fix(python-sdks): v4 API migration for integration packages by Dhravya · Pull Request #1434 · supermemoryai/supermemory

Dhravya · 2026-08-08T02:40:01Z

Summary

agent-framework: proactive search tool descriptions
cartesia / pipecat: v4 client.add + hybrid search, dedupe fixes, tests

Stacked on #1433

Test plan

pytest in agent-framework, cartesia, pipecat packages

Made with Cursor

…4 APIs Use client.add and search.memories hybrid mode, improve profile memory deduplication for string/pydantic items, and add dedupe unit tests. Co-authored-by: Cursor <cursoragent@cursor.com>

claude · 2026-08-08T02:40:22Z

Claude finished @ved015's task in 1m 59s —— View job

Code Review Complete

Fetch PR diff and existing review comments
Analyze changes for bugs, security issues, and logic errors
Submit review findings

Result: No new issues found. The two issues previously flagged by Cursor Bugbot have been addressed in subsequent commits. PR scores 9/10 — ready to ship.

cloudflare-workers-and-pages · 2026-08-08T02:42:14Z

Deploying with Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Updated (UTC)
✅ Deployment successful! View logs	supermemory-mcp	`5462e20`	Aug 24 2026, 04:27 PM

cloudflare-workers-and-pages · 2026-08-08T02:47:40Z

Deploying with Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	supermemory-app	`5462e20`	Commit Preview URL Branch Preview URL	Aug 24 2026, 04:30 PM

Dhravya · 2026-08-08T02:47:51Z

Warning

This pull request is not mergeable via GitHub because a downstack PR is open. Once all requirements are satisfied, merge this PR as a stack on Graphite.
Learn more

How to use the Graphite Merge Queue

Add the label Main to this PR to add it to the merge queue.

You must have a Graphite account in order to use the merge queue. Sign up using this link.

_{An organization admin has enabled the Graphite Merge Queue in this repository.} _{Please do not merge from GitHub as this will restart CI on PRs being processed by the merge queue.}

This stack of pull requests is managed by Graphite. Learn more about stacking.

cursor

Cursor Bugbot has reviewed your changes using high effort and found 2 potential issues.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit c449b2f. Configure here.}

cursor · 2026-08-08T02:48:59Z

-                chunk_threshold=0.6,
-                include_full_docs=include_full_docs,
+                threshold=0.6,
+                search_mode="hybrid",


include_full_docs ignored

Medium Severity

The v4 migration stops passing include_full_docs to search.memories, but the tool still exposes that parameter with a default of True. Callers or agents that set include_full_docs=False get the same hybrid search as when it is True, so documented tool behavior no longer matches runtime.

^{Reviewed by Cursor Bugbot for commit c449b2f. Configure here.}

cursor · 2026-08-08T02:48:59Z

+        # Stainless SDK returns pydantic models (attribute access, snake_case).
+        memory = getattr(item, "memory", None)
+        if isinstance(memory, str):
+            trimmed = memory.strip()


Dedupe drops chunk-only hits

Medium Severity

extract_memory_text only reads the memory field on dicts and SDK models. Hybrid v4 results that populate chunk or content instead (as cartesia/pipecat handle in this PR) are treated as empty and dropped from deduplicated search output used by middleware and context providers.

^{Reviewed by Cursor Bugbot for commit c449b2f. Configure here.}

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

claude

Overview: Migrates agent-framework, cartesia, and pipecat Python SDKs to the v4 Supermemory API, switching from search.execute to search.memories with hybrid search, updating memory storage to use client.add, and hardening deduplication to handle v4's chunk/content response fields.

Issues found: None — this looks good to ship.

The two issues flagged by Cursor Bugbot have been addressed in subsequent commits:

include_full_docs ignored ✅ Fixed — The parameter is now Optional[bool] = None with a deprecation warning, and the model-facing tool (_search_memories_tool) properly omits it. The README documents the deprecation.
Dedupe drops chunk-only hits ✅ Fixed — All three packages now check ("memory", "chunk", "content") fields when extracting text from v4 search results.

