4bdabf36bfcfdad70fc35b2d988e3950cce0ec0e7c", size = 1001377 },
+    { url = "https://files.pythonhosted.org/packages/1e/4f/0e589089c7df0d8f57d7e5293fdc34efec9a3b758a0d4d0c99a7937e2492/fastavro-1.12.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ed924233272719b5d5a6a0b4d80ef3345fc7e84fc7a382b6232192a9112d38a6", size = 3320401 },
+    { url = "https://files.pythonhosted.org/packages/f9/19/260110d56194ae29d7e423a336fccea8bcd103196d00f0b364b732bdb84e/fastavro-1.12.1-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3616e2f0e1c9265e92954fa099db79c6e7817356d3ff34f4bcc92699ae99697c", size = 3350894 },
+    { url = "https://files.pythonhosted.org/packages/d0/96/58b0411e8be9694d5972bee3167d6c1fd1fdfdf7ce253c1a19a327208f4f/fastavro-1.12.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:cb0337b42fd3c047fcf0e9b7597bd6ad25868de719f29da81eabb6343f08d399", size = 3229644 },
+    { url = "https://files.pythonhosted.org/packages/5b/db/38660660eac82c30471d9101f45b3acfdcbadfe42d8f7cdb129459a45050/fastavro-1.12.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:64961ab15b74b7c168717bbece5660e0f3d457837c3cc9d9145181d011199fa7", size = 3329704 },
+    { url = "https://files.pythonhosted.org/packages/9d/a9/1672910f458ecb30b596c9e59e41b7c00309b602a0494341451e92e62747/fastavro-1.12.1-cp314-cp314-win_amd64.whl", hash = "sha256:792356d320f6e757e89f7ac9c22f481e546c886454a6709247f43c0dd7058004", size = 452911 },
+    { url = "https://files.pythonhosted.org/packages/dc/8d/2e15d0938ded1891b33eff252e8500605508b799c2e57188a933f0bd744c/fastavro-1.12.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:120aaf82ac19d60a1016afe410935fe94728752d9c2d684e267e5b7f0e70f6d9", size = 3541999 },
+    { url = "https://files.pythonhosted.org/packages/a7/1c/6dfd082a205be4510543221b734b1191299e6a1810c452b6bc76dfa6968e/fastavro-1.12.1-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b6a3462934b20a74f9ece1daa49c2e4e749bd9a35fa2657b53bf62898fba80f5", size = 3433972 },
+    { url = "https://files.pythonhosted.org/packages/24/90/9de694625a1a4b727b1ad0958d220cab25a9b6cf7f16a5c7faa9ea7b2261/fastavro-1.12.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:1f81011d54dd47b12437b51dd93a70a9aa17b61307abf26542fc3c13efbc6c51", size = 3368752 },
+    { url = "https://files.pythonhosted.org/packages/fa/93/b44f67589e4d439913dab6720f7e3507b0fa8b8e56d06f6fc875ced26afb/fastavro-1.12.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:43ded16b3f4a9f1a42f5970c2aa618acb23ea59c4fcaa06680bdf470b255e5a8", size = 3386636 },
+]
+
 [[package]]
 name = "fastcore"
 version = "1.8.16"
@@ -1191,6 +1251,7 @@ dependencies = [
     { name = "alembic" },
     { name = "anthropic" },
     { name = "asyncpg" },
+    { name = "cohere" },
     { name = "dateparser" },
     { name = "fastapi", extra = ["standard"] },
     { name = "fastmcp" },
@@ -1215,6 +1276,7 @@ dependencies = [
     { name = "tiktoken" },
     { name = "torch" },
     { name = "transformers" },
+    { name = "typer" },
     { name = "uvicorn" },
     { name = "wsproto" },
 ]
@@ -1245,6 +1307,7 @@ requires-dist = [
     { name = "alembic", specifier = ">=1.17.1" },
     { name = "anthropic", specifier = ">=0.40.0" },
     { name = "asyncpg", specifier = ">=0.29.0" },
+    { name = "cohere", specifier = ">=5.0.0" },
     { name = "dateparser", specifier = ">=1.2.2" },
     { name = "fastapi", extras = ["standard"], specifier = ">=0.120.3" },
     { name = "fastmcp", specifier = ">=2.3.0" },
@@ -1274,6 +1337,7 @@ requires-dist = [
     { name = "tiktoken", specifier = ">=0.12.0" },
     { name = "torch", specifier = ">=2.0.0" },
     { name = "transformers", specifier = ">=4.30.0,<4.46.0" },
+    { name = "typer", specifier = ">=0.9.0" },
     { name = "uvicorn", specifier = ">=0.38.0" },
     { name = "wsproto", specifier = ">=1.0.0" },
 ]
@@ -4365,6 +4429,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/78/64/7713ffe4b5983314e9d436a90d5bd4f63b6054e2aca783a3cfc44cb95bbf/typer-0.20.0-py3-none-any.whl", hash = "sha256:5b463df6793ec1dca6213a3cf4c0f03bc6e322ac5e16e13ddd622a889489784a", size = 47028 },
 ]
 
+[[package]]
+name = "types-requests"
+version = "2.32.4.20260107"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/0f/f3/a0663907082280664d745929205a89d41dffb29e89a50f753af7d57d0a96/types_requests-2.32.4.20260107.tar.gz", hash = "sha256:018a11ac158f801bfa84857ddec1650750e393df8a004a8a9ae2a9bec6fcb24f", size = 23165 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1c/12/709ea261f2bf91ef0a26a9eed20f2623227a8ed85610c1e54c5805692ecb/types_requests-2.32.4.20260107-py3-none-any.whl", hash = "sha256:b703fe72f8ce5b31ef031264fe9395cac8f46a04661a79f7ed31a80fb308730d", size = 20676 },
+]
+
 [[package]]
 name = "typing-extensions"
 version = "4.15.0"