Llm-gemini

- Now depends on LLM 0.22, adding support for the new `model.prompt(..., key="key")` parameter. 46
- Fixed error with `-o google_search 1` option by switching the underlying tool from `google_search_retrieval` to `google_search`. Thanks, [Sebastian Rojo](https://github.com/arpagon). #39
- Added `gemini-2.0-flash` to the list of models that support `-o google_search 1`. Thanks, [Martin Trojer](https://github.com/martintrojer). #44

Three new Gemini 2.0 models: 43

- `gemini-2.0-flash` - Gemini 2.0 Flash
- `gemini-2.0-flash-lite-preview-02-05` - Gemini 2.0 Flash-Lite
- `gemini-2.0-pro-exp-02-05` - experimental release of Gemini 2.0 Pro

- Added support for grounding prompts against Google search using the new `-o google_search 1` option. Thanks, [Ricardo Mestre](https://github.com/ricmestre). #29
- Added support for `text/plain` and `text/csv` attachments. Thanks, [Michele Gregori](https://github.com/miclegr). #34
- Fixed bug handling `application/ogg` attachments. 35
- New model: `learnlm-1.5-pro-experimental`. Thanks, [Leonard Tulipan](https://github.com/leotulipan). #36
- New model: `gemini-2.0-flash-thinking-exp-01-21`. 37

- Support for [Gemini 2.0 Flash Thinking Mode](https://ai.google.dev/gemini-api/docs/thinking-mode) experimental model: `llm -m gemini-2.0-flash-thinking-exp-1219 "Solve 3*x^3-5*x=1"`. #31
- Fixed bug with async models used in conversations. Thanks, Sukhbinder Singh. 30

- New [Gemini 2.0 Flash](https://blog.google/technology/google-deepmind/google-gemini-ai-update-december-2024/#gemini-2-0-flash) model: `llm -m gemini-2.0-flash-exp 'prompt goes here'`. 28

- New model: `gemini-exp-1206`. 27