* feat: introduce hindsight-api-slim and hindsight-all-slim packages Closes #552 - Move all source code from hindsight-api/ to new hindsight-api-slim/ - hindsight-api-slim has heavy ML deps (torch, sentence-transformers, transformers, einops, flashrank, mlx, mlx-lm, safetensors) and pg0-embedded as optional extras: [local-ml], [embedded-db], [all] - hindsight-api becomes a zero-code meta-package depending on hindsight-api-slim[all] for full backward compatibility - Add hindsight-all-slim meta-package: hindsight-api-slim + client + embed - hindsight-all updated to depend on hindsight-api-slim[all] - pg0.py: lazy-import pg0 with clear ImportError pointing to [embedded-db] - Dockerfile: replace sed hack with proper uv sync --extra flags - Update release.yml, test.yml, lint.sh, release.sh, CLAUDE.md and all path references throughout the repo * refactor: rename hindsight/ directory to hindsight-all/ * docs: document hindsight-api-slim and hindsight-all-slim package variants Add package variants table and extras explanation to installation.md * docs: remove emojis from installation.md, use professional tone * docs: link Docker slim variant to pip package variants section * docs: consolidate Docker image variants into single table * ci: fix working-directory paths after package restructure - Replace all hindsight-api → hindsight-api-slim in test.yml - Replace hindsight → hindsight-all in test.yml - Add --extra embedded-db to test-embed API install step * ci: add local-ml and embedded-db extras to API sync steps These extras were previously implicit in the old hindsight-api package (which bundled everything). Now that hindsight-api-slim uses optional extras, we must explicitly request local-ml and embedded-db in CI. * ci: add API install step with embedded-db to test-embed smoke test The smoke test starts hindsight-api as a daemon, which requires pg0-embedded. Add a dedicated install step for hindsight-api-slim with embedded-db extra so the daemon can start successfully. * ci: remove --no-install-project when using optional extras When --no-install-project is combined with --extra, the optional deps are not installed because extras require the project to be active. Remove --no-install-project from steps that need local-ml or embedded-db. * ci: fix ordering of uv sync steps to preserve optional extras When uv sync runs for a different workspace member, it removes optional extras installed for other members. Fix by always running extra-requiring API sync last, after other workspace member syncs. Also remove --no-install-project from embedded-db sync in test-embed, as --no-install-project prevents optional extras from being active. * ci: add local-ml extra to test-embed API install for smoke test The smoke test starts the full API server which needs sentence-transformers for local embeddings (default provider). Add local-ml extra to the install. * ci: simplify extras with --all-extras and add slim pip smoke test - Replace explicit --extra local-ml --extra embedded-db with --all-extras for cleaner, more maintainable sync steps - Add test-pip-slim job: tests hindsight-api-slim[embedded-db] without local ML models, using Cohere for embeddings/reranking (mirrors Docker slim smoke test approach) * ci: simplify slim smoke test to health check only (mirrors Docker test)
136 lines
4.4 KiB
Python
136 lines
4.4 KiB
Python
"""
|
|
Unified API module for Hindsight.
|
|
|
|
Provides both HTTP REST API and MCP (Model Context Protocol) server.
|
|
"""
|
|
|
|
import logging
|
|
from contextlib import asynccontextmanager
|
|
|
|
from fastapi import FastAPI
|
|
|
|
from hindsight_api import MemoryEngine
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def create_app(
|
|
memory: MemoryEngine,
|
|
http_api_enabled: bool = True,
|
|
mcp_api_enabled: bool = False,
|
|
mcp_mount_path: str = "/mcp",
|
|
initialize_memory: bool = True,
|
|
) -> FastAPI:
|
|
"""
|
|
Create and configure the unified Hindsight API application.
|
|
|
|
Args:
|
|
memory: MemoryEngine instance (already initialized with required parameters).
|
|
Migrations are controlled by the MemoryEngine's run_migrations parameter.
