supermemory-agent-framework 1.0.3__tar.gz → 2.0.0__tar.gz

{supermemory_agent_framework-1.0.3 → supermemory_agent_framework-2.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: supermemory-agent-framework
-Version: 1.0.3
+Version: 2.0.0
 Summary: Memory tools and middleware for Microsoft Agent Framework with supermemory
 Project-URL: Homepage, https://supermemory.ai
 Project-URL: Repository, https://github.com/supermemoryai/supermemory
@@ -20,7 +20,7 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Requires-Dist: agent-framework-core>=1.0.0rc3
-Requires-Dist: supermemory<5,>=3.16.0
+Requires-Dist: supermemory<6,>=5.0.0
 Requires-Dist: typing-extensions>=4.0.0
 Description-Content-Type: text/markdown
 
@@ -32,16 +32,20 @@ This package provides both **automatic memory injection middleware** and **manua
 
 ## Installation
 
+Adapter version `>=2.0.0,<3` supports the Supermemory Python SDK `>=5.0.0,<6`.
+
+The OpenAI client is a separate Agent Framework package. Include `agent-framework-openai` when using the OpenAI examples below, which target its current `OpenAIChatClient` Responses API client. The adapter also supports older framework cores, but their OpenAI client names and model arguments can differ.
+
 Install using uv (recommended):
 
 ```bash
-uv add supermemory-agent-framework
+uv add "supermemory-agent-framework>=2.0.0,<3" agent-framework-openai
 ```
 
 Or with pip:
 
 ```bash
-pip install supermemory-agent-framework
+pip install "supermemory-agent-framework>=2.0.0,<3" agent-framework-openai
 ```
 
 ## Quick Start
@@ -52,7 +56,7 @@ The easiest way to add memory capabilities is using the `SupermemoryChatMiddlewa
 
 ```python
 import asyncio
-from agent_framework.openai import OpenAIResponsesClient
+from agent_framework.openai import OpenAIChatClient
 from supermemory_agent_framework import (
     AgentSupermemory,
     SupermemoryChatMiddleware,
@@ -75,7 +79,7 @@ async def main():
     )
 
     # Create agent with middleware
-    agent = OpenAIResponsesClient().as_agent(
+    agent = OpenAIChatClient(model="gpt-5").as_agent(
         name="MemoryAgent",
         instructions="You are a helpful assistant with memory.",
         middleware=[middleware],
@@ -85,6 +89,7 @@ async def main():
     response = await agent.run(
         "What's my favorite programming language?"
     )
+    await middleware.wait_for_background_tasks()
     print(response.text)
 
 asyncio.run(main())
@@ -97,7 +102,7 @@ The most idiomatic way to add memory in Agent Framework, using the same pattern
 ```python
 import asyncio
 from agent_framework import AgentSession
-from agent_framework.openai import OpenAIResponsesClient
+from agent_framework.openai import OpenAIChatClient
 from supermemory_agent_framework import AgentSupermemory, SupermemoryContextProvider
 
 async def main():
@@ -113,7 +118,7 @@ async def main():
     )
 
     # Create agent with context provider
-    agent = OpenAIResponsesClient().as_agent(
+    agent = OpenAIChatClient(model="gpt-5").as_agent(
         name="MemoryAgent",
         instructions="You are a helpful assistant with memory.",
         context_providers=[provider],
@@ -136,7 +141,7 @@ For explicit tool-based memory access:
 
 ```python
 import asyncio
-from agent_framework.openai import OpenAIResponsesClient
+from agent_framework.openai import OpenAIChatClient
 from supermemory_agent_framework import AgentSupermemory, SupermemoryTools
 
 async def main():
@@ -147,7 +152,7 @@ async def main():
     tools = SupermemoryTools(connection)
 
     # Create agent
-    agent = OpenAIResponsesClient().as_agent(
+    agent = OpenAIChatClient(model="gpt-5").as_agent(
         name="MemoryAgent",
         instructions="You are a helpful assistant with access to user memories.",
     )
@@ -168,7 +173,7 @@ For maximum flexibility, use both middleware (automatic context injection) and t
 
 ```python
 import asyncio
-from agent_framework.openai import OpenAIResponsesClient
+from agent_framework.openai import OpenAIChatClient
 from supermemory_agent_framework import (
     AgentSupermemory,
     SupermemoryChatMiddleware,
@@ -190,7 +195,7 @@ async def main():
 
     tools = SupermemoryTools(connection)
 
