feat: add Pydantic AI integration for persistent agent memory (#441)
* feat: add Pydantic AI integration for persistent agent memory Adds hindsight-pydantic-ai package providing Hindsight-backed memory tools for Pydantic AI agents. Since Pydantic AI is async-native, tools use the hindsight-client async API directly (no thread-pool compat layer). - create_hindsight_tools(): factory returning retain/recall/reflect Tool instances - memory_instructions(): auto-injects relevant memories via Agent instructions - Global configure()/get_config()/reset_config() following existing integration pattern Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * doc: add README for Pydantic AI integration Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
parent
ab70da1ead
commit
cab5a40f3a
10 changed files with 2432 additions and 0 deletions
191
hindsight-integrations/pydantic-ai/README.md
Normal file
191
hindsight-integrations/pydantic-ai/README.md
Normal file
|
|
@ -0,0 +1,191 @@
|
|||
# hindsight-pydantic-ai
|
||||
|
||||
Persistent memory tools for Pydantic AI agents via Hindsight. Give your agents long-term memory with retain, recall, and reflect — all async-native with no thread-pool hacks.
|
||||
|
||||
## Features
|
||||
|
||||
- **Async-Native Tools** - Uses Pydantic AI's async tool interface directly (`aretain`, `arecall`, `areflect`)
|
||||
- **Memory Instructions** - Auto-inject relevant memories into every agent run via `instructions=[...]`
|
||||
- **Three Memory Tools** - Retain (store), Recall (search), Reflect (synthesize) — include any combination
|
||||
- **Simple Configuration** - Configure once globally, or pass a client directly
|
||||
- **Lightweight** - Depends on `pydantic-ai-slim` to avoid pulling in all model providers
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
pip install hindsight-pydantic-ai
|
||||
```
|
||||
|
||||
## Quick Start
|
||||
|
||||
```python
|
||||
from hindsight_client import Hindsight
|
||||
from hindsight_pydantic_ai import create_hindsight_tools, memory_instructions
|
||||
from pydantic_ai import Agent
|
||||
|
||||
client = Hindsight(base_url="http://localhost:8888")
|
||||
|
||||
agent = Agent(
|
||||
"openai:gpt-4o",
|
||||
tools=create_hindsight_tools(client=client, bank_id="user-123"),
|
||||
instructions=[memory_instructions(client=client, bank_id="user-123")],
|
||||
)
|
||||
|
||||
result = await agent.run("What do you remember about my preferences?")
|
||||
print(result.output)
|
||||
```
|
||||
|
||||
The agent now has three tools it can call:
|
||||
|
||||
- **`hindsight_retain`** — Store information to long-term memory
|
||||
- **`hindsight_recall`** — Search long-term memory for relevant facts
|
||||
- **`hindsight_reflect`** — Synthesize a reasoned answer from memories
|
||||
|
||||
The `memory_instructions` callable automatically recalls relevant memories and injects them into the system prompt on every run.
|
||||
|
||||
## Tools Only (No Auto-Injection)
|
||||
|
||||
If you want the agent to decide when to use memory (rather than always injecting context):
|
||||
|
||||
```python
|
||||
agent = Agent(
|
||||
"openai:gpt-4o",
|
||||
tools=create_hindsight_tools(client=client, bank_id="user-123"),
|
||||
)
|
||||
```
|
||||
|
||||
## Instructions Only (No Tools)
|
||||
|
||||
If you just want memories auto-injected without giving the agent explicit memory tools:
|
||||
|
||||
```python
|
||||
agent = Agent(
|
||||
"openai:gpt-4o",
|
||||
instructions=[memory_instructions(client=client, bank_id="user-123")],
|
||||
)
|
||||
```
|
||||
|
||||
## Selecting Tools
|
||||
|
||||
Include only the tools you need:
|
||||
|
||||
```python
|
||||
tools = create_hindsight_tools(
|
||||
client=client,
|
||||
bank_id="user-123",
|
||||
include_retain=True,
|
||||
include_recall=True,
|
||||
include_reflect=False, # Omit reflect
|
||||
)
|
||||
```
|
||||
|
||||
## Global Configuration
|
||||
|
||||
Instead of passing a client to every call, configure once:
|
||||
|
||||
```python
|
||||
from hindsight_pydantic_ai import configure, create_hindsight_tools
|
||||
|
||||
configure(
|
||||
hindsight_api_url="http://localhost:8888",
|
||||
api_key="your-api-key", # Or set HINDSIGHT_API_KEY env var
|
||||
budget="mid", # Recall budget: low/mid/high
|
||||
max_tokens=4096, # Max tokens for recall results
|
||||
tags=["env:prod"], # Tags for stored memories
|
||||
recall_tags=["scope:global"], # Tags to filter recall
|
||||
recall_tags_match="any", # Tag match mode: any/all/any_strict/all_strict
|
||||
)
|
||||
|
||||
# Now create tools without passing client — uses global config
|
||||
tools = create_hindsight_tools(bank_id="user-123")
|
||||
```
|
||||
|
||||
## Per-Tool Overrides
|
||||
|
||||
Constructor arguments override global configuration:
|
||||
|
||||
```python
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="user-123",
|
||||
budget="high", # Override global budget
|
||||
max_tokens=8192, # Override global max_tokens
|
||||
tags=["session:abc"], # Override global tags
|
||||
)
|
||||
```
|
||||
|
||||
## Memory Instructions Options
|
||||
|
||||
Customize what memories get injected and how:
|
||||
|
||||
```python
|
||||
instructions_fn = memory_instructions(
|
||||
client=client,
|
||||
bank_id="user-123",
