autogen-memorysync 1.0.0__tar.gz

autogen_memorysync-1.0.0/.gitignore

@@ -0,0 +1,5 @@
+venv/
+dist/
+__pycache__/
+*.egg-info/
+.pytest_cache/

autogen_memorysync-1.0.0/PKG-INFO

@@ -0,0 +1,111 @@
+Metadata-Version: 2.5
+Name: autogen-memorysync
+Version: 1.0.0
+Summary: MemorySync for Microsoft AutoGen: an async-native Memory implementation with a hard recall budget, role-aware retrieval, duplicate-proof persistence, and session-scoped clear.
+Project-URL: Homepage, https://docs.memorysync.io/guides/autogen
+Project-URL: Documentation, https://docs.memorysync.io/guides/autogen
+Project-URL: Repository, https://github.com/Rafay121/memorysync-plugins
+Author-email: MemorySync <support@memorysync.io>
+License-Expression: MIT
+Keywords: agents,autogen,autogen-agentchat,long-term-memory,memory,memorysync
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Requires-Dist: autogen-core<0.8,>=0.4.0
+Requires-Dist: httpx<1,>=0.25
+Description-Content-Type: text/markdown
+
+# autogen-memorysync
+
+[MemorySync](https://memorysync.io) for [Microsoft AutoGen](https://github.com/microsoft/autogen)
+(`autogen-agentchat` 0.4+): agents that remember users across sessions —
+without ever stalling a turn.
+
+```bash
+pip install autogen-memorysync
+```
+
+## Quick start
+
+```python
+from autogen_agentchat.agents import AssistantAgent
+from autogen_memorysync import MemorySyncMemory
+
+memory = MemorySyncMemory(
+    api_key="ms_...",              # or MEMORYSYNC_API_KEY
+    user_id="customer-42",         # required — who these memories belong to
+    session_id="support-chat",     # scopes the transcript
+)
+
+agent = AssistantAgent("assistant", model_client=..., memory=[memory])
+
+result = await agent.run(task=user_text)
+# AutoGen never persists automatically — capture the exchange in one call:
+await memory.add_turn_pair(user_text, result.messages[-1].content)
+```
+
+`update_context` runs automatically before every model call: relevant
+memories are recalled and injected as a `SystemMessage`, and the
+retrieval surfaces to observers as a `MemoryQueryEvent`.
+
+## Why this one
+
+| | Mem0 (`autogen-ext[mem0]`) | Zep (`zep-autogen`) | **MemorySync** |
+| --- | --- | --- | --- |
+| Async correctness | ✗ sync client inside `async def` — blocks the event loop | ✓ | ✓ `httpx.AsyncClient` throughout |
+| Recall latency budget | ✗ none | ✗ none | ✓ hard 1.2s default — a slow backend means an unenriched turn, never a late one |
+| Retrieval query | ✗ `messages[-1]` even when it's assistant/tool text | last context message | ✓ last **user** message, role-aware |
+| Query errors | ✗ swallowed — outage looks like amnesia | logged | ✓ explicit `query()` raises; only the hot path fails open |
+| `clear()` blast radius | ✗ entire user | ✗ entire user | ✓ **session-scoped by default**; whole-user wipe is an explicit opt-in |
+| Retry safety | ✗ | ✗ | ✓ deterministic idempotency seeds — retries converge on one row |
+| Caller's metadata dict | ✗ mutated (`pop`) | — | ✓ copied, never touched |
+| `close()` | `pass` | ✓ | ✓ releases the HTTP client |
+
+## Semantics worth knowing
+
+- **The turn is never stalled and never broken.** Recall waits at most
+  `recall_timeout` (default 1.2s); on timeout, outage, or quota
+  exhaustion the agent simply answers without memories.
+- **`user_id` is required.** No silent auto-generated UUID namespaces
+  where stored memories can never be found again.
+- Turns store verbatim under the `autogen::<session>` transcript scope —
+  separate history, same shared user memories as every other MemorySync
+  surface.
+- Free-tier quota exhaustion is silent by design (adds accepted-without-
+  storing, reads empty); evaluation keys surface strict `429`s.
+- `create_memory_tools(memory)` returns `search_memory` + `save_memory`
+  `FunctionTool`s for tool-equipped agents.
+
+## Configuration
+
+| Parameter | Default | Meaning |
+| --- | --- | --- |
+| `user_id` | — (required) | End user the memories belong to |
+| `session_id` | `"default"` | Transcript scope |
+| `top_k` | `5` | Memories considered per turn |
+| `recall_timeout` | `1.2` | Hard recall budget, seconds |
+| `min_prompt_chars` | `8` | Skip recall for trivial prompts |
+| `context_template` | built-in | `{context}` placeholder, brace-safe `.replace` rendering |
+| `clear_scope` | `"session"` | `clear()` blast radius; `"user"` opt-in wipes everything |
+
+## Development
+
+```bash
+pip install -e . autogen-agentchat autogen-ext pytest pytest-asyncio
+python -m pytest tests -q      # 33 tests incl. a REAL AssistantAgent drive
+```
+
+Note: `autogen-agentchat` is in maintenance mode (Microsoft's successor
+is the Microsoft Agent Framework — a separate MemorySync adapter target).
+Maintenance mode means the `Memory` protocol this package implements is
+frozen and stable.
+
+## License
+
+MIT

