feat(kg): support local/OpenAI-compatible LLM endpoints

[bferanmi806-sketch]

Fixes #598. @keysersoft — implemented per your approved contract.

Contract compliance:

• Uses KG_LLM_BASE_URL (not AI_BASE_URL); optional KG_LLM_API_KEY (not AI_*); keeps using KG_LLM_MODEL.
• Base URL set → OpenAI-compatible request goes there; empty key valid (Ollama/LM Studio need none).
• Authorization: Bearer … only when a key exists (custom path); hosted paths byte-identical.
• No response_format on the custom endpoint — JSON instruction + existing parsing instead.
• Unusable local JSON → warn log with model + endpoint, return empty result so the enrichment/skill pass is skipped, not crashed.
• OpenAI/OpenRouter/Anthropic behaviour preserved when no base URL is set; batch stays Anthropic-only.

Tests: new llm-client.spec.ts (9/9 pass) — config resolution (custom routing, empty-key validity, model passthrough, slash trim, hosted unchanged) and request construction (no Authorization with empty key, Authorization with key, no response_format on custom, present on OpenAI, hosted parse errors still throw, custom parse failure resolves {json:{}}). eslint clean on touched files; llm-client.ts has zero tsc errors. (Pre-existing: repo-wide tsc and 5 prisma-dependent suites fail on clean tree too — generated Prisma client absent in this env.)

Docs: .env.example + docs/knowledge-graph.md updated; tested model named (qwen2.5).

Real local run (honest harness note: the Ollama binary download is blocked in this sandbox, so this ran Qwen2.5-0.5B-Instruct via llama.cpp behind a minimal /v1/chat/completions front — the identical request/response contract Ollama serves):

• resolved: {provider:custom, model:qwen2.5, apiKey:'', baseUrl:http://localhost:11435/v1}
• server saw: response_format=null auth=absent
• parsed: {relationships:[{from:e0, to:e1, kind:same_identity, confidence:0.9, reason:e0 is a person and e1 is a customer}]}

Happy to sign the CLA when the bot asks.

[github-actions]

Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution. You can sign the CLA by just posting a Pull Request Comment same as the below format.

---

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

---

Odunayo Balogun seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot.}

[github-actions]

👋 Welcome, @bferanmi806-sketch, and thanks for opening your first PR on AnythingMCP!

A few quick pointers:

• Make sure CI is green before requesting review (Backend, Frontend, Playwright, CodeQL, Trivy).
• If this is a new adapter, the parametrised catalog.spec.ts test will validate it automatically.
• Sign off your commits if you can — it's not blocking, just nice to have.

Someone from the core team will look at this within ~48h. If you don't hear back, please ping us in Discussions / Q&A.

⭐ While you wait — if you find AnythingMCP useful, a star helps others discover it.