v4.1.1

This is a patch release to address few regressions from the last release and the upcoming Gemma4, most importantly:

- Fixes Gemma 4 tokenization with llama.cpp
- Show login in api key only mode
- Small fixes to improve Anthropic API compatibility

## What's Changed
### Other Changes
* docs: Update Home Assistant integrations list by @loryanstrant in https://github.com/mudler/LocalAI/pull/9206
* chore: :arrow_up: Update ggml-org/llama.cpp to `a1cfb645307edc61a89e41557f290f441043d3c2` by @localai-bot in https://github.com/mudler/LocalAI/pull/9203
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/9210
* chore: bump inference defaults from unsloth by @github-actions[bot] in https://github.com/mudler/LocalAI/pull/9219
* docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/9214
* chore: :arrow_up: Update ggml-org/llama.cpp to `d006858316d4650bb4da0c6923294ccd741caefd` by @localai-bot in https://github.com/mudler/LocalAI/pull/9215
* fix(ui): pass by staticApiKeyRequired to show login when only api key is configured by @mudler in https://github.com/mudler/LocalAI/pull/9220
* feat(gemma4): add thinking support by @mudler in https://github.com/mudler/LocalAI/pull/9221
* fix(nats): improve error handling by @mudler in https://github.com/mudler/LocalAI/pull/9222
* feat(autoparser): prefer chat deltas from backends when emitted by @mudler in https://github.com/mudler/LocalAI/pull/9224
* fix(anthropic): show null index when not present, default to 0 by @mudler in https://github.com/mudler/LocalAI/pull/9225
* feat(api): Allow coding agents to interactively discover how to control and configure LocalAI by @richiejp in https://github.com/mudler/LocalAI/pull/9084
* chore(refactor): use interface by @mudler in https://github.com/mudler/LocalAI/pull/9226
* fix(reasoning): accumulate and strip reasoning tags from autoparser results by @mudler in https://github.com/mudler/LocalAI/pull/9227
* chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/9233
* chore: :arrow_up: Update ggml-org/llama.cpp to `b8635075ffe27b135c49afb9a8b5c434bd42c502` by @localai-bot in https://github.com/mudler/LocalAI/pull/9231

## New Contributors
* @github-actions[bot] made their first contribution in https://github.com/mudler/LocalAI/pull/9219

**Full Changelog**: https://github.com/mudler/LocalAI/compare/v4.1.0...v4.1.1