|
||||
query="relevant context about the user", # What to search for
|
||||
budget="low", # Keep it fast
|
||||
max_results=5, # Limit injected memories
|
||||
max_tokens=4096, # Max recall tokens
|
||||
prefix="Relevant memories:\n", # Text before the memory list
|
||||
tags=["scope:global"], # Filter by tags
|
||||
tags_match="any", # Tag match mode
|
||||
)
|
||||
```
|
||||
|
||||
## Configuration Reference
|
||||
|
||||
### `create_hindsight_tools()`
|
||||
|
||||
| Parameter | Default | Description |
|
||||
|---|---|---|
|
||||
| `bank_id` | *required* | Hindsight memory bank ID |
|
||||
| `client` | `None` | Pre-configured Hindsight client |
|
||||
| `hindsight_api_url` | `None` | API URL (used if no client provided) |
|
||||
| `api_key` | `None` | API key (used if no client provided) |
|
||||
| `budget` | `"mid"` | Recall/reflect budget level (low/mid/high) |
|
||||
| `max_tokens` | `4096` | Maximum tokens for recall results |
|
||||
| `tags` | `None` | Tags applied when storing memories |
|
||||
| `recall_tags` | `None` | Tags to filter when searching |
|
||||
| `recall_tags_match` | `"any"` | Tag matching mode |
|
||||
| `include_retain` | `True` | Include the retain (store) tool |
|
||||
| `include_recall` | `True` | Include the recall (search) tool |
|
||||
| `include_reflect` | `True` | Include the reflect (synthesize) tool |
|
||||
|
||||
### `memory_instructions()`
|
||||
|
||||
| Parameter | Default | Description |
|
||||
|---|---|---|
|
||||
| `bank_id` | *required* | Hindsight memory bank ID |
|
||||
| `client` | `None` | Pre-configured Hindsight client |
|
||||
| `hindsight_api_url` | `None` | API URL (used if no client provided) |
|
||||
| `api_key` | `None` | API key (used if no client provided) |
|
||||
| `query` | `"relevant context about the user"` | Recall query for memory injection |
|
||||
| `budget` | `"low"` | Recall budget level |
|
||||
| `max_results` | `5` | Maximum memories to inject |
|
||||
| `max_tokens` | `4096` | Maximum tokens for recall results |
|
||||
| `prefix` | `"Relevant memories:\n"` | Text prepended before memory list |
|
||||
| `tags` | `None` | Tags to filter recall results |
|
||||
| `tags_match` | `"any"` | Tag matching mode |
|
||||
|
||||
### `configure()`
|
||||
|
||||
| Parameter | Default | Description |
|
||||
|---|---|---|
|
||||
| `hindsight_api_url` | Production API | Hindsight API URL |
|
||||
| `api_key` | `HINDSIGHT_API_KEY` env | API key for authentication |
|
||||
| `budget` | `"mid"` | Default recall budget level |
|
||||
| `max_tokens` | `4096` | Default max tokens for recall |
|
||||
| `tags` | `None` | Default tags for retain operations |
|
||||
| `recall_tags` | `None` | Default tags to filter recall |
|
||||
| `recall_tags_match` | `"any"` | Default tag matching mode |
|
||||
| `verbose` | `False` | Enable verbose logging |
|
||||
|
||||
## Requirements
|
||||
|
||||
- Python >= 3.10
|
||||
- pydantic-ai-slim >= 1.0.0
|
||||
- hindsight-client >= 0.4.0
|
||||
- A running Hindsight API server
|
||||
|
||||
## License
|
||||
|
||||
MIT
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
"""Hindsight-Pydantic AI: Persistent memory tools for AI agents.
|
||||
|
||||
Provides Hindsight-backed tools and instructions for Pydantic AI agents,
|
||||
giving them long-term memory across runs.
|
||||
|
||||
Basic usage::
|
||||
|
||||
from hindsight_client import Hindsight
|
||||
from hindsight_pydantic_ai import create_hindsight_tools, memory_instructions
|
||||
from pydantic_ai import Agent
|
||||
|
||||
client = Hindsight(base_url="http://localhost:8888")
|
||||
|
||||
agent = Agent(
|
||||
"openai:gpt-4o",
|
||||
tools=create_hindsight_tools(client=client, bank_id="user-123"),
|
||||
instructions=[memory_instructions(client=client, bank_id="user-123")],
|
||||
)
|
||||
|
||||
result = await agent.run("What do you remember about my preferences?")
|
||||
"""
|
||||
|
||||
from .config import (
|
||||
HindsightPydanticAIConfig,
|
||||
configure,
|
||||
get_config,
|
||||
reset_config,
|
||||
)
|
||||
from .errors import HindsightError
|
||||
from .tools import create_hindsight_tools, memory_instructions
|
||||
|
||||
__version__ = "0.1.0"
|
||||
|
||||
__all__ = [
|
||||
"configure",
|
||||
"get_config",
|
||||
"reset_config",
|
||||
"HindsightPydanticAIConfig",
|
||||
"HindsightError",
|
||||
"create_hindsight_tools",
|
||||
"memory_instructions",
|
||||
]
|
||||
|
|
@ -0,0 +1,92 @@
|
|||
"""Global configuration for Hindsight-Pydantic AI integration."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from dataclasses import dataclass
|
||||
|
||||
DEFAULT_HINDSIGHT_API_URL = "https://api.hindsight.vectorize.io"
|
||||
HINDSIGHT_API_KEY_ENV = "HINDSIGHT_API_KEY"
|
||||
|
||||
|
||||
@dataclass
|
||||
class HindsightPydanticAIConfig:
|
||||
"""Connection and default settings for the Pydantic AI integration.
|
||||
|
||||
Attributes:
|
||||
hindsight_api_url: URL of the Hindsight API server.
|
||||
api_key: API key for Hindsight authentication.
|
||||
budget: Default recall budget level (low/mid/high).
|
||||
max_tokens: Default maximum tokens for recall results.
|
||||
tags: Default tags applied when storing memories.
|
||||
recall_tags: Default tags to filter when searching memories.