autogen_memorysync-1.0.0/README.md

@@ -0,0 +1,88 @@
+# autogen-memorysync
+
+[MemorySync](https://memorysync.io) for [Microsoft AutoGen](https://github.com/microsoft/autogen)
+(`autogen-agentchat` 0.4+): agents that remember users across sessions —
+without ever stalling a turn.
+
+```bash
+pip install autogen-memorysync
+```
+
+## Quick start
+
+```python
+from autogen_agentchat.agents import AssistantAgent
+from autogen_memorysync import MemorySyncMemory
+
+memory = MemorySyncMemory(
+    api_key="ms_...",              # or MEMORYSYNC_API_KEY
+    user_id="customer-42",         # required — who these memories belong to
+    session_id="support-chat",     # scopes the transcript
+)
+
+agent = AssistantAgent("assistant", model_client=..., memory=[memory])
+
+result = await agent.run(task=user_text)
+# AutoGen never persists automatically — capture the exchange in one call:
+await memory.add_turn_pair(user_text, result.messages[-1].content)
+```
+
+`update_context` runs automatically before every model call: relevant
+memories are recalled and injected as a `SystemMessage`, and the
+retrieval surfaces to observers as a `MemoryQueryEvent`.
+
+## Why this one
+
+| | Mem0 (`autogen-ext[mem0]`) | Zep (`zep-autogen`) | **MemorySync** |
+| --- | --- | --- | --- |
+| Async correctness | ✗ sync client inside `async def` — blocks the event loop | ✓ | ✓ `httpx.AsyncClient` throughout |
+| Recall latency budget | ✗ none | ✗ none | ✓ hard 1.2s default — a slow backend means an unenriched turn, never a late one |
+| Retrieval query | ✗ `messages[-1]` even when it's assistant/tool text | last context message | ✓ last **user** message, role-aware |
+| Query errors | ✗ swallowed — outage looks like amnesia | logged | ✓ explicit `query()` raises; only the hot path fails open |
+| `clear()` blast radius | ✗ entire user | ✗ entire user | ✓ **session-scoped by default**; whole-user wipe is an explicit opt-in |
+| Retry safety | ✗ | ✗ | ✓ deterministic idempotency seeds — retries converge on one row |
+| Caller's metadata dict | ✗ mutated (`pop`) | — | ✓ copied, never touched |
+| `close()` | `pass` | ✓ | ✓ releases the HTTP client |
+
+## Semantics worth knowing
+
+- **The turn is never stalled and never broken.** Recall waits at most
+  `recall_timeout` (default 1.2s); on timeout, outage, or quota
+  exhaustion the agent simply answers without memories.
+- **`user_id` is required.** No silent auto-generated UUID namespaces
+  where stored memories can never be found again.
+- Turns store verbatim under the `autogen::<session>` transcript scope —
+  separate history, same shared user memories as every other MemorySync
+  surface.
+- Free-tier quota exhaustion is silent by design (adds accepted-without-
+  storing, reads empty); evaluation keys surface strict `429`s.
+- `create_memory_tools(memory)` returns `search_memory` + `save_memory`
+  `FunctionTool`s for tool-equipped agents.
+
+## Configuration
+
+| Parameter | Default | Meaning |
+| --- | --- | --- |
+| `user_id` | — (required) | End user the memories belong to |
+| `session_id` | `"default"` | Transcript scope |
+| `top_k` | `5` | Memories considered per turn |
+| `recall_timeout` | `1.2` | Hard recall budget, seconds |
+| `min_prompt_chars` | `8` | Skip recall for trivial prompts |
+| `context_template` | built-in | `{context}` placeholder, brace-safe `.replace` rendering |
+| `clear_scope` | `"session"` | `clear()` blast radius; `"user"` opt-in wipes everything |
+
+## Development
+
+```bash
+pip install -e . autogen-agentchat autogen-ext pytest pytest-asyncio
+python -m pytest tests -q      # 33 tests incl. a REAL AssistantAgent drive
+```
+
+Note: `autogen-agentchat` is in maintenance mode (Microsoft's successor
+is the Microsoft Agent Framework — a separate MemorySync adapter target).
+Maintenance mode means the `Memory` protocol this package implements is
+frozen and stable.
+
+## License
+
+MIT

