Fix: Flatten results from update_community calls

[ZLBillShaw]

Summary

Fixed ValueError when update_communities=True is passed to add_episode(). The bug was caused by incorrect unpacking of semaphore_gather results, which returns a list of tuples rather than a single tuple.

Type of Change

• [x] Bug fix
• [ ] New feature
• [ ] Performance improvement
• [ ] Documentation/Tests

Objective

Fix the ValueError: not enough values to unpack (expected 2, got 1) error that occurs when calling add_episode() with update_communities=True.

Root Cause: In graphiti.py lines 781-787, the code attempts to directly unpack semaphore_gather results:

communities, community_edges = await semaphore_gather(
    *[update_community(self.driver, self.llm_client, self.embedder, node) for node in nodes],
    max_coroutines=self.max_coroutines,
)

However, semaphore_gather returns a list of tuples, not a single tuple:
[(communities, edges), (communities, edges), ...]

[danielchalef]

All contributors have signed the CLA ✍️ ✅
_{Posted by the CLA Assistant Lite bot.}

[ZLBillShaw]

I have read the CLA Document and I hereby sign the CLA