|
||||
recall_tags_match: Tag matching mode (any/all/any_strict/all_strict).
|
||||
verbose: Enable verbose logging.
|
||||
"""
|
||||
|
||||
hindsight_api_url: str = DEFAULT_HINDSIGHT_API_URL
|
||||
api_key: str | None = None
|
||||
budget: str = "mid"
|
||||
max_tokens: int = 4096
|
||||
tags: list[str] | None = None
|
||||
recall_tags: list[str] | None = None
|
||||
recall_tags_match: str = "any"
|
||||
verbose: bool = False
|
||||
|
||||
|
||||
_global_config: HindsightPydanticAIConfig | None = None
|
||||
|
||||
|
||||
def configure(
|
||||
hindsight_api_url: str | None = None,
|
||||
api_key: str | None = None,
|
||||
budget: str = "mid",
|
||||
max_tokens: int = 4096,
|
||||
tags: list[str] | None = None,
|
||||
recall_tags: list[str] | None = None,
|
||||
recall_tags_match: str = "any",
|
||||
verbose: bool = False,
|
||||
) -> HindsightPydanticAIConfig:
|
||||
"""Configure Hindsight connection and default settings.
|
||||
|
||||
Args:
|
||||
hindsight_api_url: Hindsight API URL (default: production).
|
||||
api_key: API key. Falls back to HINDSIGHT_API_KEY env var.
|
||||
budget: Default recall budget (low/mid/high).
|
||||
max_tokens: Default max tokens for recall.
|
||||
tags: Default tags for retain operations.
|
||||
recall_tags: Default tags to filter recall/search.
|
||||
recall_tags_match: Tag matching mode.
|
||||
verbose: Enable verbose logging.
|
||||
|
||||
Returns:
|
||||
The configured HindsightPydanticAIConfig.
|
||||
"""
|
||||
global _global_config
|
||||
|
||||
resolved_url = hindsight_api_url or DEFAULT_HINDSIGHT_API_URL
|
||||
resolved_key = api_key or os.environ.get(HINDSIGHT_API_KEY_ENV)
|
||||
|
||||
_global_config = HindsightPydanticAIConfig(
|
||||
hindsight_api_url=resolved_url,
|
||||
api_key=resolved_key,
|
||||
budget=budget,
|
||||
max_tokens=max_tokens,
|
||||
tags=tags,
|
||||
recall_tags=recall_tags,
|
||||
recall_tags_match=recall_tags_match,
|
||||
verbose=verbose,
|
||||
)
|
||||
|
||||
return _global_config
|
||||
|
||||
|
||||
def get_config() -> HindsightPydanticAIConfig | None:
|
||||
"""Get the current global configuration."""
|
||||
return _global_config
|
||||
|
||||
|
||||
def reset_config() -> None:
|
||||
"""Reset global configuration to None."""
|
||||
global _global_config
|
||||
_global_config = None
|
||||
|
|
@ -0,0 +1,7 @@
|
|||
"""Hindsight-Pydantic AI error types."""
|
||||
|
||||
|
||||
class HindsightError(Exception):
|
||||
"""Exception raised when a Hindsight memory operation fails."""
|
||||
|
||||
pass
|
||||
|
|
@ -0,0 +1,243 @@
|
|||
"""Pydantic AI tools for Hindsight memory operations.
|
||||
|
||||
Provides factory functions that create Pydantic AI ``Tool`` instances
|
||||
backed by Hindsight's retain/recall/reflect APIs.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from collections.abc import Awaitable, Callable
|
||||
from typing import Any
|
||||
|
||||
from hindsight_client import Hindsight
|
||||
from pydantic_ai import RunContext, Tool
|
||||
|
||||
from .config import get_config
|
||||
from .errors import HindsightError
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _resolve_client(
|
||||
client: Hindsight | None,
|
||||
hindsight_api_url: str | None,
|
||||
api_key: str | None,
|
||||
) -> Hindsight:
|
||||
"""Resolve a Hindsight client from explicit args or global config."""
|
||||
if client is not None:
|
||||
return client
|
||||
|
||||
config = get_config()
|
||||
url = hindsight_api_url or (config.hindsight_api_url if config else None)
|
||||
key = api_key or (config.api_key if config else None)
|
||||
|
||||
if url is None:
|
||||
raise HindsightError(
|
||||
"No Hindsight API URL configured. "
|
||||
"Pass client= or hindsight_api_url=, or call configure() first."
|
||||
)
|
||||
|
||||
kwargs: dict[str, Any] = {"base_url": url, "timeout": 30.0}
|
||||
if key:
|
||||
kwargs["api_key"] = key
|
||||
return Hindsight(**kwargs)
|
||||
|
||||
|
||||
def create_hindsight_tools(
|
||||
*,
|
||||
bank_id: str,
|
||||
client: Hindsight | None = None,
|
||||
hindsight_api_url: str | None = None,
|
||||
api_key: str | None = None,
|
||||
budget: str = "mid",
|
||||
max_tokens: int = 4096,
|
||||
tags: list[str] | None = None,
|
||||
recall_tags: list[str] | None = None,
|
||||
recall_tags_match: str = "any",
|
||||
include_retain: bool = True,
|
||||
include_recall: bool = True,
|
||||
include_reflect: bool = True,
|
||||
) -> list[Tool]:
|
||||
"""Create Hindsight memory tools for a Pydantic AI agent.
|
||||
|
||||
Returns a list of ``Tool`` instances that can be passed directly to
|
||||
``Agent(tools=...)``. Each tool is an async closure that captures
|
||||
the Hindsight client — no ``RunContext`` or deps modification needed.
|
||||
|
||||
Args:
|
||||
bank_id: The Hindsight memory bank to operate on.
|
||||
client: Pre-configured Hindsight client (preferred).
|
||||
hindsight_api_url: API URL (used if no client provided).
