feat: add Abliteration.ai as an LLM provider

[abliteration-ai]

Description

Adds Abliteration.ai as a first-class provider. Abliteration.ai is an inference API for less-restrictive, uncensored models behind an OpenAI-compatible API (https://api.abliteration.ai/v1), currently hosting abliterated-model (multimodal, 256K context) and abliterated-model-large (1M context).

Changes:

• New LLM class core/llm/llms/Abliteration.ts (extends OpenAI, sets apiBase and default model)
• Registered in core/llm/llms/index.ts, packages/openai-adapters (types + constructLlmApi), and packages/config-types
• Added to PROVIDER_HANDLES_TEMPLATING, PROVIDER_SUPPORTS_IMAGES, and PARALLEL_PROVIDERS in core/llm/autodetect.ts
• Added to the VS Code extension config_schema.json
• Added to the GUI provider selection with AUTODETECT
• New docs page docs/customize/model-providers/more/abliteration.mdx with YAML/JSON config examples, plus docs.json nav and overview table entries

AI Code Review

• Team members only: AI review runs automatically when PR is opened or marked ready for review
• Team members can also trigger a review by commenting @continue-review

Checklist

• I've read the contributing guide
• The relevant docs, if any, have been updated or created
• The relevant tests, if any, have been updated or created

Screen recording or screenshot

N/A — configuration-only provider addition, mirroring the recent Tensorix provider PR (#11184).

Tests

No new tests added (provider is a thin OpenAI subclass, same as Tensorix and other OpenAI-compatible providers). Verified locally:

• npm run tsc:check in core — clean
• tsc build in packages/openai-adapters and packages/config-types — clean
• tsc --noEmit in gui — clean
• npx vitest run llm in core — 465 tests passed
• npx vitest run in packages/openai-adapters — 145 tests passed
• jest llm/llms/OpenAI.test.ts llm/toolSupport.test.ts in core — 75 tests passed

[github-actions]

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

[abliteration-ai]

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

[abliteration-ai]

Note on CI: the jetbrains-tests failure (Autocomplete > testAutocomplete()) appears to be a pre-existing upstream issue rather than something from this change — the same test fails identically on other recent PRs (e.g. runs #30687337458 and #30615511535), and this PR doesn't touch the JetBrains extension or autocomplete code paths. All other checks (core-checks, e2e, vsix builds, binary-checks) are green.