Self-improving AI Employees for everyone
Python ai-agentsai-employeeai-employeesassistantautonomous-agentsco-employeescompanygrok-botinstinctloop-agentsmuseown-your-datapersonalself-hosted
chore: refresh global model catalogue
trohitgd58dc21ddfd3
diff --git a/server/config/llm_defaults.json b/server/config/llm_defaults.jsonindex f0c2f457..2332a6f5 100644--- a/server/config/llm_defaults.json+++ b/server/config/llm_defaults.json@@ -1,7 +1,7 @@{- "version": "2026.07",- "last_updated": "2026-07-11",- "_description": "LLM provider defaults. Connection config (base_url, models_endpoint) drives both native SDK and LangChain paths. Model specs auto-enriched by model_registry.json (OpenRouter cache).",+ "version": "2026.07.18",+ "last_updated": "2026-07-18",+ "_description": "LLM provider defaults. popular_models drives the ordered global selector and offline fallback independently of token constraints. Connection config drives native SDK and LangChain paths; model specs are enriched by model_registry.json (OpenRouter cache).","agent": {"_description": "Agent execution defaults. recursion_limit and compaction.ratio are sourced from the environment (AGENT_RECURSION_LIMIT, COMPACTION_RATIO via core.config.Settings) — these JSON values are last-resort fallbacks when the env vars aren't loaded (e.g. one-off CLI scripts that bypass Settings). default_temperature stays JSON-resident since it has no env override yet.",@@ -15,6 +15,7 @@"providers": {"openai": {"default_model": "gpt-5.6-sol",+ "popular_models": ["gpt-5.6-sol", "gpt-5.6-sol-pro", "gpt-5.6-terra", "gpt-5.6-terra-pro", "gpt-5.6-luna", "gpt-5.6-luna-pro", "gpt-5.5", "gpt-5.4", "gpt-4.1"],"detection_patterns": ["gpt", "openai", "o1", "o3", "o4"],"base_url": "https://api.openai.com/v1","models_endpoint": "https://api.openai.com/v1/models",@@ -23,8 +24,11 @@"_models_note": "GPT-5.6 family (sol/terra/luna) GA 2026-07-09. gpt-5.5 / gpt-5.4 remain GA as legacy tiers. Dropped: gpt-5.2 (new requests blocked 2026-06-30), o3 (API shutdown 2026-12-11), o4-mini (API shutdown 2026-10-23) — they fall back to _default constraints if still selected before shutdown.","max_output_tokens": {"gpt-5.6-sol": 128000,+ "gpt-5.6-sol-pro": 128000,"gpt-5.6-terra": 128000,+ "gpt-5.6-terra-pro": 128000,"gpt-5.6-luna": 128000,+ "gpt-5.6-luna-pro": 128000,"gpt-5.5": 128000,"gpt-5.4": 128000,"gpt-4.1": 32768,@@ -32,8 +36,11 @@},"context_length": {"gpt-5.6-sol": 1050000,+ "gpt-5.6-sol-pro": 1050000,"gpt-5.6-terra": 1050000,+ "gpt-5.6-terra-pro": 1050000,"gpt-5.6-luna": 1050000,+ "gpt-5.6-luna-pro": 1050000,"gpt-5.5": 1050000,"gpt-5.4": 1050000,"gpt-4.1": 1047576,@@ -46,6 +53,7 @@},"anthropic": {"default_model": "claude-opus-4-8",+ "popular_models": ["claude-fable-5", "claude-sonnet-5", "claude-opus-4-8", "claude-opus-4-7", "claude-sonnet-4-6", "claude-haiku-4-5"],"detection_patterns": ["claude", "anthropic"],"base_url": "https://api.anthropic.com/v1","models_endpoint": "https://api.anthropic.com/v1/models",@@ -74,6 +82,7 @@},"gemini": {"default_model": "gemini-3.5-flash",+ "popular_models": ["gemini-3.5-flash", "gemini-3.1-pro-preview", "gemini-3.1-flash-lite", "gemini-3-flash-preview", "gemini-2.5-pro", "gemini-2.5-flash", "gemini-2.5-flash-lite", "gemma-4-31b-it", "gemma-4-26b-a4b-it"],"detection_patterns": ["gemini", "google", "gemma"],"_detection_patterns_note": "'gemma' makes is_model_valid_for_provider accept the API-served Gemma models (gemma-4-*-it) on gemini nodes — without it the four agent-path call sites silently swap gemma to default_model. Cerebras keeps its own 'gemma-4' pattern for its gemma-4-31b (no -it suffix); is_model_valid_for_provider is per-provider so both coexist. Only the runtime-unused detect_provider_from_model classifier prefers gemini for gemma-* names (dict order).","base_url": "https://generativelanguage.googleapis.com/v1beta",@@ -114,7 +123,8 @@"incompatible_models": ["antigravity-preview-05-2026"]},"openrouter": {- "default_model": "anthropic/claude-sonnet-4.6",+ "default_model": "anthropic/claude-sonnet-5",+ "popular_models": ["anthropic/claude-sonnet-5", "openai/gpt-5.6-terra", "openai/gpt-5.6-sol", "google/gemini-3.5-flash", "moonshotai/kimi-k3", "x-ai/grok-4.20", "openrouter/auto-beta"],"detection_patterns": ["openrouter"],"base_url": "https://openrouter.ai/api/v1","models_endpoint": "https://openrouter.ai/api/v1/models",@@ -131,6 +141,7 @@},"groq": {"default_model": "llama-3.3-70b-versatile",+ "popular_models": ["openai/gpt-oss-120b", "openai/gpt-oss-20b", "llama-3.3-70b-versatile", "llama-3.1-8b-instant", "qwen/qwen3-32b"],"detection_patterns": ["groq"],"base_url": "https://api.groq.com/openai/v1","models_endpoint": "https://api.groq.com/openai/v1/models",@@ -158,6 +169,7 @@},"cerebras": {"default_model": "gpt-oss-120b",+ "popular_models": ["gpt-oss-120b", "zai-glm-4.7", "gemma-4-31b"],"detection_patterns": ["cerebras", "gpt-oss", "zai-glm", "gemma-4"],"base_url": "https://api.cerebras.ai/v1","models_endpoint": "https://api.cerebras.ai/v1/models",@@ -182,6 +194,7 @@},"xai": {"default_model": "grok-4.20",+ "popular_models": ["grok-4.20", "grok-4.20-multi-agent", "grok-4.5", "grok-4.3", "grok-3"],"detection_patterns": ["grok", "xai"],"base_url": "https://api.x.ai/v1","models_endpoint": "https://api.x.ai/v1/models",@@ -195,6 +208,8 @@},"context_length": {"grok-4.20": 2000000,+ "grok-4.20-multi-agent": 2000000,+ "grok-4.5": 500000,"grok-4.3": 1000000,"grok-3": 131072,"_default": 131072@@ -203,6 +218,7 @@},"deepseek": {"default_model": "deepseek-v4-flash",+ "popular_models": ["deepseek-v4-flash", "deepseek-v4-pro", "deepseek-chat", "deepseek-reasoner"],"detection_patterns": ["deepseek"],"base_url": "https://api.deepseek.com","models_endpoint": "https://api.deepseek.com/models",@@ -228,6 +244,7 @@},"kimi": {"default_model": "kimi-k2.6",+ "popular_models": ["kimi-k3", "kimi-k2.7-code", "kimi-k2.6", "kimi-k2.5"],"detection_patterns": ["kimi", "moonshot"],"base_url": "https://api.moonshot.ai/v1","models_endpoint": "https://api.moonshot.ai/v1/models",@@ -243,6 +260,7 @@"_default": 8192},"context_length": {+ "kimi-k3": 1048576,"kimi-k2.6": 262144,"kimi-k2.5": 262144,"kimi-k2.7-code": 262144,@@ -252,6 +270,7 @@},"mistral": {"default_model": "mistral-large-latest",+ "popular_models": ["mistral-large-latest", "mistral-medium-latest", "mistral-small-latest", "codestral-latest"],"detection_patterns": ["mistral", "codestral"],"base_url": "https://api.mistral.ai/v1","models_endpoint": "https://api.mistral.ai/v1/models",diff --git a/server/config/model_registry.json b/server/config/model_registry.jsonindex 35b86bf9..a3845c6f 100644--- a/server/config/model_registry.json+++ b/server/config/model_registry.json@@ -1,8 +1,145 @@{- "_generated": "2026-07-16T09:36:38.152250+00:00",+ "_generated": "2026-07-18T13:57:53.993876+00:00","_source": "openrouter",- "_model_count": 342,+ "_model_count": 344,"models": {+ "thinkingmachines/inkling": {+ "id": "thinkingmachines/inkling",+ "name": "Thinking Machines: Inkling",+ "provider": "thinkingmachines",+ "local_id": "inkling",+ "context_length": 1048576,+ "max_output_tokens": 0,+ "input_price_per_mtok": 1.0,+ "output_price_per_mtok": 4.05,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "logit_bias",+ "max_tokens",+ "min_p",+ "presence_penalty",+ "reasoning",+ "reasoning_effort",+ "repetition_penalty",+ "stop",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_p"+ ]+ },+ "openrouter/auto-beta": {+ "id": "openrouter/auto-beta",+ "name": "Auto Router (Beta)",+ "provider": "openrouter",+ "local_id": "auto-beta",+ "context_length": 2000000,+ "max_output_tokens": 0,+ "input_price_per_mtok": -1000000.0,+ "output_price_per_mtok": -1000000.0,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "logit_bias",+ "logprobs",+ "max_tokens",+ "min_p",+ "prediction",+ "presence_penalty",+ "reasoning",+ "reasoning_effort",+ "repetition_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_a",+ "top_k",+ "top_logprobs",+ "top_p",+ "web_search_options"+ ]+ },+ "moonshotai/kimi-k3": {+ "id": "moonshotai/kimi-k3",+ "name": "MoonshotAI: Kimi K3",+ "provider": "moonshotai",+ "local_id": "kimi-k3",+ "context_length": 1048576,+ "max_output_tokens": 0,+ "input_price_per_mtok": 3.0,+ "output_price_per_mtok": 15.0,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "max_tokens",+ "presence_penalty",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "stop",+ "structured_outputs",+ "tool_choice",+ "tools"+ ]+ },+ "meta/muse-spark-1.1": {+ "id": "meta/muse-spark-1.1",+ "name": "Meta: Muse Spark 1.1",+ "provider": "meta",+ "local_id": "muse-spark-1.1",+ "context_length": 1048576,+ "max_output_tokens": 0,+ "input_price_per_mtok": 1.25,+ "output_price_per_mtok": 4.25,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "repetition_penalty",+ "response_format",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_p"+ ]+ },"kwaipilot/kat-coder-air-v2.5": {"id": "kwaipilot/kat-coder-air-v2.5","name": "Kwaipilot: KAT-Coder-Air V2.5",@@ -694,8 +831,8 @@"local_id": "glm-5.2","context_length": 1048576,"max_output_tokens": 131072,- "input_price_per_mtok": 0.959,- "output_price_per_mtok": 3.014,+ "input_price_per_mtok": 0.2954,+ "output_price_per_mtok": 0.9284,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -752,8 +889,8 @@"local_id": "kimi-k2.7-code","context_length": 262144,"max_output_tokens": 262144,- "input_price_per_mtok": 0.719,- "output_price_per_mtok": 3.49,+ "input_price_per_mtok": 1.0,+ "output_price_per_mtok": 4.4,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1652,10 +1789,10 @@"name": "MoonshotAI Kimi Latest","provider": "moonshotai","local_id": "kimi-latest",- "context_length": 262144,- "max_output_tokens": 262144,- "input_price_per_mtok": 0.66,- "output_price_per_mtok": 3.41,+ "context_length": 1048576,+ "max_output_tokens": 0,+ "input_price_per_mtok": 3.0,+ "output_price_per_mtok": 15.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1666,24 +1803,15 @@"supported_parameters": ["frequency_penalty","include_reasoning",- "logit_bias",- "logprobs","max_tokens",- "min_p",- "parallel_tool_calls","presence_penalty","reasoning",- "repetition_penalty",+ "reasoning_effort","response_format",- "seed","stop","structured_outputs",- "temperature","tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"+ "tools"]},"gemini/gemini-flash-latest": {@@ -2527,9 +2655,9 @@"provider": "gemini","local_id": "gemma-4-31b-it","context_length": 262144,- "max_output_tokens": 262144,- "input_price_per_mtok": 0.22,- "output_price_per_mtok": 0.55,+ "max_output_tokens": 16384,+ "input_price_per_mtok": 0.12,+ "output_price_per_mtok": 0.37,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2554,6 +2682,7 @@"temperature","tool_choice","tools",+ "top_a","top_k","top_logprobs","top_p"@@ -2858,8 +2987,8 @@"local_id": "minimax-m2.7","context_length": 204800,"max_output_tokens": 131072,- "input_price_per_mtok": 0.3,- "output_price_per_mtok": 1.2,+ "input_price_per_mtok": 0.25,+ "output_price_per_mtok": 1.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -3393,9 +3522,9 @@"provider": "qwen","local_id": "qwen3.5-27b","context_length": 262144,- "max_output_tokens": 65536,- "input_price_per_mtok": 0.195,- "output_price_per_mtok": 1.56,+ "max_output_tokens": 81920,+ "input_price_per_mtok": 0.26,+ "output_price_per_mtok": 2.6,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -3682,8 +3811,8 @@"local_id": "qwen3.5-397b-a17b","context_length": 262144,"max_output_tokens": 65536,- "input_price_per_mtok": 0.45,- "output_price_per_mtok": 3.0,+ "input_price_per_mtok": 0.39,+ "output_price_per_mtok": 