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- anthropic: remove claude-3.5-sonnet (superseded by 4.x)
- openai: remove gpt-4o/4-turbo/3.5/o1/o3-mini (superseded by gpt-5/4.1/o3/o4-mini)
- gemini: remove 1.5-*/2.0-flash (superseded by 2.5/3.x)
- deepseek: remove coder/chat-v3-0324 (superseded by r1/v3)
- qwen: remove turbo/2.5-coder (superseded by qwen3)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- xai: remove grok-2 (superseded by grok-3/4)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

@@ -1,4 +1,5 @@
-# meta-llama — auto-generated from OpenRouter API
+# meta-llama — https://llama.com
+# Models: 5
 
 [provider]
 id = "meta-llama"
@@ -7,106 +8,6 @@ api_key_env = "LLAMA_API_KEY"
 base_url = "https://api.llama.com/v1"
 key_required = true
 
-[[models]]
-id = "llama-3-70b-instruct"
-display_name = "Meta: Llama 3 70B Instruct"
-tier = "smart"
-context_window = 8192
-max_output_tokens = 8000
-input_cost_per_m = 0.51
-output_cost_per_m = 0.74
-supports_streaming = true
-
-[[models]]
-id = "llama-3-8b-instruct"
-display_name = "Meta: Llama 3 8B Instruct"
-tier = "fast"
-context_window = 8192
-max_output_tokens = 16384
-input_cost_per_m = 0.03
-output_cost_per_m = 0.04
-supports_streaming = true
-
-[[models]]
-id = "llama-3.1-70b-instruct"
-display_name = "Meta: Llama 3.1 70B Instruct"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 0.4
-output_cost_per_m = 0.4
-supports_streaming = true
-
-[[models]]
-id = "llama-3.1-8b-instruct"
-display_name = "Meta: Llama 3.1 8B Instruct"
-tier = "fast"
-context_window = 16384
-max_output_tokens = 16384
-input_cost_per_m = 0.02
-output_cost_per_m = 0.05
-supports_streaming = true
-
-[[models]]
-id = "llama-3.2-11b-vision-instruct"
-display_name = "Meta: Llama 3.2 11B Vision Instruct"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 0.245
-output_cost_per_m = 0.245
-supports_streaming = true
-
-[[models]]
-id = "llama-3.2-1b-instruct"
-display_name = "Meta: Llama 3.2 1B Instruct"
-tier = "fast"
-context_window = 60000
-max_output_tokens = 15000
-input_cost_per_m = 0.027
-output_cost_per_m = 0.2
-supports_streaming = true
-
-[[models]]
-id = "llama-3.2-3b-instruct"
-display_name = "Meta: Llama 3.2 3B Instruct"
-tier = "fast"
-context_window = 80000
-max_output_tokens = 16384
-input_cost_per_m = 0.051
-output_cost_per_m = 0.34
-supports_streaming = true
-
-[[models]]
-id = "llama-3.2-3b-instruct:free"
-display_name = "Meta: Llama 3.2 3B Instruct (free)"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_streaming = true
-
-[[models]]
-id = "llama-3.3-70b-instruct"
-display_name = "Meta: Llama 3.3 70B Instruct"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 0.1
-output_cost_per_m = 0.32
-supports_streaming = true
-
-[[models]]
-id = "llama-3.3-70b-instruct:free"
-display_name = "Meta: Llama 3.3 70B Instruct (free)"
-tier = "fast"
-context_window = 65536
-max_output_tokens = 16384
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_streaming = true
-
 [[models]]
 id = "llama-4-maverick"
 display_name = "Meta: Llama 4 Maverick"
@@ -128,8 +29,8 @@ output_cost_per_m = 0.3
 supports_streaming = true
 
 [[models]]
-id = "llama-guard-3-8b"
-display_name = "Llama Guard 3 8B"
+id = "llama-3.3-70b-instruct"
+display_name = "Meta: Llama 3.3 70B Instruct"
 tier = "fast"
 context_window = 131072
 max_output_tokens = 16384