-    agent = OpenAIResponsesClient().as_agent(
+    agent = OpenAIChatClient(model="gpt-5").as_agent(
         name="MemoryAgent",
         instructions="You are a helpful assistant with memory.",
         middleware=[middleware],
@@ -284,10 +289,23 @@ result = await tools.add_memory("User prefers dark mode")
 result = await tools.get_profile()
 ```
 
-`search_memories` uses v4 hybrid search, so results can contain either a
+`search_memories` uses v5 hybrid search, so results can contain either a
 structured memory or a source chunk. The old Python-only `include_full_docs`
-argument is deprecated and ignored because v4 search does not return full
-source documents; it is not exposed to the model as a tool parameter.
+argument remains deprecated and ignored; this tool does not request full
+source documents, and the argument is not exposed to the model.
+
+### V5 compatibility
+
+- Keep passing `container_tag` and `conversation_id`. The adapter passes the container tag as the v5 namespace and uses the unchanged `conversation_<conversation_id>` value as the document `id`. Choose a separate container tag for each tenant; the default `msft_agent_chat` is shared, not tenant-specific.
+- All writes still use add/append, including tool writes and automatic conversation storage. Reusing a conversation ID adds or diffs new content into its document; it does not replace earlier turns. No document update or replacement operation is used.
+- `entity_context` remains display context prepended to retrieved memories; this migration does not start sending it as ingestion `supporting_context`.
+- Profile mode makes one profile request, query mode makes one search request, and full mode makes both when there is a user query. V5 profiles no longer accept a query. Profile-associated search keeps the legacy memory-only mode and `0.6` threshold rather than adopting v5's broader defaults; the explicit search tool keeps its hybrid mode and `0.6` threshold. Provider and middleware context still contains fact text rather than `{id, memory}` objects and deduplicates facts across profile/search results.
+- Tool JSON envelopes remain unchanged: search returns `success`, `results`, and `count`; add returns `success` and `memory`; profile returns `success`, `profile`, and `search_results`. Profile static/dynamic/bucket values remain strings. Profile search results retain `results`, `timing`, and `total` (the number returned). Search results retain a top-level `updated_at` mapped from v5 `system.updated_at`, along with v5 fields. Legacy optional fields that v5 does not return, such as version numbers and file paths, remain present as `null`; their values cannot be reconstructed.
+- The provider has no adapter-owned persisted state schema and leaves its scoped session state unchanged. Existing framework session exports remain loadable; keep using the same container tag and conversation ID when reconstructing the connection. The API client's credentials are not serialized into session state.
+
+This maps requests but does not move server-side data. If existing v3/v4 data has not been migrated into the corresponding v5 namespace, follow the [v5 migration guide](https://supermemory.ai/docs/migration/api-v5) before relying on historical recall. The adapter does not delete or rewrite the old data.
+
+Writes are accepted asynchronously; `queued` is not a guarantee that a later search already contains the new memory. The SDK's default processing mode is unchanged. Enabling both provider storage and middleware storage can submit overlapping conversation content, so use one automatic storage path unless that is intentional.
 
 ### SupermemoryChatMiddleware
 
@@ -333,6 +351,8 @@ except SupermemoryConfigurationError as e:
 
 ### Exception Types
 
+Tools return failures as JSON with `success: false` and `error`. Provider retrieval/storage and middleware retrieval failures are logged and do not abort the agent run. Middleware background write failures are logged; `wait_for_background_tasks()` waits for those tasks but does not re-raise their operation errors (its own wait timeout still raises `asyncio.TimeoutError`). SDK connection and request timeout failures are classified separately for background writes.
+
 - **`SupermemoryError`** - Base class for all Supermemory exceptions
 - **`SupermemoryConfigurationError`** - Missing API keys, invalid configuration
 - **`SupermemoryAPIError`** - API request failures (includes status codes)
@@ -349,7 +369,7 @@ except SupermemoryConfigurationError as e:
 
 ### Required
 - `agent-framework-core>=1.0.0rc3` - Microsoft Agent Framework
-- `supermemory>=3.16.0` - Supermemory client with v4 hybrid search support
+- `supermemory>=5.0.0,<6` - Namespace-first Supermemory v5 client
 - `typing-extensions>=4.0.0` - Typing compatibility helpers
 
 ## Development
@@ -368,8 +388,11 @@ uv run mypy src/supermemory_agent_framework
 # Formatting
 uv run black src/ tests/
 uv run isort src/ tests/
+uv run flake8 src/ tests/ --ignore=E501,W503,E704
 ```
 
+The HTTP-transport regression suite uses the actual Supermemory SDK and runs a real Agent Framework agent/tool loop without API credentials or a live model. It is verified against both `agent-framework-core==1.0.0rc3` and `1.21.0`.
+
 ## License
 
 MIT License - see LICENSE file for details.

