chore: prune deprecated models across providers (#75)

* chore: prune deprecated models across providers

Remove old-generation models that are strictly superseded by current versions
on the same provider/family. Affected providers: anthropic, bedrock, vertex-ai,
xai, moonshot, zhipu, baichuan, stepfun, volcengine, minimax, cohere, together,
fireworks, deepinfra, openrouter. Also clean up orphan aliases (grok3, grok-mini,
minimax-m2.1) and remap moonshot alias to kimi-k2.5.

Net: -42 model entries across 18 files. Provider model counts and README rows
updated accordingly.

* chore: remove redundant and orphan aliases from aliases.toml

Provider TOML files auto-register their model.aliases at load time, so
re-declaring them globally is duplication. Also drop entries pointing to
models that no longer exist after the prune.

- 45 redundant entries duplicating provider-defined aliases
- 11 orphan targets (gpt-4o, gpt-4o-mini, grok-2-mini, grok-3,
  mixtral-8x7b-32768, copilot/gpt-4, open-mistral-nemo,
  pixtral-large-latest, jamba-1.5-large, palmyra-x5, venice-uncensored)

Net: 100 lines down to 21. The file is now what the header comment
always claimed it was: 'additional global aliases not tied to a specific
model entry.'

* chore: second pass — prune more deprecated models

Apply the same 'strictly superseded by same-provider/family successor'
rule to providers missed in the first pass:

- openai: gpt-4.1 / -mini / -nano, o3, o4-mini (5)
- meta-llama: llama-3.3-70b-instruct (1)
- zhipu: glm-4v-plus (1)
- together: Llama-3.3-70B-Instruct-Turbo (1)
- xiaomi: mimo-v2-flash / -omni / -pro (3)
- aion-labs: aion-1.0 / -mini (2)
- qianfan: ernie-speed-128k, ernie-4.0-turbo-8k (2)
- cerebras: cerebras/llama3.1-8b (1)
- qwen-code: qwen-code/qwq-32b (1)
- nvidia-nim: 12 models (llama-3.1/3.2 series, mixtral-8x22b,
  mistral-small-3.1, phi-4-mini, qwq-32b, r1-distill-32b,
  qwen2.5-coder, nemotron-mini-4b, nemotron-70b-instruct)
- openrouter: meta-llama/llama-3.3-70b (paid), rekaai/reka-edge (2)
- alibaba-coding-plan: qwen3.5-plus, qwen3-max-2026-01-23,
  MiniMax-M2.5, kimi-k2.5 (4)

Net: -35 model entries. providers/README.md model counts updated.
220 models remain.

aliases.toml

@@ -5,106 +5,16 @@
 # that are not tied to a specific model entry.
 
 [aliases]
-# Anthropic
-"sonnet" = "claude-sonnet-4-6"
-"claude-sonnet" = "claude-sonnet-4-6"
-"haiku" = "claude-haiku-4-5-20251001"
-"claude-haiku" = "claude-haiku-4-5-20251001"
-"opus" = "claude-opus-4-6"
-"claude-opus" = "claude-opus-4-6"
-
-# OpenAI
-"gpt4" = "gpt-4o"
-"gpt4o" = "gpt-4o"
-"gpt4-mini" = "gpt-4o-mini"
-"gpt5" = "gpt-5.2"
-"gpt5-mini" = "gpt-5-mini"
-
-# Google Gemini
-"flash" = "gemini-2.5-flash"
-"gemini-pro" = "gemini-3.1-pro-preview"
-"gemini-flash" = "gemini-3-flash-preview"
-
-# DeepSeek
-"deepseek" = "deepseek-chat"
-"deepseek-v3" = "deepseek-chat"
-"deepseek-r1" = "deepseek-reasoner"
-
-# Groq
-"llama" = "llama-3.3-70b-versatile"
-"llama-70b" = "llama-3.3-70b-versatile"
-"mixtral" = "mixtral-8x7b-32768"
-
-# Mistral
-"mistral" = "mistral-large-latest"
-"codestral" = "codestral-latest"
-"mistral-nemo" = "open-mistral-nemo"
-"pixtral" = "pixtral-large-latest"
-
-# xAI
-"grok" = "grok-4-0709"
-"grok-4" = "grok-4-0709"
-"grok-mini" = "grok-2-mini"
-"grok3" = "grok-3"
-"grok-fast" = "grok-4-1-fast-reasoning"
-
-# Perplexity
-"sonar" = "sonar-pro"
-
-# AI21
-"jamba" = "jamba-1.5-large"
-
-# Cohere
-"command-r" = "command-r-plus"
-"command" = "command-a"
-
-# GitHub Copilot
+# GitHub Copilot — bare names not registered on the copilot/gpt-4o model
 "copilot" = "copilot/gpt-4o"
 "copilot-4o" = "copilot/gpt-4o"
-"copilot-4" = "copilot/gpt-4"
-"copilot-gpt4o" = "copilot/gpt-4o"
-"copilot-gpt4" = "copilot/gpt-4"
 
-# Chinese models
-"qwen" = "qwen-plus"
-"glm" = "glm-5-20250605"
+# Chinese models — common short names not on the canonical model entries
 "ernie" = "ernie-4.5-8k"
-"kimi" = "kimi-k2"
-"moonshot" = "moonshot-v1-128k"
+"moonshot" = "kimi-k2.5"
 "minimax" = "MiniMax-M2.7"
-"minimax-m2.5" = "MiniMax-M2.5"
-"minimax-m2.5-highspeed" = "MiniMax-M2.5-highspeed"
 "minimax-highspeed" = "MiniMax-M2.7-highspeed"
-"minimax-m2.1" = "MiniMax-M2.1"
-"codegeex" = "codegeex-4"
 "doubao" = "doubao-seed-2-0-pro-260215"
 "doubao-seed" = "doubao-seed-2-0-pro-260215"
 "stepfun" = "step-3.5-flash"
 "baichuan" = "Baichuan4"
-"baichuan-4" = "Baichuan4"
-
-# Writer
-"palmyra" = "palmyra-x5"
-"writer" = "palmyra-x5"
-
-# ChatGPT Session Auth
-"chatgpt" = "gpt-5.1-codex-mini"
-"chatgpt-mini" = "gpt-5.1-codex-mini"
-"chatgpt-5.1" = "gpt-5.1-codex"
-"chatgpt-5.2" = "gpt-5.2-codex"
-"chatgpt-5.3" = "gpt-5.3-codex"
-"chatgpt-5.4" = "gpt-5.4-codex"
-
-# Codex
-"codex" = "codex/gpt-4.1"
-"codex-4.1" = "codex/gpt-4.1"
-"codex-o4" = "codex/o4-mini"
-
-# Venice
-"venice" = "venice-uncensored"
-
-# Claude Code
-"claude-code" = "claude-code/sonnet"
-"claude-code-opus" = "claude-code/opus"
-"claude-code-sonnet" = "claude-code/sonnet"
-"claude-code-haiku" = "claude-code/haiku"