|
||||
api_key: API key (used if no client provided).
|
||||
budget: Recall/reflect budget level (low/mid/high).
|
||||
max_tokens: Maximum tokens for recall results.
|
||||
tags: Tags applied when storing memories via retain.
|
||||
recall_tags: Tags to filter when searching memories.
|
||||
recall_tags_match: Tag matching mode (any/all/any_strict/all_strict).
|
||||
include_retain: Include the retain (store) tool.
|
||||
include_recall: Include the recall (search) tool.
|
||||
include_reflect: Include the reflect (synthesize) tool.
|
||||
|
||||
Returns:
|
||||
List of Pydantic AI Tool instances.
|
||||
|
||||
Raises:
|
||||
HindsightError: If no client or API URL can be resolved.
|
||||
"""
|
||||
resolved_client = _resolve_client(client, hindsight_api_url, api_key)
|
||||
|
||||
# Resolve defaults from global config
|
||||
config = get_config()
|
||||
effective_tags = tags if tags is not None else (config.tags if config else None)
|
||||
effective_recall_tags = (
|
||||
recall_tags if recall_tags is not None else (config.recall_tags if config else None)
|
||||
)
|
||||
effective_recall_tags_match = recall_tags_match or (config.recall_tags_match if config else "any")
|
||||
effective_budget = budget or (config.budget if config else "mid")
|
||||
effective_max_tokens = max_tokens or (config.max_tokens if config else 4096)
|
||||
|
||||
tools: list[Tool] = []
|
||||
|
||||
if include_retain:
|
||||
|
||||
async def hindsight_retain(content: str) -> str:
|
||||
"""Store information to long-term memory for later retrieval.
|
||||
|
||||
Use this to save important facts, user preferences, decisions,
|
||||
or any information that should be remembered across conversations.
|
||||
"""
|
||||
try:
|
||||
retain_kwargs: dict[str, Any] = {"bank_id": bank_id, "content": content}
|
||||
if effective_tags:
|
||||
retain_kwargs["tags"] = effective_tags
|
||||
await resolved_client.aretain(**retain_kwargs)
|
||||
return "Memory stored successfully."
|
||||
except Exception as e:
|
||||
logger.error(f"Retain failed: {e}")
|
||||
raise HindsightError(f"Retain failed: {e}") from e
|
||||
|
||||
tools.append(Tool(hindsight_retain, takes_ctx=False))
|
||||
|
||||
if include_recall:
|
||||
|
||||
async def hindsight_recall(query: str) -> str:
|
||||
"""Search long-term memory for relevant information.
|
||||
|
||||
Use this to find previously stored facts, preferences, or context.
|
||||
Returns a numbered list of matching memories.
|
||||
"""
|
||||
try:
|
||||
recall_kwargs: dict[str, Any] = {
|
||||
"bank_id": bank_id,
|
||||
"query": query,
|
||||
"budget": effective_budget,
|
||||
"max_tokens": effective_max_tokens,
|
||||
}
|
||||
if effective_recall_tags:
|
||||
recall_kwargs["tags"] = effective_recall_tags
|
||||
recall_kwargs["tags_match"] = effective_recall_tags_match
|
||||
response = await resolved_client.arecall(**recall_kwargs)
|
||||
if not response.results:
|
||||
return "No relevant memories found."
|
||||
lines = []
|
||||
for i, result in enumerate(response.results, 1):
|
||||
lines.append(f"{i}. {result.text}")
|
||||
return "\n".join(lines)
|
||||
except Exception as e:
|
||||
logger.error(f"Recall failed: {e}")
|
||||
raise HindsightError(f"Recall failed: {e}") from e
|
||||
|
||||
tools.append(Tool(hindsight_recall, takes_ctx=False))
|
||||
|
||||
if include_reflect:
|
||||
|
||||
async def hindsight_reflect(query: str) -> str:
|
||||
"""Synthesize a thoughtful answer from long-term memories.
|
||||
|
||||
Use this when you need a coherent summary or reasoned response
|
||||
about what you know, rather than raw memory facts.
|
||||
"""
|
||||
try:
|
||||
reflect_kwargs: dict[str, Any] = {
|
||||
"bank_id": bank_id,
|
||||
"query": query,
|
||||
"budget": effective_budget,
|
||||
}
|
||||
response = await resolved_client.areflect(**reflect_kwargs)
|
||||
return response.text or "No relevant memories found."
|
||||
except Exception as e:
|
||||
logger.error(f"Reflect failed: {e}")
|
||||
raise HindsightError(f"Reflect failed: {e}") from e
|
||||
|
||||
tools.append(Tool(hindsight_reflect, takes_ctx=False))
|
||||
|
||||
return tools
|
||||
|
||||
|
||||
def memory_instructions(
|
||||
*,
|
||||
bank_id: str,
|
||||
client: Hindsight | None = None,
|
||||
hindsight_api_url: str | None = None,
|
||||
api_key: str | None = None,
|
||||
query: str = "relevant context about the user",
|
||||
budget: str = "low",
|
||||
max_results: int = 5,
|
||||
max_tokens: int = 4096,
|
||||
prefix: str = "Relevant memories:\n",
|
||||
tags: list[str] | None = None,
|
||||
tags_match: str = "any",
|
||||
) -> Callable[[RunContext[Any]], Awaitable[str]]:
|
||||
"""Create an instructions function that auto-injects relevant memories.
|
||||
|
||||
Returns an async callable suitable for use with Pydantic AI's
|
||||
``instructions`` parameter. Because instructions are re-evaluated
|
||||
on every run, memories stay fresh even when ``message_history``
|
||||
is reused.
|
||||
|
||||
Args:
|
||||
bank_id: The Hindsight memory bank to recall from.
|
||||
client: Pre-configured Hindsight client (preferred).
|
||||
hindsight_api_url: API URL (used if no client provided).