2.34,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -4137,9 +4266,9 @@"name": "Z.ai: GLM 4.7 Flash","provider": "z-ai","local_id": "glm-4.7-flash",- "context_length": 202752,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.06,+ "context_length": 200000,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.0605,"output_price_per_mtok": 0.4,"supports_thinking": false,"thinking_type": "none",@@ -5085,7 +5214,7 @@"provider": "moonshotai","local_id": "kimi-k2-thinking","context_length": 262144,- "max_output_tokens": 262144,+ "max_output_tokens": 100352,"input_price_per_mtok": 0.6,"output_price_per_mtok": 2.5,"supports_thinking": false,@@ -5589,41 +5718,6 @@"top_p"]},- "nvidia/llama-3.3-nemotron-super-49b-v1.5": {- "id": "nvidia/llama-3.3-nemotron-super-49b-v1.5",- "name": "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",- "provider": "nvidia",- "local_id": "llama-3.3-nemotron-super-49b-v1.5",- "context_length": 131072,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.4,- "output_price_per_mtok": 0.4,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "include_reasoning",- "logit_bias",- "max_tokens",- "min_p",- "presence_penalty",- "reasoning",- "repetition_penalty",- "response_format",- "seed",- "stop",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_p"- ]- },"gemini/gemini-2.5-flash-image": {"id": "google/gemini-2.5-flash-image","name": "Google: Nano Banana (Gemini 2.5 Flash Image)",@@ -7814,9 +7908,9 @@"provider": "qwen","local_id": "qwen3-30b-a3b","context_length": 131072,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.12,- "output_price_per_mtok": 0.5,+ "max_output_tokens": 8192,+ "input_price_per_mtok": 0.13,+ "output_price_per_mtok": 0.52,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -7881,9 +7975,9 @@"provider": "qwen","local_id": "qwen3-14b","context_length": 131702,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.12,- "output_price_per_mtok": 0.24,+ "max_output_tokens": 8192,+ "input_price_per_mtok": 0.2275,+ "output_price_per_mtok": 0.91,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -8486,9 +8580,9 @@"provider": "gemini","local_id": "gemma-3-27b-it","context_length": 131072,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.08,- "output_price_per_mtok": 0.45,+ "max_output_tokens": 0,+ "input_price_per_mtok": 0.1,+ "output_price_per_mtok": 0.3,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -9516,37 +9610,6 @@"top_p"]},- "meta/llama-3.2-11b-vision-instruct": {- "id": "meta-llama/llama-3.2-11b-vision-instruct",- "name": "Meta: Llama 3.2 11B Vision Instruct",- "provider": "meta",- "local_id": "llama-3.2-11b-vision-instruct",- "context_length": 131072,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.345,- "output_price_per_mtok": 0.345,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "logit_bias",- "max_tokens",- "min_p",- "presence_penalty",- "repetition_penalty",- "response_format",- "seed",- "stop",- "temperature",- "top_k",- "top_p"- ]- },"meta/llama-3.2-1b-instruct": {"id": "meta-llama/llama-3.2-1b-instruct","name": "Meta: Llama 3.2 1B Instruct",@@ -9583,9 +9646,9 @@"provider": "meta","local_id": "llama-3.2-3b-instruct","context_length": 131072,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.05,- "output_price_per_mtok": 0.33,+ "max_output_tokens": 80000,+ "input_price_per_mtok": 0.0509,+ "output_price_per_mtok": 0.335,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -10003,8 +10066,8 @@"local_id": "mistral-nemo","context_length": 131072,"max_output_tokens": 16384,- "input_price_per_mtok": 0.02,- "output_price_per_mtok": 0.04,+ "input_price_per_mtok": 0.019,+ "output_price_per_mtok": 0.03,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -10439,7 +10502,6 @@"include_reasoning","logit_bias","logprobs",- "max_completion_tokens","max_tokens","min_p","prediction",@@ -10533,8 +10595,8 @@"local_id": "weaver","context_length": 8000,"max_output_tokens": 2000,- "input_price_per_mtok": 0.75,- "output_price_per_mtok": 1.0,+ "input_price_per_mtok": 0.5,+ "output_price_per_mtok": 0.75,"supports_thinking": false,"thinking_type": "none","temperature_range": [diff --git a/server/services/ai.py b/server/services/ai.pyindex fb906325..b13a5ae3 100644--- a/server/services/ai.py+++ b/server/services/ai.py@@ -1363,10 +1363,14 @@ class AIService:def _get_curated_models(self, provider: str) -> List[str]:"""Get curated model list from llm_defaults.json for a provider.