{supermemory_agent_framework-1.0.3 → supermemory_agent_framework-2.0.0}/README.md

@@ -6,16 +6,20 @@ This package provides both **automatic memory injection middleware** and **manua
 
 ## Installation
 
+Adapter version `>=2.0.0,<3` supports the Supermemory Python SDK `>=5.0.0,<6`.
+
+The OpenAI client is a separate Agent Framework package. Include `agent-framework-openai` when using the OpenAI examples below, which target its current `OpenAIChatClient` Responses API client. The adapter also supports older framework cores, but their OpenAI client names and model arguments can differ.
+
 Install using uv (recommended):
 
 ```bash
-uv add supermemory-agent-framework
+uv add "supermemory-agent-framework>=2.0.0,<3" agent-framework-openai
 ```
 
 Or with pip:
 
 ```bash
-pip install supermemory-agent-framework
+pip install "supermemory-agent-framework>=2.0.0,<3" agent-framework-openai
 ```
 
 ## Quick Start
@@ -26,7 +30,7 @@ The easiest way to add memory capabilities is using the `SupermemoryChatMiddlewa
 
 ```python
 import asyncio
-from agent_framework.openai import OpenAIResponsesClient
+from agent_framework.openai import OpenAIChatClient
 from supermemory_agent_framework import (
     AgentSupermemory,
     SupermemoryChatMiddleware,
@@ -49,7 +53,7 @@ async def main():
     )
 
     # Create agent with middleware
-    agent = OpenAIResponsesClient().as_agent(
+    agent = OpenAIChatClient(model="gpt-5").as_agent(
         name="MemoryAgent",
         instructions="You are a helpful assistant with memory.",
         middleware=[middleware],
@@ -59,6 +63,7 @@ async def main():
     response = await agent.run(
         "What's my favorite programming language?"
     )
+    await middleware.wait_for_background_tasks()
     print(response.text)
 
 asyncio.run(main())
@@ -71,7 +76,7 @@ The most idiomatic way to add memory in Agent Framework, using the same pattern
 ```python
 import asyncio
 from agent_framework import AgentSession
-from agent_framework.openai import OpenAIResponsesClient
+from agent_framework.openai import OpenAIChatClient
 from supermemory_agent_framework import AgentSupermemory, SupermemoryContextProvider
 
 async def main():
@@ -87,7 +92,7 @@ async def main():
     )
 
     # Create agent with context provider
-    agent = OpenAIResponsesClient().as_agent(
+    agent = OpenAIChatClient(model="gpt-5").as_agent(
         name="MemoryAgent",
         instructions="You are a helpful assistant with memory.",
         context_providers=[provider],
@@ -110,7 +115,7 @@ For explicit tool-based memory access:
 
 ```python
 import asyncio
-from agent_framework.openai import OpenAIResponsesClient
+from agent_framework.openai import OpenAIChatClient
 from supermemory_agent_framework import AgentSupermemory, SupermemoryTools
 
 async def main():
@@ -121,7 +126,7 @@ async def main():
     tools = SupermemoryTools(connection)
 
     # Create agent
-    agent = OpenAIResponsesClient().as_agent(
+    agent = OpenAIChatClient(model="gpt-5").as_agent(
         name="MemoryAgent",
         instructions="You are a helpful assistant with access to user memories.",
     )
@@ -142,7 +147,7 @@ For maximum flexibility, use both middleware (automatic context injection) and t
 
 ```python
 import asyncio
-from agent_framework.openai import OpenAIResponsesClient
+from agent_framework.openai import OpenAIChatClient
 from supermemory_agent_framework import (
     AgentSupermemory,
     SupermemoryChatMiddleware,
@@ -164,7 +169,7 @@ async def main():
 
     tools = SupermemoryTools(connection)
 
