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- anthropic: remove claude-3.5-sonnet (superseded by 4.x)
- openai: remove gpt-4o/4-turbo/3.5/o1/o3-mini (superseded by gpt-5/4.1/o3/o4-mini)
- gemini: remove 1.5-*/2.0-flash (superseded by 2.5/3.x)
- deepseek: remove coder/chat-v3-0324 (superseded by r1/v3)
- qwen: remove turbo/2.5-coder (superseded by qwen3)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- xai: remove grok-2 (superseded by grok-3/4)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/groq.toml

@@ -1,5 +1,5 @@
 # Groq — https://groq.com
-# Models: 10
+# Models: 3
 
 [provider]
 id = "groq"
@@ -22,96 +22,18 @@ supports_streaming = true
 aliases = ["llama", "llama-70b"]
 
 [[models]]
-id = "llama-3.1-8b-instant"
-display_name = "Llama 3.1 8B"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.05
-output_cost_per_m = 0.08
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "llama-3.2-90b-vision-preview"
-display_name = "Llama 3.2 90B Vision"
-tier = "smart"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.90
-output_cost_per_m = 0.90
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "llama-3.2-11b-vision-preview"
-display_name = "Llama 3.2 11B Vision"
+id = "meta-llama/llama-4-scout-17b-16e-instruct"
+display_name = "Llama 4 Scout 17B"
 tier = "balanced"
 context_window = 128000
 max_output_tokens = 8192
-input_cost_per_m = 0.18
-output_cost_per_m = 0.18
+input_cost_per_m = 0.11
+output_cost_per_m = 0.34
 supports_tools = true
 supports_vision = true
 supports_streaming = true
 aliases = []
 
-[[models]]
-id = "llama-3.2-3b-preview"
-display_name = "Llama 3.2 3B"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.06
-output_cost_per_m = 0.06
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "llama-3.2-1b-preview"
-display_name = "Llama 3.2 1B"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.04
-output_cost_per_m = 0.04
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "mixtral-8x7b-32768"
-display_name = "Mixtral 8x7B"
-tier = "balanced"
-context_window = 32768
-max_output_tokens = 4096
-input_cost_per_m = 0.024
-output_cost_per_m = 0.024
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["mixtral"]
-
-[[models]]
-id = "gemma2-9b-it"
-display_name = "Gemma 2 9B"
-tier = "fast"
-context_window = 8192
-max_output_tokens = 4096
-input_cost_per_m = 0.02
-output_cost_per_m = 0.02
-supports_tools = false
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "qwen-qwq-32b"
 display_name = "Qwen QWQ 32B"
@@ -125,16 +47,3 @@ supports_vision = false
 supports_streaming = true
 supports_thinking = true
 aliases = []
-
-[[models]]
-id = "meta-llama/llama-4-scout-17b-16e-instruct"
-display_name = "Llama 4 Scout 17B"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.11
-output_cost_per_m = 0.34
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []