docs: add langchain-distil to community middleware integrations

[Shakes (dshakes)]

Adds langchain-distil to the Community middleware integrations table.

It's a context-compression middleware in the same family as the existing compact-middleware and langchain-collapse entries: it reversibly digests large tool outputs and message history before the model call (tool/function messages reversibly, human/system losslessly, the model's own messages never rewritten), with byte-exact recovery of every digest. Decision-equivalence between compressed and full context is certified offline by a statistical non-inferiority gate.

• Package: https://pypi.org/project/langchain-distil/ (published, 0.1.0)
• Source: https://github.com/dshakes/distil

Single-row addition to the community table, matching the existing format. I'm the author.

[github-actions]

Thanks for opening a docs PR, Shakes (@dshakes)! When it's ready for review, please add the relevant reviewers:

• @mdrxy (Python integrations)