feat(providers): expand ollama catalog with thinking-capable models (#58)

* feat(providers): expand ollama model catalog with thinking-capable models

Add commonly used local models with accurate capability flags:
- gemma4, gemma3: supports_thinking, supports_vision
- deepseek-r1: supports_thinking (fix missing flag)
- deepseek-v3: supports_tools
- qwen3, qwq: supports_thinking
- llama4: supports_vision
- llama3.3: supports_tools
- phi4: supports_tools

Previously only 6 models were listed and none had supports_thinking
(except deepseek-r1), causing the dashboard to hide thinking toggles
for models that actually support it.

* chore(providers): major cleanup — remove defunct providers and old models

Delete 21 defunct/obscure providers:
aion-labs, arcee-ai, deepcogito, eleutherai, essentialai, ibm-granite,
inception, inflection, kwaipilot, lemonade, liquid, morph, nex-agi,
nousresearch, prime-intellect, reka, relace, switchpoint, tngtech,
upstage, writer

Clean up 10 major providers — keep only latest generation models:
- anthropic: remove claude-3.5-sonnet (superseded by 4.x)
- openai: remove gpt-4o/4-turbo/3.5/o1/o3-mini (superseded by gpt-5/4.1/o3/o4-mini)
- gemini: remove 1.5-*/2.0-flash (superseded by 2.5/3.x)
- deepseek: remove coder/chat-v3-0324 (superseded by r1/v3)
- qwen: remove turbo/2.5-coder (superseded by qwen3)
- groq: remove old llama/mixtral/gemma (keep latest only)
- mistral: remove medium/nemo/pixtral-large (keep large/small/codestral)
- xai: remove grok-2 (superseded by grok-3/4)
- meta-llama: remove 3.x/guard (keep llama-4 + 3.3)
- ollama: rewrite with current models (gemma4, qwen3, qwq, llama4, etc)

Total: 90 → 48 models across major providers. All thinking-capable
models now have supports_thinking = true.

* chore: add pre-commit hook for automatic TOML formatting

- .githooks/pre-commit: runs taplo fmt on staged .toml files
- Makefile: add setup target + auto-configure hooks on first make
- .gitignore: add .make-setup-done and .sync_marker

providers/ollama.toml

@@ -1,5 +1,5 @@
 # Ollama — https://ollama.com
-# Models: 6 (static entries; additional models discovered dynamically at runtime)
+# Current-generation models only. Additional models are discovered dynamically at runtime.
 
 [provider]
 id = "ollama"
@@ -9,80 +9,96 @@ base_url = "http://localhost:11434/v1"
 key_required = false
 
 [[models]]
-id = "llama3.2"
-display_name = "Llama 3.2 (Ollama)"
+id = "gemma4"
+display_name = "Gemma 4"
 tier = "local"
 context_window = 128000
-max_output_tokens = 4096
+max_output_tokens = 8192
 input_cost_per_m = 0.0
 output_cost_per_m = 0.0
 supports_tools = true
-supports_vision = false
+supports_vision = true
 supports_streaming = true
-aliases = []
-
-[[models]]
-id = "llama3.1"
-display_name = "Llama 3.1 (Ollama)"
-tier = "local"
-context_window = 128000
-max_output_tokens = 4096
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "mistral:latest"
-display_name = "Mistral (Ollama)"
-tier = "local"
-context_window = 32768
-max_output_tokens = 4096
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "qwen2.5"
-display_name = "Qwen 2.5 (Ollama)"
-tier = "local"
-context_window = 32768
-max_output_tokens = 4096
-input_cost_per_m = 0.2
-output_cost_per_m = 0.6
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "phi3"
-display_name = "Phi-3 (Ollama)"
-tier = "local"
-context_window = 128000
-max_output_tokens = 4096
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_tools = false
-supports_vision = false
-supports_streaming = true
-aliases = []
+supports_thinking = true
+aliases = ["gemma4:latest"]
 
 [[models]]
 id = "deepseek-r1:latest"
-display_name = "DeepSeek R1 (Ollama)"
+display_name = "DeepSeek R1"
 tier = "local"
 context_window = 64000
-max_output_tokens = 4096
+max_output_tokens = 8192
 input_cost_per_m = 0.0
 output_cost_per_m = 0.0
 supports_tools = false
 supports_vision = false
 supports_streaming = true
 supports_thinking = true
+aliases = ["deepseek-r1"]
+
+[[models]]
+id = "qwen3"
+display_name = "Qwen 3"
+tier = "local"
+context_window = 40960
+max_output_tokens = 8192
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+supports_thinking = true
+aliases = ["qwen3:latest"]
+
+[[models]]
+id = "qwq"
+display_name = "QwQ"
+tier = "local"
+context_window = 40960
+max_output_tokens = 8192
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+supports_thinking = true
+aliases = ["qwq:latest"]
+
+[[models]]
+id = "llama4"
+display_name = "Llama 4"
+tier = "local"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["llama4:latest"]
+
+[[models]]
+id = "mistral:latest"
+display_name = "Mistral"
+tier = "local"
+context_window = 32768
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
 aliases = []
+
+[[models]]
+id = "phi4"
+display_name = "Phi-4"
+tier = "local"
+context_window = 16384
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["phi4:latest"]