- Returns model IDs from max_output_tokens keys (excluding _default),- preserving config order. Returns empty list if provider has no curated list.+ Prefer the explicit ``popular_models`` list, preserving its order.+ Older provider blocks fall back to max_output_tokens keys (excluding+ _default). Returns empty when neither source has a curated list."""provider_cfg = _LLM_DEFAULTS.get("providers", {}).get(provider, {})+ explicit = provider_cfg.get("popular_models") or []+ if explicit:+ return list(explicit)max_tokens_map = provider_cfg.get("max_output_tokens", {})return [m for m in max_tokens_map if m != "_default"]diff --git a/server/services/settings/handlers.py b/server/services/settings/handlers.pyindex 9c382d23..95b31cca 100644--- a/server/services/settings/handlers.py+++ b/server/services/settings/handlers.py@@ -155,7 +155,9 @@ async def handle_get_validated_ai_providers(provider_config = llm_defaults.get("providers", {}).get(provider, {})default_model = provider_config.get("default_model", "")- popular_models = [m for m in provider_config.get("max_output_tokens", {}).keys() if m != "_default"]+ popular_models = provider_config.get("popular_models") or [+ m for m in provider_config.get("max_output_tokens", {}).keys() if m != "_default"+ ]provider_defaults = await database.get_provider_defaults(provider)if provider_defaults and provider_defaults.get("default_model"):diff --git a/server/tests/llm/test_global_model_catalogue.py b/server/tests/llm/test_global_model_catalogue.pynew file mode 100644index 00000000..c8b02b7f--- /dev/null+++ b/server/tests/llm/test_global_model_catalogue.py@@ -0,0 +1,47 @@+"""Curated global-model list stays aligned with the router cache."""++import json+from pathlib import Path++from services.ai import AIService+++CONFIG_DIR = Path(__file__).resolve().parents[2] / "config"+++def _defaults():+ return json.loads((CONFIG_DIR / "llm_defaults.json").read_text(encoding="utf-8"))+++def _registry():+ return json.loads((CONFIG_DIR / "model_registry.json").read_text(encoding="utf-8"))+++def test_cloud_defaults_are_present_in_explicit_global_lists() -> None:+ providers = _defaults()["providers"]+ for provider, config in providers.items():+ popular = config.get("popular_models")+ if not popular:+ continue+ assert len(popular) == len(set(popular)), f"{provider} has duplicate popular models"+ assert config["default_model"] in popular, f"{provider} default is absent from global list"+++def test_openrouter_global_models_exist_in_latest_router_cache() -> None:+ defaults = _defaults()["providers"]["openrouter"]+ registry_ids = {entry["id"] for entry in _registry()["models"].values()}+ assert set(defaults["popular_models"]).issubset(registry_ids)+++def test_latest_router_families_are_exposed() -> None:+ providers = _defaults()["providers"]+ assert "gpt-5.6-sol-pro" in providers["openai"]["popular_models"]+ assert "claude-sonnet-5" in providers["anthropic"]["popular_models"]+ assert "gemini-3.5-flash" in providers["gemini"]["popular_models"]+ assert "kimi-k3" in providers["kimi"]["popular_models"]+ assert "grok-4.5" in providers["xai"]["popular_models"]+++def test_ai_service_offline_fallback_uses_explicit_order() -> None:+ expected = _defaults()["providers"]["openrouter"]["popular_models"]+ assert AIService._get_curated_models(None, "openrouter") == expected