Notable improvements in this PR:

Consistent _field() helper across cartesia/pipecat for reading dict or pydantic model fields
Date-prefix normalization in deduplication prevents false duplicates between profile and search results
Pipecat storage queue with retry-on-failure and proper cleanup drain
Cartesia per-turn context injection with legacy fallback for older Line versions

Score: 9/10

Minor observation: The unbounded storage queue in pipecat could grow during sustained API failures, but this is a reasonable tradeoff to avoid data loss.

claude

Overview: Migrates agent-framework, cartesia, and pipecat Python SDKs to the v4 Supermemory API, switching from search.execute to search.memories with hybrid search, updating memory storage to use client.add, and hardening deduplication to handle v4's chunk/content response fields.

Issues found: None — this looks good to ship.

The two issues flagged by Cursor Bugbot have been addressed in subsequent commits:

include_full_docs ignored ✅ Fixed — The parameter is now Optional[bool] = None with a deprecation warning at tools.py:97-103, and the model-facing tool (_search_memories_tool at line 212) properly omits it. The README documents the deprecation.
Dedupe drops chunk-only hits ✅ Fixed — All three packages now check ("memory", "chunk", "content") fields when extracting text from v4 search results (e.g., utils.py:100-109 in agent-framework).

Notable improvements in this PR:

Consistent _field() helper across cartesia/pipecat for reading dict or pydantic model fields
Date-prefix normalization in deduplication prevents false duplicates between profile and search results
Pipecat storage queue with retry-on-failure and proper cleanup drain via _drain_storage_queue()
Cartesia per-turn context injection with legacy fallback for older Line versions via _agent_accepts_context()
OpenAI middleware now properly threads sync client.add calls and adds timeout/redirect handling

Score: 9/10

Minor observation: The unbounded storage queue in pipecat (_storage_queue: deque) could grow during sustained API failures, but this is a reasonable tradeoff to avoid data loss. The _drain_storage_queue() method provides graceful cleanup at teardown.

claude

Overview: Migrates agent-framework, cartesia, and pipecat Python SDKs to the v4 Supermemory API, switching from search.execute to search.memories with hybrid search, updating memory storage to use client.add, and hardening deduplication to handle v4's chunk/content response fields.

Issues found: None — this looks good to ship.

The two issues flagged by Cursor Bugbot have been addressed in subsequent commits:

include_full_docs ignored ✅ Fixed — The parameter is now Optional[bool] = None with a deprecation warning at tools.py:97-103, and the model-facing tool (_search_memories_tool at line 212) properly omits it. The README documents the deprecation.
Dedupe drops chunk-only hits ✅ Fixed — All three packages now check ("memory", "chunk", "content") fields when extracting text from v4 search results (e.g., utils.py:100-109 in agent-framework, cartesia's _field() helper at utils.py:50-67, pipecat's equivalent at utils.py:57-73).

Notable improvements:

Consistent _field() helper across cartesia/pipecat for reading dict or pydantic model fields
Date-prefix normalization in deduplication prevents false duplicates between profile and search results
Pipecat storage queue with retry-on-failure and proper cleanup drain via _drain_storage_queue()
Cartesia per-turn context injection with legacy fallback for older Line versions via _agent_accepts_context()
OpenAI middleware properly threads sync client.add calls via asyncio.to_thread and adds timeout/redirect handling
CI workflows pinned to commit SHAs and test against minimum/current dependency versions

Score: 9/10

Minor observation: The unbounded storage queue in pipecat (_storage_queue: deque) could grow during sustained API failures, but this is a reasonable tradeoff to avoid data loss and the _drain_storage_queue() method provides graceful cleanup at teardown.

fix(python-sdks): migrate agent-framework, cartesia, and pipecat to v…

c449b2f

…4 APIs Use client.add and search.memories hybrid mode, improve profile memory deduplication for string/pydantic items, and add dedupe unit tests. Co-authored-by: Cursor <cursoragent@cursor.com>

graphite-app Bot assigned Dhravya Aug 8, 2026

Dhravya mentioned this pull request Aug 8, 2026

docs(skills): refresh Supermemory skill for 7-tool parity #1435

Open

1 task

Dhravya force-pushed the fix/python-sdks-v4-api branch from 2b9934b to c449b2f Compare August 8, 2026 02:47

