Bundles 10 community fixes for the Python wrappers, each commit kept with its original author. Ships supermemory-openai-sdk 1.0.10, supermemory-cartesia 0.1.5 and supermemory-pipecat 0.1.5.
- openai-sdk-python: shared OpenAI clients no longer leak memories across tenants (#1503), memory search fails open instead of crashing the chat (#1288), the requests fallback runs off the event loop (#1660), get_profile works for users with no memories (#1759).
- cartesia: the wrapped agent runs exactly once per event (#1280, #1670), plain-string and chunk-only search results are kept (#1683, #1693).
- pipecat: memory text stays literal when replacing the injected block (#1647), `InputParams` is exported from the package root (#1575).
- #1503 was hand-ported onto main's newer middleware. #1751 is left out: the v5 agent-framework migration (#1786) appends to the conversation document by design.
Co-Authored-By: abhinav7x94 <204053250+abhinav7x94@users.noreply.github.com>
Co-Authored-By: shamAnimates <145093437+shamAnimates@users.noreply.github.com>
Co-Authored-By: aloktripathi1 <142301030+aloktripathi1@users.noreply.github.com>
Co-Authored-By: Cintu07 <178455858+Cintu07@users.noreply.github.com>
Co-Authored-By: Atharvsinh-codez <201381760+Atharvsinh-codez@users.noreply.github.com>
Co-Authored-By: abhay-codes07 <182421137+abhay-codes07@users.noreply.github.com>
Co-Authored-By: nkootstra <545768+nkootstra@users.noreply.github.com>
Co-Authored-By: Agnik47 <140933190+Agnik47@users.noreply.github.com>
## Stack Context
Part 2 of a 3-PR stack moving memory deduplication into the SDKs. See `sdk-dedup/tools-ts` (parent) for the full context and the TypeScript implementation this mirrors.
## What?
Port the normalized, priority-ordered (`static > dynamic > search`) profile deduplication into the Python SDKs.
- Each request injects one **owned memory block that replaces** the prior block rather than accumulating.
- Dedup is **request-local** (no shared state), so it stays correct under concurrency.
Covers OpenAI, Agent Framework (middleware + context provider), Cartesia, and Pipecat.
## Why?
Keeps the Python SDKs at behavioral parity with the TypeScript SDK so all integrations deduplicate memory the same way.
## Testing
- OpenAI: 31 passed, 11 skipped (live)
- Agent Framework: 59 passed
- Cartesia: 8 passed
- Pipecat: 8 passed
🤖 Generated with [Claude Code](https://claude.com/claude-code)
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Medium Risk**
> Changes memory formatting and system-prompt injection across multiple SDK integrations; incorrect dedup or replacement could alter LLM context, but there is no auth or data-store risk.
>
> **Overview**
> Ports **normalized cross-source memory deduplication** and **replace-not-append injection** into the Python OpenAI, Agent Framework, Cartesia, and Pipecat packages so they match the TypeScript SDK behavior.
>
> **Deduplication** uses request-local keys: strip optional `[YYYY-MM-DD]` prefixes, normalize whitespace, and compare with `casefold`, with priority **static → dynamic → search**. In **`query` mode**, profile static/dynamic are excluded from dedup input so facts that only appear in search (or overlap profile) are not dropped before formatting.
>
> **Injection** no longer appends memory text every turn. OpenAI and Agent Framework middleware **strip prior owned `<supermemory context="user-memories" readonly>` blocks** and **replace** them once per request while keeping the caller’s system instructions; extra system messages lose stale blocks only. New helpers (`strip`/`replace`/`wrap`) live in each package’s utils.
>
> Tests cover normalized fact variants, query-mode search retention, and stale block replacement.
>
> <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit 42f308b224. Bugbot is set up for automated code reviews on this repo. Configure [here](https://www.cursor.com/dashboard/bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
## Summary
- Expand `SupermemoryTools` from 2 tools to 7 (matches `@supermemory/tools`)
- Add `memory_forget` via shared HTTP helper
- Add document list/add/delete and get_profile tool surfaces
- Expand tests for new tools and execution paths
Stacked on #1429
## Test plan
- [x] `uv run pytest tests/test_tools.py::TestMemoryOperationsUnit`
Made with [Cursor](https://cursor.com)
## Summary
- Replace deprecated `search.execute` with `search.memories` (hybrid mode) in `search_memories`
- Replace `memories.add` with `client.add` in tools and middleware
- Fix middleware `container_tag` param (was incorrectly `container_tags`)
- Fix profile memory deduplication for string and Pydantic API items
- Bump `supermemory>=3.50` and `requires-python>=3.9`
## Test plan
- [x] `uv run pytest tests/test_tools.py::TestMemoryOperationsUnit`
Made with [Cursor](https://cursor.com)