autogen_memorysync-1.0.0/pyproject.toml

@@ -0,0 +1,42 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "autogen-memorysync"
+dynamic = ["version"]
+description = "MemorySync for Microsoft AutoGen: an async-native Memory implementation with a hard recall budget, role-aware retrieval, duplicate-proof persistence, and session-scoped clear."
+readme = "README.md"
+license = "MIT"
+requires-python = ">=3.10"
+authors = [{ name = "MemorySync", email = "support@memorysync.io" }]
+keywords = ["autogen", "autogen-agentchat", "agents", "memory", "memorysync", "long-term-memory"]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "autogen-core>=0.4.0,<0.8",
+    "httpx>=0.25,<1",
+]
+
+[project.urls]
+Homepage = "https://docs.memorysync.io/guides/autogen"
+Documentation = "https://docs.memorysync.io/guides/autogen"
+Repository = "https://github.com/Rafay121/memorysync-plugins"
+
+[tool.hatch.version]
+path = "src/autogen_memorysync/_version.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/autogen_memorysync"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]

autogen_memorysync-1.0.0/src/autogen_memorysync/__init__.py

@@ -0,0 +1,20 @@
+"""MemorySync for Microsoft AutoGen (autogen-agentchat 0.4+)."""
+
+from ._api import MemorySyncAPIError, fnv1a64
+from ._version import __version__
+from .memory import (
+    DEFAULT_CONTEXT_TEMPLATE,
+    MemorySyncMemory,
+    MemorySyncMemoryConfig,
+)
+from .tools import create_memory_tools
+
+__all__ = [
+    "MemorySyncMemory",
+    "MemorySyncMemoryConfig",
+    "MemorySyncAPIError",
+    "DEFAULT_CONTEXT_TEMPLATE",
+    "create_memory_tools",
+    "fnv1a64",
+    "__version__",
+]

autogen_memorysync-1.0.0/src/autogen_memorysync/_api.py

@@ -0,0 +1,311 @@
+"""Async client for the MemorySync v1 data plane used by this adapter.
+
+Conversation turns persist through the *episodic* ingestion path
+(``POST /v1/memory/add_turn``), which stores text verbatim — no fact
+extraction, no low-value-chatter gate, no rewriting. An agent transcript
+must round-trip byte-for-byte; a plane that second-guessed it would
+corrupt the user's history.
+
+Everything here is async-native because AutoGen's ``Memory`` protocol is
+fully async — a blocking HTTP client inside ``update_context`` would
+stall the event loop for every agent in the process (the exact bug in
+the Mem0 adapter that ships inside autogen-ext).
+"""
+
+from __future__ import annotations
+
+import os
+from typing import Any, Dict, List, Optional
+
+import httpx
+
+from ._version import __version__
+
+DEFAULT_BASE_URL = "https://api.memorysync.io"
+_USER_AGENT = f"autogen-memorysync/{__version__}"
+
+#: Namespace used when the key cannot list projects (see resolve_tenant_id).
+FALLBACK_TENANT = "default"
+
+#: One turn beyond this length is truncated before storage.
+MAX_TURN_CHARS = 16000
+
+
+class MemorySyncAPIError(Exception):
+    """A MemorySync call failed. Carries the status code and server detail."""
+
+    def __init__(self, message: str, *, status_code: Optional[int] = None) -> None:
+        super().__init__(message)
+        self.status_code = status_code
+
+
+def resolve_api_key(api_key: Optional[str]) -> str:
+    key = api_key or os.environ.get("MEMORYSYNC_API_KEY", "")
+    if not key or not key.strip():
+        raise ValueError(
+            "A MemorySync API key is required. Pass api_key=... or set the "
+            "MEMORYSYNC_API_KEY environment variable."
+        )
+    return key.strip()
+
+
+def resolve_base_url(base_url: Optional[str]) -> str:
+    url = base_url or os.environ.get("MEMORYSYNC_BASE_URL", "") or DEFAULT_BASE_URL
+    return url.rstrip("/")
+
+
+def fnv1a64(value: str) -> str:
+    """FNV-1a 64-bit over UTF-16 code units, as a fixed-width hex string.
+
+    Over UTF-16 code units — not code points, not UTF-8 bytes — so the
+    output matches every other MemorySync adapter (Python and JS)
+    character for character. Identical seeds across surfaces mean a turn
+    persisted here and again elsewhere converge on one stored row.
+    """
+    prime = 0x100000001B3
+    mask = 0xFFFFFFFFFFFFFFFF
+    h = 0xCBF29CE484222325
+    data = value.encode("utf-16-le")
+    for i in range(0, len(data), 2):
+        unit = data[i] | (data[i + 1] << 8)
+        h ^= unit
+        h = (h * prime) & mask
+    return format(h, "016x")
+
+
+class AsyncV1Api:
+    """Minimal asynchronous v1 client: add_turn, recall, query, list, forget."""
+
+    def __init__(
+        self,
+        *,
+        api_key: str,
+        base_url: str,
+        project_id: Optional[str] = None,
+        timeout: float = 30.0,
+        transport: Optional[httpx.AsyncBaseTransport] = None,
+    ) -> None:
+        self._api_key = api_key
+        self._base_url = base_url.rstrip("/")
+        self._project_id = project_id
+        self._timeout = timeout
+        self._transport = transport
+        self._http = httpx.AsyncClient(timeout=timeout, transport=transport)
+        self._tenant_id: Optional[str] = None
+        self._tenant_is_fallback = False
+
+    async def aclose(self) -> None:
+        await self._http.aclose()
+
+    @property
+    def base_url(self) -> str:
+        return self._base_url
+
+    # ── plumbing ─────────────────────────────────────────────────────
+
+    def _headers(self, *, end_user_id: Optional[str] = None) -> Dict[str, str]:
+        h = {
+            "X-API-Key": self._api_key,
+            "Accept": "application/json",
+            "User-Agent": _USER_AGENT,
+        }
+        if self._project_id:
+            h["X-Project-ID"] = self._project_id
+        if end_user_id:
+            h["X-End-User-ID"] = end_user_id
+        return h
+
+    async def _request(
+        self,
+        method: str,
+        path: str,
+        *,
+        json: Optional[Dict[str, Any]] = None,
+        params: Optional[Dict[str, Any]] = None,
+        end_user_id: Optional[str] = None,
+    ) -> Any:
+        url = f"{self._base_url}{path}"
+        try:
+            response = await self._http.request(
+                method,
+                url,
+                headers=self._headers(end_user_id=end_user_id),
+                json=json,
+                params=params,
+            )
+        except httpx.TimeoutException as e:
+            raise MemorySyncAPIError(f"Request timed out: {e}") from e
+        except httpx.HTTPError as e:
+            raise MemorySyncAPIError(f"Network error: {e}") from e
+
+        if response.status_code == 204:
+            return None
+        try:
+            body: Any = response.json()
+        except ValueError:
+            body = response.text or None
+        if response.status_code >= 400:
+            detail = body.get("detail") if isinstance(body, dict) else body
+            raise MemorySyncAPIError(
+                f"{method} {path} failed with HTTP {response.status_code}: {detail}",
+                status_code=response.status_code,
+            )
+        return body
+
+    # ── calls ────────────────────────────────────────────────────────
+
+    async def resolve_tenant_id(self) -> str:
+        """The tenant id, which the v1 routes need in path or body.
+