This was referenced Aug 8, 2026

fix(openai-sdk-python): migrate to v4 Supermemory APIs #1429

Open

feat(openai-sdk-python): 7-tool parity #1430

Open

chore(ci): Python SDK pytest workflow #1431

Open

This was referenced Aug 8, 2026

feat(tools): 7-tool parity and description refresh #1432

Open

feat(ai-sdk): re-export 7-tool surface #1433

Open

chore(ci): wire JS tools unit tests into CI #1436

Open

feat(sdk-playground): interactive SDK chat playground #1437

Open

cursor Bot reviewed Aug 8, 2026

View reviewed changes

Dhravya force-pushed the fix/python-sdks-v4-api branch from ce503a4 to c449b2f Compare August 18, 2026 15:18

This was referenced Aug 18, 2026

feat(tools): SDK-level cross-source memory deduplication #1531

Open

feat(python-sdks): SDK-level cross-source memory deduplication #1532

Open

feat(sdk-playground): reflect SDK-owned memory block in debug view #1533

Open

chore: update bun.lock for v4 SDK dependencies

4b41cba

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Dhravya assigned ved015 Aug 18, 2026

Dhravya requested a review from MaheshtheDev August 18, 2026 15:20

fix(python-sdks): harden v4 integrations

903d78e

claude Bot reviewed Aug 23, 2026

View reviewed changes

ved015 added 3 commits August 23, 2026 20:03

chore: merge latest stacked SDK fixes

9f5decb

fix(openai-sdk-python): harden middleware requests

6180c04

chore: merge latest stacked SDK fixes

80ccb5c

claude Bot reviewed Aug 24, 2026

View reviewed changes

Merge branch 'feat/ai-sdk-tool-reexports' into fix/python-sdks-v4-api

5462e20

ved015 approved these changes Aug 24, 2026

View reviewed changes

claude Bot reviewed Aug 24, 2026

View reviewed changes

Navigation Menu

Uh oh!

fix(python-sdks): v4 API migration for integration packages - #1434

fix(python-sdks): v4 API migration for integration packages#1434
Dhravya wants to merge 7 commits into
feat/ai-sdk-tool-reexportsfrom
fix/python-sdks-v4-api

Dhravya commented Aug 8, 2026

Uh oh!

claude Bot commented Aug 8, 2026 •

edited

Loading

Uh oh!

cloudflare-workers-and-pages Bot commented Aug 8, 2026 •

edited

Loading

Uh oh!

cloudflare-workers-and-pages Bot commented Aug 8, 2026 •

edited

Loading

Uh oh!

Dhravya commented Aug 8, 2026 •

edited

Loading

Uh oh!

cursor Bot left a comment

Uh oh!

cursor Bot Aug 8, 2026

Uh oh!

cursor Bot Aug 8, 2026

Uh oh!

claude Bot left a comment

Uh oh!

claude Bot left a comment

Uh oh!

claude Bot left a comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

Dhravya commented Aug 8, 2026

Summary

Test plan

Uh oh!

claude Bot commented Aug 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Code Review Complete

Uh oh!

cloudflare-workers-and-pages Bot commented Aug 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Deploying with Cloudflare Workers

Uh oh!

cloudflare-workers-and-pages Bot commented Aug 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Deploying with Cloudflare Workers

Uh oh!

Dhravya commented Aug 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

How to use the Graphite Merge Queue

Uh oh!

cursor Bot left a comment

Choose a reason for hiding this comment

Uh oh!

cursor Bot Aug 8, 2026

Choose a reason for hiding this comment

include_full_docs ignored

Uh oh!

cursor Bot Aug 8, 2026

Choose a reason for hiding this comment

Dedupe drops chunk-only hits

Uh oh!

claude Bot left a comment

Choose a reason for hiding this comment

Uh oh!

claude Bot left a comment

Choose a reason for hiding this comment

Uh oh!

claude Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

claude Bot commented Aug 8, 2026 •

edited

Loading

cloudflare-workers-and-pages Bot commented Aug 8, 2026 •

edited

Loading

cloudflare-workers-and-pages Bot commented Aug 8, 2026 •

edited

Loading

Dhravya commented Aug 8, 2026 •

edited

Loading