|
||||
api_key: API key (used if no client provided).
|
||||
query: The recall query to find relevant memories.
|
||||
budget: Recall budget level (low/mid/high).
|
||||
max_results: Maximum number of memories to include.
|
||||
max_tokens: Maximum tokens for recall results.
|
||||
prefix: Text prepended before the memory list.
|
||||
tags: Tags to filter recall results.
|
||||
tags_match: Tag matching mode (any/all/any_strict/all_strict).
|
||||
|
||||
Returns:
|
||||
An async function compatible with ``Agent(instructions=[...])``.
|
||||
|
||||
Raises:
|
||||
HindsightError: If no client or API URL can be resolved.
|
||||
"""
|
||||
resolved_client = _resolve_client(client, hindsight_api_url, api_key)
|
||||
|
||||
async def _instructions(ctx: RunContext[Any]) -> str:
|
||||
try:
|
||||
recall_kwargs: dict[str, Any] = {
|
||||
"bank_id": bank_id,
|
||||
"query": query,
|
||||
"budget": budget,
|
||||
"max_tokens": max_tokens,
|
||||
}
|
||||
if tags:
|
||||
recall_kwargs["tags"] = tags
|
||||
recall_kwargs["tags_match"] = tags_match
|
||||
response = await resolved_client.arecall(**recall_kwargs)
|
||||
results = response.results[:max_results] if response.results else []
|
||||
if not results:
|
||||
return ""
|
||||
lines = [prefix]
|
||||
for i, result in enumerate(results, 1):
|
||||
lines.append(f"{i}. {result.text}")
|
||||
return "\n".join(lines)
|
||||
except Exception:
|
||||
# Silently return empty — instructions failures shouldn't block the agent
|
||||
return ""
|
||||
|
||||
return _instructions
|
||||
60
hindsight-integrations/pydantic-ai/pyproject.toml
Normal file
60
hindsight-integrations/pydantic-ai/pyproject.toml
Normal file
|
|
@ -0,0 +1,60 @@
|
|||
[project]
|
||||
name = "hindsight-pydantic-ai"
|
||||
version = "0.1.0"
|
||||
description = "Pydantic AI integration for Hindsight - persistent memory tools for AI agents"
|
||||
requires-python = ">=3.10"
|
||||
license = { text = "MIT" }
|
||||
authors = [
|
||||
{ name = "Vectorize", email = "support@vectorize.io" }
|
||||
]
|
||||
keywords = [
|
||||
"ai",
|
||||
"memory",
|
||||
"pydantic-ai",
|
||||
"agents",
|
||||
"hindsight",
|
||||
]
|
||||
classifiers = [
|
||||
"Development Status :: 4 - Beta",
|
||||
"Intended Audience :: Developers",
|
||||
"License :: OSI Approved :: MIT License",
|
||||
"Programming Language :: Python :: 3",
|
||||
"Programming Language :: Python :: 3.10",
|
||||
"Programming Language :: Python :: 3.11",
|
||||
"Programming Language :: Python :: 3.12",
|
||||
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
||||
]
|
||||
|
||||
dependencies = [
|
||||
"pydantic-ai-slim>=1.0.0",
|
||||
"hindsight-client>=0.4.0",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
dev = [
|
||||
"pytest>=7.0.0",
|
||||
"pytest-mock>=3.10.0",
|
||||
"pytest-asyncio>=0.23.0",
|
||||
]
|
||||
|
||||
[project.urls]
|
||||
Homepage = "https://github.com/vectorize-io/hindsight"
|
||||
Documentation = "https://github.com/vectorize-io/hindsight/tree/main/hindsight-integrations/pydantic-ai"
|
||||
Repository = "https://github.com/vectorize-io/hindsight"
|
||||
|
||||
[build-system]
|
||||
requires = ["hatchling"]
|
||||
build-backend = "hatchling.build"
|
||||
|
||||
[tool.hatch.build.targets.wheel]
|
||||
packages = ["hindsight_pydantic_ai"]
|
||||
|
||||
[tool.pytest.ini_options]
|
||||
testpaths = ["tests"]
|
||||
asyncio_mode = "auto"
|
||||
|
||||
[dependency-groups]
|
||||
dev = [
|
||||
"pytest>=9.0.2",
|
||||
"pytest-asyncio>=0.23.0",
|
||||
]
|
||||
0
hindsight-integrations/pydantic-ai/tests/__init__.py
Normal file
0
hindsight-integrations/pydantic-ai/tests/__init__.py
Normal file
76
hindsight-integrations/pydantic-ai/tests/test_config.py
Normal file
76
hindsight-integrations/pydantic-ai/tests/test_config.py
Normal file
|
|
@ -0,0 +1,76 @@
|
|||
"""Unit tests for hindsight_pydantic_ai configuration."""
