@oh-my-pi/pi-ai 13.18.0 → 13.19.0

package/CHANGELOG.md

@@ -2,6 +2,16 @@
 
 ## [Unreleased]
 
+## [13.19.0] - 2026-04-05
+
+### Fixed
+
+- Fixed GitHub Copilot model context window detection by correcting fallback priority for maxContextWindowTokens and maxPromptTokens
+- Fixed Gemini 2.5 Pro context window detection in GitHub Copilot model limits test
+- Fixed Claude Opus 4.6 context window detection in GitHub Copilot model limits test
+- Fixed Anthropic streaming to suppress transient SDK console errors for malformed SSE keep-alive frames so the TUI only shows surfaced provider errors
+
+- Added environment-based credential fallback for the OpenAI Codex provider.
 ## [13.17.6] - 2026-04-01
 
 ### Fixed

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-ai",
-	"version": "13.18.0",
+	"version": "13.19.0",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"homepage": "https://github.com/can1357/oh-my-pi",
 	"author": "Can Boluk",
@@ -41,7 +41,7 @@
 		"@aws-sdk/client-bedrock-runtime": "^3",
 		"@bufbuild/protobuf": "^2.11",
 		"@google/genai": "^1.43",
-		"@oh-my-pi/pi-utils": "13.18.0",
+		"@oh-my-pi/pi-utils": "13.19.0",
 		"@sinclair/typebox": "^0.34",
 		"@smithy/node-http-handler": "^4.4",
 		"ajv": "^8.18",

package/src/model-thinking.ts

@@ -289,6 +289,13 @@ function applyAnthropicCatalogPolicy(model: ApiModel<Api>, parsedModel: Anthropi
 		model.cost.cacheWrite = 6.25;
 	}
 
+	// GitHub Copilot Opus 4.6: discovery currently reports a stale 144K prompt window,
+	// but the model supports a 1M context window. Keep the bundled catalog truthful
+	// until Copilot fixes the upstream metadata.
+	if (model.provider === "github-copilot" && parsedModel.kind === "opus" && semverEqual(parsedModel.version, "4.6")) {
+		model.contextWindow = 1000000;
+	}
+
 	// Bedrock Opus 4.6: upstream metadata is stale for cache pricing and context.
 	if (model.provider === "amazon-bedrock" && parsedModel.kind === "opus" && semverEqual(parsedModel.version, "4.6")) {
 		model.cost.cacheRead = 0.5;

