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- anthropic: remove claude-3.5-sonnet (superseded by 4.x)
- openai: remove gpt-4o/4-turbo/3.5/o1/o3-mini (superseded by gpt-5/4.1/o3/o4-mini)
- gemini: remove 1.5-*/2.0-flash (superseded by 2.5/3.x)
- deepseek: remove coder/chat-v3-0324 (superseded by r1/v3)
- qwen: remove turbo/2.5-coder (superseded by qwen3)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- xai: remove grok-2 (superseded by grok-3/4)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

@@ -1,5 +1,5 @@
 # OpenAI — https://openai.com
-# Models: 18 (including 2 Codex variants)
+# Models: 13 (including 2 Codex variants)
 
 [provider]
 id = "openai"
@@ -9,32 +9,6 @@ base_url = "https://api.openai.com/v1"
 key_required = true
 media_capabilities = ["image_generation", "text_to_speech"]
 
-[[models]]
-id = "gpt-4o"
-display_name = "GPT-4o"
-tier = "smart"
-context_window = 128000
-max_output_tokens = 16384
-input_cost_per_m = 2.50
-output_cost_per_m = 10.0
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = ["gpt4", "gpt4o"]
-
-[[models]]
-id = "gpt-4o-mini"
-display_name = "GPT-4o Mini"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 16384
-input_cost_per_m = 0.15
-output_cost_per_m = 0.60
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = ["gpt4-mini"]
-
 [[models]]
 id = "gpt-4.1"
 display_name = "GPT-4.1"
@@ -88,20 +62,6 @@ supports_streaming = true
 supports_thinking = true
 aliases = []
 
-[[models]]
-id = "o3-mini"
-display_name = "o3-mini"
-tier = "smart"
-context_window = 200000
-max_output_tokens = 100000
-input_cost_per_m = 1.10
-output_cost_per_m = 4.40
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-supports_thinking = true
-aliases = []
-
 [[models]]
 id = "o4-mini"
 display_name = "o4-mini"
@@ -116,32 +76,6 @@ supports_streaming = true
 supports_thinking = true
 aliases = []
 
-[[models]]
-id = "gpt-4-turbo"
-display_name = "GPT-4 Turbo"
-tier = "smart"
-context_window = 128000
-max_output_tokens = 4096
-input_cost_per_m = 10.00
-output_cost_per_m = 30.00
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "gpt-3.5-turbo"
-display_name = "GPT-3.5 Turbo"
-tier = "fast"
-context_window = 16385
-max_output_tokens = 4096
-input_cost_per_m = 0.5
-output_cost_per_m = 1.5
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "gpt-5"
 display_name = "GPT-5"