-    agent = OpenAIResponsesClient().as_agent(
+    agent = OpenAIChatClient(model="gpt-5").as_agent(
         name="MemoryAgent",
         instructions="You are a helpful assistant with memory.",
         middleware=[middleware],
@@ -258,10 +263,23 @@ result = await tools.add_memory("User prefers dark mode")
 result = await tools.get_profile()
 ```
 
-`search_memories` uses v4 hybrid search, so results can contain either a
+`search_memories` uses v5 hybrid search, so results can contain either a
 structured memory or a source chunk. The old Python-only `include_full_docs`
-argument is deprecated and ignored because v4 search does not return full
-source documents; it is not exposed to the model as a tool parameter.
+argument remains deprecated and ignored; this tool does not request full
+source documents, and the argument is not exposed to the model.
+
+### V5 compatibility
+
+- Keep passing `container_tag` and `conversation_id`. The adapter passes the container tag as the v5 namespace and uses the unchanged `conversation_<conversation_id>` value as the document `id`. Choose a separate container tag for each tenant; the default `msft_agent_chat` is shared, not tenant-specific.
+- All writes still use add/append, including tool writes and automatic conversation storage. Reusing a conversation ID adds or diffs new content into its document; it does not replace earlier turns. No document update or replacement operation is used.
+- `entity_context` remains display context prepended to retrieved memories; this migration does not start sending it as ingestion `supporting_context`.
+- Profile mode makes one profile request, query mode makes one search request, and full mode makes both when there is a user query. V5 profiles no longer accept a query. Profile-associated search keeps the legacy memory-only mode and `0.6` threshold rather than adopting v5's broader defaults; the explicit search tool keeps its hybrid mode and `0.6` threshold. Provider and middleware context still contains fact text rather than `{id, memory}` objects and deduplicates facts across profile/search results.
+- Tool JSON envelopes remain unchanged: search returns `success`, `results`, and `count`; add returns `success` and `memory`; profile returns `success`, `profile`, and `search_results`. Profile static/dynamic/bucket values remain strings. Profile search results retain `results`, `timing`, and `total` (the number returned). Search results retain a top-level `updated_at` mapped from v5 `system.updated_at`, along with v5 fields. Legacy optional fields that v5 does not return, such as version numbers and file paths, remain present as `null`; their values cannot be reconstructed.
+- The provider has no adapter-owned persisted state schema and leaves its scoped session state unchanged. Existing framework session exports remain loadable; keep using the same container tag and conversation ID when reconstructing the connection. The API client's credentials are not serialized into session state.
+
+This maps requests but does not move server-side data. If existing v3/v4 data has not been migrated into the corresponding v5 namespace, follow the [v5 migration guide](https://supermemory.ai/docs/migration/api-v5) before relying on historical recall. The adapter does not delete or rewrite the old data.
+
+Writes are accepted asynchronously; `queued` is not a guarantee that a later search already contains the new memory. The SDK's default processing mode is unchanged. Enabling both provider storage and middleware storage can submit overlapping conversation content, so use one automatic storage path unless that is intentional.
 
 ### SupermemoryChatMiddleware
 
@@ -307,6 +325,8 @@ except SupermemoryConfigurationError as e:
 
 ### Exception Types
 
+Tools return failures as JSON with `success: false` and `error`. Provider retrieval/storage and middleware retrieval failures are logged and do not abort the agent run. Middleware background write failures are logged; `wait_for_background_tasks()` waits for those tasks but does not re-raise their operation errors (its own wait timeout still raises `asyncio.TimeoutError`). SDK connection and request timeout failures are classified separately for background writes.
+
 - **`SupermemoryError`** - Base class for all Supermemory exceptions
 - **`SupermemoryConfigurationError`** - Missing API keys, invalid configuration
 - **`SupermemoryAPIError`** - API request failures (includes status codes)
@@ -323,7 +343,7 @@ except SupermemoryConfigurationError as e:
 
 ### Required
 - `agent-framework-core>=1.0.0rc3` - Microsoft Agent Framework
-- `supermemory>=3.16.0` - Supermemory client with v4 hybrid search support
+- `supermemory>=5.0.0,<6` - Namespace-first Supermemory v5 client
 - `typing-extensions>=4.0.0` - Typing compatibility helpers
 
 ## Development
@@ -342,8 +362,11 @@ uv run mypy src/supermemory_agent_framework
 # Formatting
 uv run black src/ tests/
 uv run isort src/ tests/
+uv run flake8 src/ tests/ --ignore=E501,W503,E704
 ```
 
+The HTTP-transport regression suite uses the actual Supermemory SDK and runs a real Agent Framework agent/tool loop without API credentials or a live model. It is verified against both `agent-framework-core==1.0.0rc3` and `1.21.0`.
+
 ## License
 
 MIT License - see LICENSE file for details.

{supermemory_agent_framework-1.0.3 → supermemory_agent_framework-2.0.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "supermemory-agent-framework"
-version = "1.0.3"
+version = "2.0.0"
 description = "Memory tools and middleware for Microsoft Agent Framework with supermemory"
 readme = "README.md"
 license = "MIT"
@@ -25,7 +25,7 @@ classifiers = [
 requires-python = ">=3.10"
 dependencies = [
     "agent-framework-core>=1.0.0rc3",
-    "supermemory>=3.16.0,<5",
+    "supermemory>=5.0.0,<6",
     "typing-extensions>=4.0.0",
 ]
 

{supermemory_agent_framework-1.0.3 → supermemory_agent_framework-2.0.0}/src/supermemory_agent_framework/__init__.py

@@ -3,38 +3,33 @@
 from .connection import (
     AgentSupermemory,
 )
-
-from .tools import (
-    SupermemoryTools,
-    MemorySearchResult,
-    MemoryAddResult,
-    ProfileResult,
+from .context_provider import (
+    SupermemoryContextProvider,
+)
+from .exceptions import (
+    SupermemoryAPIError,
+    SupermemoryConfigurationError,
+    SupermemoryError,
+    SupermemoryMemoryOperationError,
+    SupermemoryNetworkError,
+    SupermemoryTimeoutError,
 )
-
 from .middleware import (
     SupermemoryChatMiddleware,
     SupermemoryMiddlewareOptions,
 )
-
-from .context_provider import (
-    SupermemoryContextProvider,
+from .tools import (
+    MemoryAddResult,
+    MemorySearchResult,
+    ProfileResult,
+    SupermemoryTools,
 )
-
 from .utils import (
+    DeduplicatedMemories,
     Logger,
+    convert_profile_to_markdown,
     create_logger,
     deduplicate_memories,
-    DeduplicatedMemories,
-    convert_profile_to_markdown,
-)
-
-from .exceptions import (
-    SupermemoryError,
-    SupermemoryConfigurationError,
-    SupermemoryAPIError,
-    SupermemoryMemoryOperationError,
-    SupermemoryTimeoutError,
-    SupermemoryNetworkError,
 )
 
 __all__ = [
@@ -57,4 +52,4 @@ __all__ = [
     "SupermemoryMemoryOperationError",
     "SupermemoryTimeoutError",
     "SupermemoryNetworkError",
-]
+]

{supermemory_agent_framework-1.0.3 → supermemory_agent_framework-2.0.0}/src/supermemory_agent_framework/context_provider.py

@@ -14,13 +14,11 @@ from agent_framework import Message
 try:
     from agent_framework import BaseContextProvider  # type: ignore[attr-defined]
 except ImportError:
-    # Renamed in agent-framework-core 1.0.0 stable; the interface is
-    # unchanged (source_id __init__, before_run/after_run hooks with
-    # identical keyword-only signatures).
     from agent_framework import ContextProvider as BaseContextProvider
 
 from .connection import AgentSupermemory
 from .utils import (
+    _fetch_profile_and_search,
     convert_profile_to_markdown,
     create_logger,
     deduplicate_memories,
@@ -40,7 +38,7 @@ class SupermemoryContextProvider(BaseContextProvider):
     Example:
         ```python
         from agent_framework import Agent, AgentSession
-        from agent_framework.openai import OpenAIResponsesClient
+        from agent_framework.openai import OpenAIChatClient
         from supermemory_agent_framework import (
             AgentSupermemory,
             SupermemoryContextProvider,
@@ -54,7 +52,7 @@ class SupermemoryContextProvider(BaseContextProvider):
             store_conversations=True,
         )
 
-        agent = OpenAIResponsesClient().as_agent(
+        agent = OpenAIChatClient(model="gpt-5").as_agent(
             name="MemoryAgent",
             instructions="You are a helpful assistant with memory.",
             context_providers=[provider],
@@ -107,7 +105,6 @@ class SupermemoryContextProvider(BaseContextProvider):
         state: dict[str, Any],
     ) -> None:
         """Search Supermemory for relevant memories and inject into context."""
-        # Extract query text from input messages
         query_text = ""
         if self._mode != "profile":
             query_text = self._extract_query_from_context(context)
@@ -137,11 +134,9 @@ class SupermemoryContextProvider(BaseContextProvider):
             self._logger.debug("No memories found")
             return
 
-        # Prepend entity context if available
         if self._connection.entity_context:
             memories_text = f"{self._connection.entity_context}\n\n{memories_text}"
 
-        # Inject memories into the session context
         full_text = wrap_memory_injection(memories_text, self._context_prompt)
 
         self._logger.debug(
@@ -149,11 +144,9 @@ class SupermemoryContextProvider(BaseContextProvider):
             {"length": len(memories_text)},
         )
 
-        # Use extend_instructions to add memory context
         if hasattr(context, "extend_instructions"):
             context.extend_instructions(self.source_id, full_text)
         elif hasattr(context, "extend_messages"):
-            # Fallback: add as a system message
             context.extend_messages(
                 self.source_id,
                 [Message("system", [full_text])],
@@ -185,13 +178,11 @@ class SupermemoryContextProvider(BaseContextProvider):
                 },
             )
 
-            add_params: dict[str, Any] = {
-                "content": conversation_text,
-                "container_tag": self._container_tag,
-                "custom_id": self._connection.custom_id,
-            }
-
-            await self._client.add(**add_params)
+            await self._client.add(
+                self._container_tag,
+                content=conversation_text,
+                id=self._connection.custom_id,
+            )
 
             self._logger.info("Conversation stored successfully")
 
@@ -203,20 +194,16 @@ class SupermemoryContextProvider(BaseContextProvider):
 
     async def _fetch_memories(self, query_text: str = "") -> str:
         """Fetch and format memories from Supermemory."""
-        kwargs: dict[str, Any] = {"container_tag": self._container_tag}
-        if query_text:
-            kwargs["q"] = query_text
-
-        response = await self._client.profile(**kwargs)
-
-        profile = response.profile if response.profile else None
+        response, search = await _fetch_profile_and_search(
+            self._client,
+            self._container_tag,
+            include_profile=self._mode != "query",
+            query=query_text if self._mode != "profile" else "",
+        )
+        profile = response.profile if response else None
         static = list(profile.static) if profile and profile.static else []
         dynamic = list(profile.dynamic) if profile and profile.dynamic else []
-        search_results_raw = (
-            list(response.search_results.results)
-            if response.search_results and response.search_results.results
-            else []
-        )
+        search_results_raw = list(search.results) if search else []
 
         deduplicated = deduplicate_memories(
             static=static if self._mode != "query" else [],
@@ -224,7 +211,6 @@ class SupermemoryContextProvider(BaseContextProvider):
             search_results=search_results_raw,
         )
 
-        # Build formatted text based on mode
         profile_text = ""
         if self._mode != "query":
             profile_text = convert_profile_to_markdown(
@@ -290,13 +276,11 @@ class SupermemoryContextProvider(BaseContextProvider):
         """Extract conversation text from context for storage."""
         messages: list[Any] = []
 
-        # Gather input messages
         if hasattr(context, "input_messages"):
             messages.extend(context.input_messages or [])
         elif hasattr(context, "messages"):
             messages.extend(context.messages or [])
 
-        # Gather response messages
         if hasattr(context, "response") and context.response:
             resp = context.response
             if hasattr(resp, "text") and resp.text:

{supermemory_agent_framework-1.0.3 → supermemory_agent_framework-2.0.0}/src/supermemory_agent_framework/middleware.py

@@ -15,9 +15,11 @@ from .connection import AgentSupermemory
 from .exceptions import (
     SupermemoryMemoryOperationError,
     SupermemoryNetworkError,
+    SupermemoryTimeoutError,
 )
 from .utils import (
     Logger,
+    _fetch_profile_and_search,
     convert_profile_to_markdown,
     create_logger,
     deduplicate_memories,
@@ -125,20 +127,16 @@ async def _build_memories_text(
     query_text: str = "",
 ) -> str:
     """Build formatted memories text from Supermemory API."""
-    kwargs: dict[str, Any] = {"container_tag": container_tag}
-    if query_text:
-        kwargs["q"] = query_text
-
-    memories_response = await client.profile(**kwargs)
-
-    profile = memories_response.profile if memories_response.profile else None
+    memories_response, search = await _fetch_profile_and_search(
+        client,
+        container_tag,
+        include_profile=mode != "query",
+        query=query_text if mode != "profile" else "",
+    )
+    profile = memories_response.profile if memories_response else None
     static = list(profile.static) if profile and profile.static else []
     dynamic = list(profile.dynamic) if profile and profile.dynamic else []
-    search_results_raw = (
-        list(memories_response.search_results.results)
-        if memories_response.search_results and memories_response.search_results.results
-        else []
-    )
+    search_results_raw = list(search.results) if search else []
 
     logger.info(
         "Memory search completed",
@@ -146,9 +144,7 @@ async def _build_memories_text(
             "container_tag": container_tag,
             "memory_count_static": len(static),
             "memory_count_dynamic": len(dynamic),
-            "query_text": (
-                query_text[:100] + ("..." if len(query_text) > 100 else "")
-            ),
+            "query_text": (query_text[:100] + ("..." if len(query_text) > 100 else "")),
             "mode": mode,
         },
     )
@@ -190,13 +186,7 @@ async def _save_memory(
 ) -> None:
     """Save a memory to Supermemory."""
     try:
-        add_params: dict[str, Any] = {
-            "content": content,
-            "container_tag": container_tag,
-            "custom_id": custom_id,
-        }
-
-        response = await client.add(**add_params)
+        response = await client.add(container_tag, content=content, id=custom_id)
 
         logger.info(
             "Memory saved successfully",
@@ -207,10 +197,11 @@ async def _save_memory(
                 "memory_id": getattr(response, "id", None),
             },
         )
-    except (OSError, ConnectionError) as network_error:
-        logger.error(
-            "Network error while saving memory", {"error": str(network_error)}
-        )
+    except supermemory.APITimeoutError as timeout_error:
+        logger.error("Timeout while saving memory", {"error": str(timeout_error)})
+        raise SupermemoryTimeoutError("Timed out saving memory", timeout_error)
+    except (supermemory.APIConnectionError, OSError, ConnectionError) as network_error:
+        logger.error("Network error while saving memory", {"error": str(network_error)})
         raise SupermemoryNetworkError(
             "Failed to save memory due to network error", network_error
         )
@@ -228,7 +219,7 @@ class SupermemoryChatMiddleware(ChatMiddleware):
 
     Example:
         ```python
-        from agent_framework.openai import OpenAIResponsesClient
+        from agent_framework.openai import OpenAIChatClient
         from supermemory_agent_framework import (
             AgentSupermemory,
             SupermemoryChatMiddleware,
@@ -246,7 +237,7 @@ class SupermemoryChatMiddleware(ChatMiddleware):
             ),
         )
 
-        agent = OpenAIResponsesClient().as_agent(
+        agent = OpenAIChatClient(model="gpt-5").as_agent(
             name="MemoryAgent",
             instructions="You are a helpful assistant with memory.",
             middleware=[middleware],
@@ -274,12 +265,9 @@ class SupermemoryChatMiddleware(ChatMiddleware):
         call_next: Callable[[], Awaitable[None]],
     ) -> None:
         """Process the chat request by injecting memories and optionally saving conversations."""
-        # Remove stale SDK-owned context before every lifecycle path. A failed,
-        # empty, or skipped lookup must never leak memories from a prior run.
         _inject_memories(context, "")
         messages = context.messages
 
-        # Save conversation memory in background if configured
         if self._options.add_memory == "always":
             user_message = _get_last_user_message(messages)
             if user_message and user_message.strip():
@@ -310,7 +298,6 @@ class SupermemoryChatMiddleware(ChatMiddleware):
 
                 task.add_done_callback(_handle_task_exception)
 
-        # Determine query text based on mode
         query_text = ""
         if self._options.mode != "profile":
             user_message = _get_last_user_message(messages)
@@ -329,7 +316,6 @@ class SupermemoryChatMiddleware(ChatMiddleware):
             },
         )
 
-        # Fetch and build memories text
         try:
             memories = await _build_memories_text(
                 self._container_tag,
@@ -347,7 +333,6 @@ class SupermemoryChatMiddleware(ChatMiddleware):
             return
 
         if memories:
-            # Prepend entity context if available
             if self._connection.entity_context:
                 memories = f"{self._connection.entity_context}\n\n{memories}"
 
@@ -356,14 +341,11 @@ class SupermemoryChatMiddleware(ChatMiddleware):
                 {"content": memories[:200], "full_length": len(memories)},
             )
 
-            # Inject memories into messages
             _inject_memories(context, memories)
 
         await call_next()
 
-    async def wait_for_background_tasks(
-        self, timeout: Optional[float] = 10.0
-    ) -> None:
+    async def wait_for_background_tasks(self, timeout: Optional[float] = 10.0) -> None:
         """Wait for all background memory storage tasks to complete."""
         if not self._background_tasks:
             return

{supermemory_agent_framework-1.0.3 → supermemory_agent_framework-2.0.0}/src/supermemory_agent_framework/tools.py

@@ -8,8 +8,10 @@ import warnings
 from typing import Annotated, Any, Optional, TypedDict
 
 from agent_framework import FunctionTool, tool
+from supermemory.types import SearchResponse
 
 from .connection import AgentSupermemory
+from .utils import _fetch_profile_and_search
 
 
 class MemorySearchResult(TypedDict, total=False):
@@ -50,13 +52,30 @@ def _to_jsonable(value: Any) -> Any:
         try:
             return _to_jsonable(model_dump(mode="json"))
         except TypeError:
-            # Compatibility with pydantic-like models whose model_dump does not
-            # accept Pydantic v2's ``mode`` argument.
             return _to_jsonable(model_dump())
 
     return value
 
 
+def _serialize_search_results(response: SearchResponse) -> dict[str, Any]:
+    """Keep the tool's legacy result fields while retaining v5 metadata."""
+    results = [
+        {
+            "chunks": None,
+            "context": None,
+            "documents": None,
+            "filepath": None,
+            "is_aggregated": None,
+            "root_memory_id": None,
+            "version": None,
+            **_to_jsonable(item),
+            "updated_at": item.system.updated_at,
+        }
+        for item in response.results
+    ]
+    return {"results": results, "timing": response.search_time, "total": len(results)}
+
+
 class SupermemoryTools:
     """Memory tools for Microsoft Agent Framework.
 
@@ -92,28 +111,28 @@ class SupermemoryTools:
         """Search stored memories and source chunks.
 