|
||||
|
||||
import os
|
||||
from unittest.mock import patch
|
||||
|
||||
from hindsight_pydantic_ai import configure, get_config, reset_config
|
||||
from hindsight_pydantic_ai.config import (
|
||||
DEFAULT_HINDSIGHT_API_URL,
|
||||
HINDSIGHT_API_KEY_ENV,
|
||||
)
|
||||
|
||||
|
||||
class TestDefaults:
|
||||
def test_default_api_url(self):
|
||||
assert DEFAULT_HINDSIGHT_API_URL == "https://api.hindsight.vectorize.io"
|
||||
|
||||
def test_env_var_name(self):
|
||||
assert HINDSIGHT_API_KEY_ENV == "HINDSIGHT_API_KEY"
|
||||
|
||||
|
||||
class TestConfigure:
|
||||
def setup_method(self):
|
||||
reset_config()
|
||||
|
||||
def teardown_method(self):
|
||||
reset_config()
|
||||
|
||||
def test_configure_with_no_arguments(self):
|
||||
config = configure()
|
||||
assert config.hindsight_api_url == DEFAULT_HINDSIGHT_API_URL
|
||||
assert config.budget == "mid"
|
||||
assert config.max_tokens == 4096
|
||||
assert config.verbose is False
|
||||
|
||||
def test_configure_reads_api_key_from_env(self):
|
||||
with patch.dict(os.environ, {HINDSIGHT_API_KEY_ENV: "test-key"}):
|
||||
config = configure()
|
||||
assert config.api_key == "test-key"
|
||||
|
||||
def test_configure_explicit_overrides_env(self):
|
||||
with patch.dict(os.environ, {HINDSIGHT_API_KEY_ENV: "env-key"}):
|
||||
config = configure(api_key="explicit-key")
|
||||
assert config.api_key == "explicit-key"
|
||||
|
||||
def test_configure_all_options(self):
|
||||
config = configure(
|
||||
hindsight_api_url="http://custom:8888",
|
||||
api_key="my-key",
|
||||
budget="high",
|
||||
max_tokens=2048,
|
||||
tags=["env:test"],
|
||||
recall_tags=["scope:global"],
|
||||
recall_tags_match="all",
|
||||
verbose=True,
|
||||
)
|
||||
assert config.hindsight_api_url == "http://custom:8888"
|
||||
assert config.api_key == "my-key"
|
||||
assert config.budget == "high"
|
||||
assert config.max_tokens == 2048
|
||||
assert config.tags == ["env:test"]
|
||||
assert config.recall_tags == ["scope:global"]
|
||||
assert config.recall_tags_match == "all"
|
||||
assert config.verbose is True
|
||||
|
||||
def test_get_config_returns_none_without_configure(self):
|
||||
assert get_config() is None
|
||||
|
||||
def test_get_config_returns_config_after_configure(self):
|
||||
configure()
|
||||
assert get_config() is not None
|
||||
|
||||
def test_reset_config(self):
|
||||
configure()
|
||||
assert get_config() is not None
|
||||
reset_config()
|
||||
assert get_config() is None
|
||||
468
hindsight-integrations/pydantic-ai/tests/test_tools.py
Normal file
468
hindsight-integrations/pydantic-ai/tests/test_tools.py
Normal file
|
|
@ -0,0 +1,468 @@
|
|||
"""Unit tests for Hindsight Pydantic AI tools."""
|
||||
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
from hindsight_pydantic_ai import (
|
||||
configure,
|
||||
create_hindsight_tools,
|
||||
memory_instructions,
|
||||
reset_config,
|
||||
)
|
||||
from hindsight_pydantic_ai.errors import HindsightError
|
||||
|
||||
|
||||
def _mock_client():
|
||||
"""Create a mock Hindsight client with async methods."""
|
||||
client = MagicMock()
|
||||
client.aretain = AsyncMock()
|
||||
client.arecall = AsyncMock()
|
||||
client.areflect = AsyncMock()
|
||||
return client
|
||||
|
||||
|
||||
def _mock_recall_result(text: str):
|
||||
"""Create a mock RecallResult."""
|
||||
result = MagicMock()
|
||||
result.text = text
|
||||
return result
|
||||
|
||||
|
||||
def _mock_recall_response(texts: list[str]):
|
||||
"""Create a mock RecallResponse with results."""
|
||||
response = MagicMock()
|
||||
response.results = [_mock_recall_result(t) for t in texts]
|
||||
return response
|
||||
|
||||
|
||||
def _mock_reflect_response(text: str):
|
||||
"""Create a mock ReflectResponse."""
|
||||
response = MagicMock()
|
||||
response.text = text
|
||||
return response
|
||||
|
||||
|
||||
def _mock_retain_response():
|
||||
"""Create a mock RetainResponse."""
|
||||
response = MagicMock()
|
||||
response.success = True
|
||||
return response
|
||||
|
||||
|
||||
class TestCreateHindsightTools:
|
||||
def setup_method(self):
|
||||
reset_config()
|
||||
|
||||
def teardown_method(self):
|
||||
reset_config()
|
||||
|
||||
def test_returns_three_tools_by_default(self):
|
||||
client = _mock_client()
|
||||
tools = create_hindsight_tools(bank_id="test", client=client)
|
||||
assert len(tools) == 3
|
||||
|
||||
def test_include_retain_only(self):
|
||||
client = _mock_client()
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
include_retain=True,
|
||||
include_recall=False,
|
||||
include_reflect=False,
|
||||
)
|
||||
assert len(tools) == 1
|
||||
assert tools[0].name == "hindsight_retain"
|
||||
|
||||
def test_include_recall_only(self):
|
||||
client = _mock_client()
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
include_retain=False,
|
||||
include_recall=True,
|
||||
include_reflect=False,
|
||||
)
|
||||
assert len(tools) == 1
|
||||
assert tools[0].name == "hindsight_recall"
|
||||
|
||||
def test_include_reflect_only(self):
|
||||
client = _mock_client()
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
include_retain=False,
|
||||
include_recall=False,
|
||||
include_reflect=True,
|
||||
)
|
||||
assert len(tools) == 1
|
||||
assert tools[0].name == "hindsight_reflect"
|
||||
|
||||
def test_no_tools_when_all_excluded(self):
|
||||
client = _mock_client()
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
include_retain=False,
|
||||
include_recall=False,
|
||||
include_reflect=False,
|
||||
)
|
||||
assert len(tools) == 0
|
||||
|
||||
def test_raises_without_client_or_config(self):
|
||||
with pytest.raises(HindsightError, match="No Hindsight API URL"):
|
||||
create_hindsight_tools(bank_id="test")
|
||||
|
||||
def test_falls_back_to_global_config(self):
|
||||
configure(hindsight_api_url="http://localhost:8888")
|
||||
with patch("hindsight_pydantic_ai.tools.Hindsight") as mock_cls:
|
||||
mock_cls.return_value = _mock_client()
|
||||
tools = create_hindsight_tools(bank_id="test")
|
||||
assert len(tools) == 3
|
||||
mock_cls.assert_called_once_with(
|
||||
base_url="http://localhost:8888", timeout=30.0
|
||||
)
|
||||
|
||||
def test_explicit_url_overrides_config(self):
|
||||
configure(hindsight_api_url="http://config:8888")
|
||||
with patch("hindsight_pydantic_ai.tools.Hindsight") as mock_cls:
|
||||
mock_cls.return_value = _mock_client()
|
||||
create_hindsight_tools(
|
||||
bank_id="test", hindsight_api_url="http://explicit:9999"
|
||||
)
|
||||
mock_cls.assert_called_once_with(
|
||||
base_url="http://explicit:9999", timeout=30.0
|
||||
)
|
||||
|
||||
|
||||
class TestRetainTool:
|
||||
@pytest.mark.asyncio
|
||||
async def test_retain_stores_memory(self):
|
||||
client = _mock_client()
|
||||
client.aretain.return_value = _mock_retain_response()
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test-bank",
|
||||
client=client,
|
||||
include_recall=False,
|
||||
include_reflect=False,
|
||||
)
|
||||
tool_fn = tools[0].function
|
||||
|
||||
result = await tool_fn("The user likes Python")
|
||||
|
||||
assert result == "Memory stored successfully."
