sync model validation with cli catalog

2026-06-29 01:01:33 +03:00 · 2026-03-25 21:23:02 +08:00
parent f362a160c3
commit 8793336dad
8 changed files with 192 additions and 125 deletions
@@ -0,0 +1,106 @@
+"""Shared model catalog for CLI selections and validation."""
+
+from __future__ import annotations
+
+from typing import Dict, List, Tuple
+
+ModelOption = Tuple[str, str]
+ProviderModeOptions = Dict[str, List[ModelOption]]
+
+
+MODEL_OPTIONS: ProviderModeOptions = {
+    "openai": {
+        "quick": [
+            ("GPT-5 Mini - Balanced speed, cost, and capability", "gpt-5-mini"),
+            ("GPT-5 Nano - High-throughput, simple tasks", "gpt-5-nano"),
+            ("GPT-5.4 - Latest frontier, 1M context", "gpt-5.4"),
+            ("GPT-4.1 - Smartest non-reasoning model", "gpt-4.1"),
+        ],
+        "deep": [
+            ("GPT-5.4 - Latest frontier, 1M context", "gpt-5.4"),
+            ("GPT-5.2 - Strong reasoning, cost-effective", "gpt-5.2"),
+            ("GPT-5 Mini - Balanced speed, cost, and capability", "gpt-5-mini"),
+            ("GPT-5.4 Pro - Most capable, expensive ($30/$180 per 1M tokens)", "gpt-5.4-pro"),
+        ],
+    },
+    "anthropic": {
+        "quick": [
+            ("Claude Sonnet 4.6 - Best speed and intelligence balance", "claude-sonnet-4-6"),
+            ("Claude Haiku 4.5 - Fast, near-instant responses", "claude-haiku-4-5"),
+            ("Claude Sonnet 4.5 - Agents and coding", "claude-sonnet-4-5"),
+        ],
+        "deep": [
+            ("Claude Opus 4.6 - Most intelligent, agents and coding", "claude-opus-4-6"),
+            ("Claude Opus 4.5 - Premium, max intelligence", "claude-opus-4-5"),
+            ("Claude Sonnet 4.6 - Best speed and intelligence balance", "claude-sonnet-4-6"),
+            ("Claude Sonnet 4.5 - Agents and coding", "claude-sonnet-4-5"),
+        ],
+    },
+    "google": {
+        "quick": [
+            ("Gemini 3 Flash - Next-gen fast", "gemini-3-flash-preview"),
+            ("Gemini 2.5 Flash - Balanced, stable", "gemini-2.5-flash"),
+            ("Gemini 3.1 Flash Lite - Most cost-efficient", "gemini-3.1-flash-lite-preview"),
+            ("Gemini 2.5 Flash Lite - Fast, low-cost", "gemini-2.5-flash-lite"),
+        ],
+        "deep": [
+            ("Gemini 3.1 Pro - Reasoning-first, complex workflows", "gemini-3.1-pro-preview"),
+            ("Gemini 3 Flash - Next-gen fast", "gemini-3-flash-preview"),
+            ("Gemini 2.5 Pro - Stable pro model", "gemini-2.5-pro"),
+            ("Gemini 2.5 Flash - Balanced, stable", "gemini-2.5-flash"),
+        ],
+    },
+    "xai": {
+        "quick": [
+            ("Grok 4.1 Fast (Non-Reasoning) - Speed optimized, 2M ctx", "grok-4-1-fast-non-reasoning"),
+            ("Grok 4 Fast (Non-Reasoning) - Speed optimized", "grok-4-fast-non-reasoning"),
+            ("Grok 4.1 Fast (Reasoning) - High-performance, 2M ctx", "grok-4-1-fast-reasoning"),
+        ],
+        "deep": [
+            ("Grok 4 - Flagship model", "grok-4-0709"),
+            ("Grok 4.1 Fast (Reasoning) - High-performance, 2M ctx", "grok-4-1-fast-reasoning"),
+            ("Grok 4 Fast (Reasoning) - High-performance", "grok-4-fast-reasoning"),
+            ("Grok 4.1 Fast (Non-Reasoning) - Speed optimized, 2M ctx", "grok-4-1-fast-non-reasoning"),
+        ],
+    },
+    "openrouter": {
+        "quick": [
+            ("NVIDIA Nemotron 3 Nano 30B (free)", "nvidia/nemotron-3-nano-30b-a3b:free"),
+            ("Z.AI GLM 4.5 Air (free)", "z-ai/glm-4.5-air:free"),
+        ],
+        "deep": [
+            ("Z.AI GLM 4.5 Air (free)", "z-ai/glm-4.5-air:free"),
+            ("NVIDIA Nemotron 3 Nano 30B (free)", "nvidia/nemotron-3-nano-30b-a3b:free"),
+        ],
+    },
+    "ollama": {
+        "quick": [
+            ("Qwen3:latest (8B, local)", "qwen3:latest"),
+            ("GPT-OSS:latest (20B, local)", "gpt-oss:latest"),
+            ("GLM-4.7-Flash:latest (30B, local)", "glm-4.7-flash:latest"),
+        ],
+        "deep": [
+            ("GLM-4.7-Flash:latest (30B, local)", "glm-4.7-flash:latest"),
+            ("GPT-OSS:latest (20B, local)", "gpt-oss:latest"),
+            ("Qwen3:latest (8B, local)", "qwen3:latest"),
+        ],
+    },
+}
+
+
+def get_model_options(provider: str, mode: str) -> List[ModelOption]:
+    """Return shared model options for a provider and selection mode."""
+    return MODEL_OPTIONS[provider.lower()][mode]
+
+
+def get_known_models() -> Dict[str, List[str]]:
+    """Build known model names from the shared CLI catalog."""
+    known_models: Dict[str, List[str]] = {}
+    for provider, mode_options in MODEL_OPTIONS.items():
+        model_names = {
+            value
+            for options in mode_options.values()
+            for _, value in options
+        }
+        known_models[provider] = sorted(model_names)
+    return known_models