haylan 47bdb22457 docs: record issue #24's smoke-test findings and local litellm-pgvector patches ...

memory-knowledgebase.md no longer says 'not yet verified' — it's been
smoke-tested end-to-end (direct search + the file_search tool on a chat
completion) and the bugs found are fixed in the preceding commits.
VENDORED.md documents the three local patches on top of the upstream
litellm-pgvector commit so a future re-vendor doesn't silently drop them.

2026-09-02 21:32:38 +00:00

..

agents

Set up agent skills config and chart wayfinder map for local AI stack

2026-08-24 12:13:21 +02:00

research

docs(research): LangChain+pgvector-direct vs litellm-pgvector for issue #25

2026-09-02 22:02:58 +02:00

coding-cli-setup.md

Migrate Open WebUI and coding CLIs to the AI proxy (resolves #15)

2026-08-25 07:18:03 +02:00

memory-knowledgebase.md

docs: record issue #24's smoke-test findings and local litellm-pgvector patches

2026-09-02 21:32:38 +00:00

network-access.md

Document AI proxy network exposure plan (resolves #13)

2026-08-25 07:05:01 +02:00

proxy-key-onboarding.md

fix(docs): update stale MEMORY_RETRIEVAL_EMBEDDING_KEY refs after litellm-pgvector revert

2026-09-02 22:46:10 +02:00

proxy-request-priority.md

Document AI proxy request priority/queueing plan (resolves #16)

2026-08-25 07:07:20 +02:00

server-planing.md

Add build plan documentation for 4x Radeon AI PRO R9700 rackmount LLM server

2026-08-25 07:20:58 +02:00