|
||||
client.aretain.assert_called_once_with(bank_id="test-bank", content="The user likes Python")
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_retain_passes_tags(self):
|
||||
client = _mock_client()
|
||||
client.aretain.return_value = _mock_retain_response()
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test-bank",
|
||||
client=client,
|
||||
tags=["source:chat"],
|
||||
include_recall=False,
|
||||
include_reflect=False,
|
||||
)
|
||||
tool_fn = tools[0].function
|
||||
|
||||
await tool_fn("some content")
|
||||
|
||||
call_kwargs = client.aretain.call_args[1]
|
||||
assert call_kwargs["tags"] == ["source:chat"]
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_retain_raises_hindsight_error(self):
|
||||
client = _mock_client()
|
||||
client.aretain.side_effect = RuntimeError("connection refused")
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
include_recall=False,
|
||||
include_reflect=False,
|
||||
)
|
||||
tool_fn = tools[0].function
|
||||
|
||||
with pytest.raises(HindsightError, match="Retain failed"):
|
||||
await tool_fn("content")
|
||||
|
||||
|
||||
class TestRecallTool:
|
||||
@pytest.mark.asyncio
|
||||
async def test_recall_returns_numbered_results(self):
|
||||
client = _mock_client()
|
||||
client.arecall.return_value = _mock_recall_response(
|
||||
["User likes Python", "User is in NYC"]
|
||||
)
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test-bank",
|
||||
client=client,
|
||||
include_retain=False,
|
||||
include_reflect=False,
|
||||
)
|
||||
tool_fn = tools[0].function
|
||||
|
||||
result = await tool_fn("user preferences")
|
||||
|
||||
assert "1. User likes Python" in result
|
||||
assert "2. User is in NYC" in result
|
||||
client.arecall.assert_called_once()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_recall_empty_results(self):
|
||||
client = _mock_client()
|
||||
client.arecall.return_value = _mock_recall_response([])
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
include_retain=False,
|
||||
include_reflect=False,
|
||||
)
|
||||
tool_fn = tools[0].function
|
||||
|
||||
result = await tool_fn("anything")
|
||||
|
||||
assert result == "No relevant memories found."
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_recall_passes_budget_and_max_tokens(self):
|
||||
client = _mock_client()
|
||||
client.arecall.return_value = _mock_recall_response(["fact"])
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
budget="high",
|
||||
max_tokens=2048,
|
||||
include_retain=False,
|
||||
include_reflect=False,
|
||||
)
|
||||
tool_fn = tools[0].function
|
||||
|
||||
await tool_fn("query")
|
||||
|
||||
call_kwargs = client.arecall.call_args[1]
|
||||
assert call_kwargs["budget"] == "high"
|
||||
assert call_kwargs["max_tokens"] == 2048
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_recall_passes_tags(self):
|
||||
client = _mock_client()
|
||||
client.arecall.return_value = _mock_recall_response(["fact"])
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
recall_tags=["scope:user"],
|
||||
recall_tags_match="all",
|
||||
include_retain=False,
|
||||
include_reflect=False,
|
||||
)
|
||||
tool_fn = tools[0].function
|
||||
|
||||
await tool_fn("query")
|
||||
|
||||
call_kwargs = client.arecall.call_args[1]
|
||||
assert call_kwargs["tags"] == ["scope:user"]
|
||||
assert call_kwargs["tags_match"] == "all"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_recall_raises_hindsight_error(self):
|
||||
client = _mock_client()
|
||||
client.arecall.side_effect = RuntimeError("timeout")
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
include_retain=False,
|
||||
include_reflect=False,
|
||||
)
|
||||
tool_fn = tools[0].function
|
||||
|
||||
with pytest.raises(HindsightError, match="Recall failed"):
|
||||
await tool_fn("query")
|
||||
|
||||
|
||||
class TestReflectTool:
|
||||
@pytest.mark.asyncio
|
||||
async def test_reflect_returns_text(self):
|
||||
client = _mock_client()
|
||||
client.areflect.return_value = _mock_reflect_response(
|
||||
"The user is a Python developer who prefers functional patterns."
|
||||
)
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test-bank",
|
||||
client=client,
|
||||
include_retain=False,
|
||||
include_recall=False,
|
||||
)
|
||||
tool_fn = tools[0].function
|
||||
|
||||
result = await tool_fn("What do you know about the user?")
|
||||
|
||||
assert result == "The user is a Python developer who prefers functional patterns."
|
||||
client.areflect.assert_called_once()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_reflect_empty_returns_fallback(self):
|
||||
client = _mock_client()
|
||||
client.areflect.return_value = _mock_reflect_response("")
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
include_retain=False,
|
||||
include_recall=False,
|
||||
)
|
||||
tool_fn = tools[0].function
|
||||
|
||||
result = await tool_fn("anything")
|
||||
|
||||
assert result == "No relevant memories found."