+        Derived from the project listing rather than asked for. Cached for
+        the lifetime of this client. Keys without the ``projects:read``
+        scope (evaluation keys) fall back to the fixed namespace
+        ``"default"`` — deterministic, so every read and write through
+        this client lands in one namespace. Only a definite 401/403
+        triggers the fallback; a transient server error re-raises rather
+        than silently switching namespaces.
+        """
+        if self._tenant_id:
+            return self._tenant_id
+        try:
+            projects = await self._request("GET", "/org/projects")
+        except MemorySyncAPIError as exc:
+            if exc.status_code in (401, 403):
+                self._tenant_id = FALLBACK_TENANT
+                self._tenant_is_fallback = True
+                return self._tenant_id
+            raise
+        first = projects[0] if isinstance(projects, list) and projects else None
+        tenant = first.get("tenant_id") if isinstance(first, dict) else None
+        if not tenant:
+            raise MemorySyncAPIError(
+                "Could not determine the tenant for this API key. Pass "
+                "tenant_id explicitly, or verify the key with `memorysync doctor`."
+            )
+        self._tenant_id = str(tenant)
+        return self._tenant_id
+
+    def set_tenant_id(self, tenant_id: str) -> None:
+        self._tenant_id = tenant_id
+
+    async def add_turn(
+        self,
+        *,
+        tenant_id: str,
+        user_id: str,
+        text: str,
+        speaker: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+        source: str = "autogen",
+        sync_embed: bool = False,
+    ) -> Dict[str, Any]:
+        """Store one item verbatim (episodic ingestion).
+
+        ``speaker`` participates in the server's idempotency seed, so
+        retrying an identical payload is recognised
+        (``already_exists: true``) instead of stored twice.
+        """
+        body: Dict[str, Any] = {
+            "tenant_id": tenant_id,
+            "user_id": user_id,
+            "source": source,
+            "text": text,
+            "sync_embed": sync_embed,
+        }
+        if speaker is not None:
+            body["speaker"] = speaker
+        if metadata is not None:
+            body["metadata"] = metadata
+        return await self._request("POST", "/v1/memory/add_turn", json=body) or {}
+
+    async def recall(
+        self,
+        *,
+        tenant_id: str,
+        user_id: str,
+        prompt: str,
+        k: Optional[int] = None,
+    ) -> Dict[str, Any]:
+        """Hierarchical recall: grouped, prompt-ready context block."""
+        body: Dict[str, Any] = {
+            "tenant_id": tenant_id,
+            "user_id": user_id,
+            "prompt": prompt,
+        }
+        if k is not None:
+            body["k"] = k
+        return await self._request("POST", "/v1/memory/recall", json=body) or {}
+
+    async def query(
+        self,
+        *,
+        tenant_id: str,
+        user_id: str,
+        prompt: str,
+        k: Optional[int] = None,
+    ) -> Dict[str, Any]:
+        """Plain semantic search over the pair's memories (episodic included)."""
+        body: Dict[str, Any] = {
+            "tenant_id": tenant_id,
+            "user_id": user_id,
+            "prompt": prompt,
+        }
+        if k is not None:
+            body["k"] = k
+        return await self._request("POST", "/v1/memory/query", json=body) or {}
+
+    async def list_memories(
+        self,
+        *,
+        tenant_id: str,
+        user_id: str,
+        limit: int = 0,
+    ) -> List[Dict[str, Any]]:
+        """Every memory for the tenant/user pair, newest first.
+
+        ``limit=0`` means no limit — a scoped clear must see every row,
+        so that is the default here.
+        """
+        from urllib.parse import quote
+
+        raw = await self._request(
+            "GET",
+            f"/v1/memory/{quote(tenant_id, safe='')}/{quote(user_id, safe='')}/list",
+            params={"limit": limit},
+        )
+        memories = raw.get("memories") if isinstance(raw, dict) else None
+        return list(memories) if isinstance(memories, list) else []
+
+    async def forget(self, *, user_id: str, memory_ids: List[int]) -> None:
+        """Delete specific memories by numeric id, scoped to one end user."""
+        if not memory_ids:
+            return
+        # Deletion in bounded batches so one enormous clear cannot build
+        # an unbounded request body.
+        for start in range(0, len(memory_ids), 100):
+            batch = memory_ids[start : start + 100]
+            await self._request(
+                "DELETE",
+                "/memory/forget",
+                json={"memory_ids": batch},
+                end_user_id=user_id,
+            )
+
+    async def add_memory(
+        self,
+        *,
+        user_id: str,
+        text: str,
+        source: str = "autogen",
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> Dict[str, Any]:
+        """Store a fact through the extraction path (server-side gating)."""
+        body: Dict[str, Any] = {"text": text, "source": source}
+        if metadata is not None:
+            body["metadata"] = metadata
+        return (
+            await self._request(
+                "POST", "/memory/add", json=body, end_user_id=user_id
+            )
+            or {}
+        )

autogen_memorysync-1.0.0/src/autogen_memorysync/_version.py

@@ -0,0 +1 @@
+__version__ = "1.0.0"