         ``include_full_docs`` remains a deprecated Python-only argument for
-        source compatibility. V4 search cannot return full source documents.
+        source compatibility. This tool does not return full source documents.
         """
         if include_full_docs is not None:
             warnings.warn(
-                "include_full_docs is deprecated and ignored because v4 search "
-                "does not return full source documents",
+                "include_full_docs is deprecated and ignored; search_memories "
+                "does not request full source documents",
                 DeprecationWarning,
                 stacklevel=2,
             )
 
         try:
-            response = await self._client.search.memories(
-                q=information_to_get,
-                container_tag=self._connection.container_tag,
+            response = await self._client.search(
+                self._connection.container_tag,
+                query=information_to_get,
                 limit=limit,
                 threshold=0.6,
                 search_mode="hybrid",
             )
-            results = response.results or []
+            results = _serialize_search_results(response)["results"]
             result: MemorySearchResult = {
                 "success": True,
-                "results": [_to_jsonable(item) for item in results],
+                "results": results,
                 "count": len(results),
             }
             return json.dumps(result, default=str)
@@ -131,9 +150,9 @@ class SupermemoryTools:
         """Add (remember) memories/details/information about the user or other facts or entities. Run when explicitly asked or when the user mentions any information generalizable beyond the context of the current conversation."""
         try:
             response = await self._client.add(
+                self._connection.container_tag,
                 content=memory,
-                container_tag=self._connection.container_tag,
-                custom_id=self._connection.custom_id,
+                id=self._connection.custom_id,
             )
             result: MemoryAddResult = {
                 "success": True,
@@ -153,23 +172,24 @@ class SupermemoryTools:
     ) -> str:
         """Get user profile containing static memories (permanent facts) and dynamic memories (recent context). Optionally include search results by providing a query."""
         try:
-            kwargs: dict[str, Any] = {"container_tag": self._connection.container_tag}
-            if query:
-                kwargs["q"] = query
-
-            response = await self._client.profile(**kwargs)
+            response, search = await _fetch_profile_and_search(
+                self._client, self._connection.container_tag, query=query
+            )
             result: dict[str, Any] = {
                 "success": True,
                 "profile": (
-                    _to_jsonable(response.profile)
-                    if hasattr(response, "profile")
-                    else None
-                ),
-                "search_results": (
-                    _to_jsonable(response.search_results)
-                    if hasattr(response, "search_results")
+                    {
+                        "static": [fact.memory for fact in response.profile.static],
+                        "dynamic": [fact.memory for fact in response.profile.dynamic],
+                        "buckets": {
+                            name: [fact.memory for fact in facts]
+                            for name, facts in response.profile.buckets.items()
+                        },
+                    }
+                    if response
                     else None
                 ),
+                "search_results": _serialize_search_results(search) if search else None,
             }
             return json.dumps(result, default=str)
         except Exception as error:

{supermemory_agent_framework-1.0.3 → supermemory_agent_framework-2.0.0}/src/supermemory_agent_framework/utils.py

@@ -1,9 +1,13 @@
 """Utility functions for Supermemory Agent Framework integration."""
 
+import asyncio
 import json
 import re
 from typing import Any, Optional, Protocol
 
+import supermemory
+from supermemory.types import ProfileResponse, SearchResponse
+
 DEFAULT_CONTEXT_PROMPT = "The following are retrieved memories about the user."
 MEMORY_CONTEXT_PATTERN = re.compile(
     r'(?:\r?\n)?<supermemory context="user-memories" readonly>.*?</supermemory>',
@@ -15,6 +19,31 @@ SUPERMEMORY_TAG_PATTERN = re.compile(
 )
 
 
+async def _fetch_profile_and_search(
+    client: supermemory.AsyncSupermemory,
+    container_tag: str,
+    *,
+    include_profile: bool = True,
+    query: str = "",
+) -> tuple[Optional[ProfileResponse], Optional[SearchResponse]]:
+    """Fetch the independent v5 profile and query resources in one namespace."""
+    if include_profile and query:
+        profile, search = await asyncio.gather(
+            client.profile(container_tag),
+            client.search(
+                container_tag, query=query, threshold=0.6, search_mode="memories"
+            ),
+        )
+        return profile, search
+    if include_profile:
+        return await client.profile(container_tag), None
+    if query:
+        return None, await client.search(
+            container_tag, query=query, threshold=0.6, search_mode="memories"
+        )
+    return None, None
+
+
 def _escape_supermemory_tags(content: str) -> str:
     """Escape nested Supermemory tags supplied as untrusted memory data."""
 
@@ -134,7 +163,6 @@ def deduplicate_memories(
                 if isinstance(value, str) and value.strip():
                     return value.strip()
             return None
-        # Stainless SDK returns pydantic models (attribute access, snake_case).
         for field in ("memory", "chunk", "content"):
             value = getattr(item, field, None)
             if isinstance(value, str) and value.strip():