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_reflect_passes_budget(self):
|
||||
client = _mock_client()
|
||||
client.areflect.return_value = _mock_reflect_response("answer")
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
budget="high",
|
||||
include_retain=False,
|
||||
include_recall=False,
|
||||
)
|
||||
tool_fn = tools[0].function
|
||||
|
||||
await tool_fn("query")
|
||||
|
||||
call_kwargs = client.areflect.call_args[1]
|
||||
assert call_kwargs["budget"] == "high"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_reflect_raises_hindsight_error(self):
|
||||
client = _mock_client()
|
||||
client.areflect.side_effect = RuntimeError("timeout")
|
||||
tools = create_hindsight_tools(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
include_retain=False,
|
||||
include_recall=False,
|
||||
)
|
||||
tool_fn = tools[0].function
|
||||
|
||||
with pytest.raises(HindsightError, match="Reflect failed"):
|
||||
await tool_fn("query")
|
||||
|
||||
|
||||
class TestMemoryInstructions:
|
||||
@pytest.mark.asyncio
|
||||
async def test_returns_formatted_memories(self):
|
||||
client = _mock_client()
|
||||
client.arecall.return_value = _mock_recall_response(
|
||||
["Likes Python", "Lives in NYC", "Prefers dark mode"]
|
||||
)
|
||||
instructions_fn = memory_instructions(
|
||||
bank_id="test-bank", client=client
|
||||
)
|
||||
|
||||
# Instructions functions receive RunContext — mock it
|
||||
mock_ctx = MagicMock()
|
||||
result = await instructions_fn(mock_ctx)
|
||||
|
||||
assert "Relevant memories:" in result
|
||||
assert "1. Likes Python" in result
|
||||
assert "2. Lives in NYC" in result
|
||||
assert "3. Prefers dark mode" in result
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_respects_max_results(self):
|
||||
client = _mock_client()
|
||||
client.arecall.return_value = _mock_recall_response(
|
||||
["fact1", "fact2", "fact3", "fact4", "fact5"]
|
||||
)
|
||||
instructions_fn = memory_instructions(
|
||||
bank_id="test", client=client, max_results=2
|
||||
)
|
||||
|
||||
mock_ctx = MagicMock()
|
||||
result = await instructions_fn(mock_ctx)
|
||||
|
||||
assert "1. fact1" in result
|
||||
assert "2. fact2" in result
|
||||
assert "3." not in result
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_custom_prefix(self):
|
||||
client = _mock_client()
|
||||
client.arecall.return_value = _mock_recall_response(["fact"])
|
||||
instructions_fn = memory_instructions(
|
||||
bank_id="test", client=client, prefix="Memory context:\n"
|
||||
)
|
||||
|
||||
mock_ctx = MagicMock()
|
||||
result = await instructions_fn(mock_ctx)
|
||||
|
||||
assert result.startswith("Memory context:")
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_empty_results_returns_empty_string(self):
|
||||
client = _mock_client()
|
||||
client.arecall.return_value = _mock_recall_response([])
|
||||
instructions_fn = memory_instructions(
|
||||
bank_id="test", client=client
|
||||
)
|
||||
|
||||
mock_ctx = MagicMock()
|
||||
result = await instructions_fn(mock_ctx)
|
||||
|
||||
assert result == ""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_error_returns_empty_string(self):
|
||||
client = _mock_client()
|
||||
client.arecall.side_effect = RuntimeError("connection error")
|
||||
instructions_fn = memory_instructions(
|
||||
bank_id="test", client=client
|
||||
)
|
||||
|
||||
mock_ctx = MagicMock()
|
||||
result = await instructions_fn(mock_ctx)
|
||||
|
||||
assert result == ""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_passes_query_and_budget(self):
|
||||
client = _mock_client()
|
||||
client.arecall.return_value = _mock_recall_response(["fact"])
|
||||
instructions_fn = memory_instructions(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
query="user preferences and context",
|
||||
budget="high",
|
||||
)
|
||||
|
||||
mock_ctx = MagicMock()
|
||||
await instructions_fn(mock_ctx)
|
||||
|
||||
call_kwargs = client.arecall.call_args[1]
|
||||
assert call_kwargs["query"] == "user preferences and context"
|
||||
assert call_kwargs["budget"] == "high"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_passes_tags(self):
|
||||
client = _mock_client()
|
||||
client.arecall.return_value = _mock_recall_response(["fact"])
|
||||
instructions_fn = memory_instructions(
|
||||
bank_id="test",
|
||||
client=client,
|
||||
tags=["scope:user"],
|
||||
tags_match="all",
|
||||
)
|
||||
|
||||
mock_ctx = MagicMock()
|
||||
await instructions_fn(mock_ctx)
|
||||
|
||||
call_kwargs = client.arecall.call_args[1]
|
||||
assert call_kwargs["tags"] == ["scope:user"]
|
||||
assert call_kwargs["tags_match"] == "all"
|
||||
|
||||
def test_raises_without_client_or_config(self):
|
||||
reset_config()
|
||||
with pytest.raises(HindsightError, match="No Hindsight API URL"):
|
||||
memory_instructions(bank_id="test")
|
||||
1253
hindsight-integrations/pydantic-ai/uv.lock
Normal file
1253
hindsight-integrations/pydantic-ai/uv.lock
Normal file
File diff suppressed because it is too large
Load diff
Loading…
Reference in a new issue