kartik-mem0 2b8e4ea059 fix(llms/lmstudio): honor LMSTUDIO_BASE_URL in the LLM too ...

The embedder fix in this branch left the sibling LLM still hardcoded, so
a self-hosted LM Studio behind a non-default host worked for embeddings
and silently fell back to localhost for generation.

LMStudioConfig baked "http://localhost:1234/v1" into __init__, which
makes any env-var lookup downstream dead code. The field now defaults to
None and LMStudioLLM resolves config value, then LMSTUDIO_BASE_URL, then
the localhost default, matching the embedder and DeepSeek.

2026-08-13 19:45:57 +05:30

..

client

feat(sdk, docs): expose agent_custom_instructions for agent-scoped extraction (#6809)

2026-08-05 22:12:10 +05:30

configs

fix(llms/lmstudio): honor LMSTUDIO_BASE_URL in the LLM too

2026-08-13 19:45:57 +05:30

embeddings

fix(embeddings/lmstudio): honor LMSTUDIO_BASE_URL env var

2026-08-13 17:36:59 +05:30

llms

fix(llms/lmstudio): honor LMSTUDIO_BASE_URL in the LLM too

2026-08-13 19:45:57 +05:30

memory

fix(memory): escape delimiters when building the session scope key (#6892)

2026-08-11 23:23:55 +05:30

proxy

fix: replace mutable default arguments with None sentinels (B006) (#5302)

2026-06-04 18:53:03 +05:30

reranker

fix: OSS Python SDK hygiene batch, 9 small bug fixes (#6770)

2026-08-03 20:36:28 +05:30

utils

fix: OSS Python SDK hygiene batch, 9 small bug fixes (#6770)

2026-08-03 20:36:28 +05:30

vector_stores

fix(pgvector): raise ValueError when 'in'/'nin' filter value is not a list (#6879)

2026-08-11 20:15:07 +05:30

__init__.py

chore: trigger Mintlify redeploy for #5152 docs (#5185)

2026-05-18 16:22:48 +05:30

exceptions.py

fix: align default model names with SDK defaults (#6704)

2026-08-01 01:30:57 +05:30