|
|
http_api_enabled: Whether to enable HTTP REST API endpoints (default: True)
|
|
mcp_api_enabled: Whether to enable MCP server (default: False)
|
|
mcp_mount_path: Path to mount MCP server (default: /mcp)
|
|
initialize_memory: Whether to initialize memory system on startup (default: True)
|
|
|
|
Returns:
|
|
Configured FastAPI application with enabled APIs
|
|
|
|
Example:
|
|
# HTTP only
|
|
app = create_app(memory)
|
|
|
|
# MCP only
|
|
app = create_app(memory, http_api_enabled=False, mcp_api_enabled=True)
|
|
|
|
# Both HTTP and MCP
|
|
app = create_app(memory, mcp_api_enabled=True)
|
|
"""
|
|
mcp_servers = None
|
|
|
|
# Create MCP servers first if enabled (we need their lifespans for chaining)
|
|
if mcp_api_enabled:
|
|
try:
|
|
from .mcp import MCPMiddleware, create_mcp_servers
|
|
|
|
mcp_servers = create_mcp_servers(memory=memory)
|
|
except ImportError as e:
|
|
logger.error(f"MCP server requested but dependencies not available: {e}")
|
|
logger.error("Install with: pip install hindsight-api[mcp]")
|
|
raise
|
|
|
|
# Import and create HTTP API if enabled
|
|
if http_api_enabled:
|
|
from .http import create_app as create_http_app
|
|
|
|
app = create_http_app(memory=memory, initialize_memory=initialize_memory)
|
|
logger.info("HTTP REST API enabled")
|
|
else:
|
|
# Create minimal FastAPI app
|
|
app = FastAPI(title="Hindsight API", version="0.0.7")
|
|
logger.info("HTTP REST API disabled")
|
|
|
|
# Add MCP middleware and chain its lifespan if enabled
|
|
if mcp_servers is not None:
|
|
multi_bank_server, single_bank_server, multi_bank_starlette_app, single_bank_starlette_app = mcp_servers
|
|
|
|
# Store the original lifespan
|
|
original_lifespan = app.router.lifespan_context
|
|
|
|
@asynccontextmanager
|
|
async def chained_lifespan(app_instance: FastAPI):
|
|
"""Chain both MCP lifespans with the main app lifespan."""
|
|
# Start both MCP lifespans (multi-bank and single-bank)
|
|
async with multi_bank_starlette_app.router.lifespan_context(multi_bank_starlette_app):
|
|
async with single_bank_starlette_app.router.lifespan_context(single_bank_starlette_app):
|
|
logger.info("MCP lifespans started (multi-bank and single-bank)")
|
|
# Then start the original app lifespan
|
|
async with original_lifespan(app_instance):
|
|
yield
|
|
logger.info("MCP lifespans stopped")
|
|
|
|
# Replace the app's lifespan with the chained version
|
|
app.router.lifespan_context = chained_lifespan
|
|
|
|
# Add MCP as a wrapping middleware — intercepts /mcp* requests directly,
|
|
# passes everything else through to the FastAPI app. No Starlette Mount
|
|
# means no 307 redirect for /mcp (no trailing slash).
|
|
app.add_middleware(
|
|
MCPMiddleware,
|
|
memory=memory,
|
|
prefix=mcp_mount_path,
|
|
multi_bank_app=multi_bank_starlette_app,
|
|
single_bank_app=single_bank_starlette_app,
|
|
multi_bank_server=multi_bank_server,
|
|
single_bank_server=single_bank_server,
|
|
)
|
|
|
|
logger.info(f"MCP server enabled at {mcp_mount_path}/")
|
|
|
|
return app
|
|
|
|
|
|
# Re-export commonly used items for backwards compatibility
|
|
from .http import (
|
|
CreateBankRequest,
|
|
DispositionTraits,
|
|
MemoryItem,
|
|
RecallRequest,
|
|
RecallResponse,
|
|
RecallResult,
|
|
ReflectRequest,
|
|
ReflectResponse,
|
|
RetainRequest,
|
|
)
|
|
|
|
__all__ = [
|
|
"create_app",
|
|
"RecallRequest",
|
|
"RecallResult",
|
|
"RecallResponse",
|
|
"MemoryItem",
|
|
"RetainRequest",
|
|
"ReflectRequest",
|
|
"ReflectResponse",
|
|
"CreateBankRequest",
|
|
"DispositionTraits",
|
|
]
|