package/src/models.json

@@ -202,6 +202,34 @@
 				"minLevel": "minimal",
 				"maxLevel": "high"
 			}
+		},
+		"qwen3.6-plus": {
+			"id": "qwen3.6-plus",
+			"name": "Qwen3.6 Plus",
+			"api": "openai-completions",
+			"provider": "alibaba-coding-plan",
+			"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1000000,
+			"maxTokens": 65536,
+			"compat": {
+				"supportsDeveloperRole": false
+			},
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
 		}
 	},
 	"amazon-bedrock": {
@@ -4605,7 +4633,7 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": 144000,
+			"contextWindow": 1000000,
 			"maxTokens": 64000,
 			"headers": {
 				"User-Agent": "GitHubCopilotChat/0.35.0",
@@ -6290,6 +6318,56 @@
 			},
 			"contextWindow": 131072,
 			"maxTokens": 8192
+		},
+		"gemma-4-26b": {
+			"id": "gemma-4-26b",
+			"name": "Gemma 4 26B",
+			"api": "google-generative-ai",
+			"provider": "google",
+			"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 256000,
+			"maxTokens": 8192,
+			"thinking": {
+				"mode": "budget",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
+		},
+		"gemma-4-31b": {
+			"id": "gemma-4-31b",
+			"name": "Gemma 4 31B",
+			"api": "google-generative-ai",
+			"provider": "google",
+			"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 256000,
+			"maxTokens": 8192,
+			"thinking": {
+				"mode": "budget",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
 		}
 	},
 	"google-antigravity": {
@@ -6813,6 +6891,31 @@
 				"minLevel": "low",
 				"maxLevel": "high"
 			}
+		},
+		"gemini-3.1-flash-lite-preview": {
+			"id": "gemini-3.1-flash-lite-preview",
+			"name": "Gemini 3.1 Flash Lite Preview",
+			"api": "google-gemini-cli",
+			"provider": "google-gemini-cli",
+			"baseUrl": "https://cloudcode-pa.googleapis.com",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1048576,
+			"maxTokens": 65536,
+			"thinking": {
+				"mode": "google-level",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
 		}
 	},
 	"google-vertex": {
@@ -8518,6 +8621,25 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"bytedance-seed/dola-seed-2.0-pro:free": {
+			"id": "bytedance-seed/dola-seed-2.0-pro:free",
+			"name": "ByteDance Seed: Dola Seed 2.0 Pro (free)",
+			"api": "openai-completions",
+			"provider": "kilo",
+			"baseUrl": "https://api.kilo.ai/api/gateway",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 222222,
+			"maxTokens": 8888
+		},
 		"bytedance-seed/seed-1.6": {
 			"id": "bytedance-seed/seed-1.6",
 			"name": "ByteDance Seed: Seed 1.6",
@@ -9504,6 +9626,50 @@
 			"contextWindow": 128000,
 			"maxTokens": 4096
 		},
+		"google/gemma-4-26b-a4b-it": {
+			"id": "google/gemma-4-26b-a4b-it",
+			"name": "Google: Gemma 4 26B A4B",
+			"api": "openai-completions",
+			"provider": "kilo",
+			"baseUrl": "https://api.kilo.ai/api/gateway",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 222222,
+			"maxTokens": 8888
+		},
+		"google/gemma-4-31b-it": {
+			"id": "google/gemma-4-31b-it",
+			"name": "Gemma-4-31B-IT",
+			"api": "openai-completions",
+			"provider": "kilo",
+			"baseUrl": "https://api.kilo.ai/api/gateway",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 256000,
+			"maxTokens": 16384,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
+		},
 		"google/lyria-3-clip-preview": {
 			"id": "google/lyria-3-clip-preview",
 			"name": "Google: Lyria 3 Clip Preview",
@@ -13889,6 +14055,25 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"qwen/qwen3.6-plus:free": {
+			"id": "qwen/qwen3.6-plus:free",
+			"name": "Qwen: Qwen3.6 Plus (free)",
+			"api": "openai-completions",
+			"provider": "kilo",
+			"baseUrl": "https://api.kilo.ai/api/gateway",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 222222,
+			"maxTokens": 8888
+		},
 		"qwen/qwq-32b": {
 			"id": "qwen/qwq-32b",
 			"name": "Qwen: QwQ 32B",
@@ -14969,13 +15154,14 @@
 		},
 		"z-ai/glm-5v-turbo": {
 			"id": "z-ai/glm-5v-turbo",
-			"name": "Z.ai: GLM 5V Turbo",
+			"name": "GLM 5V Turbo",
 			"api": "openai-completions",
 			"provider": "kilo",
 			"baseUrl": "https://api.kilo.ai/api/gateway",
-			"reasoning": false,
+			"reasoning": true,
 			"input": [
-				"text"
+				"text",
+				"image"
 			],
 			"cost": {
 				"input": 0,
@@ -14983,8 +15169,13 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": 222222,
-			"maxTokens": 8888
+			"contextWindow": 200000,
+			"maxTokens": 128000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
 		}
 	},
 	"kimi-code": {
@@ -18257,6 +18448,30 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"arcee-ai/trinity-large-thinking": {
+			"id": "arcee-ai/trinity-large-thinking",
+			"name": "Arcee AI: Trinity Large Thinking",
+			"api": "openai-completions",
+			"provider": "nanogpt",
+			"baseUrl": "https://nano-gpt.com/api/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.25,
+				"output": 0.8999999999999999,
+				"cacheRead": 0.06,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 80000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
+		},
 		"arcee-ai/trinity-mini": {
 			"id": "arcee-ai/trinity-mini",
 			"name": "Arcee AI: Trinity Mini",
@@ -21562,6 +21777,25 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"glm-4.7-flash-heretic": {
+			"id": "glm-4.7-flash-heretic",
+			"name": "glm-4.7-flash-heretic",
+			"api": "openai-completions",
+			"provider": "nanogpt",
+			"baseUrl": "https://nano-gpt.com/api/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 222222,
+			"maxTokens": 8888
+		},
 		"glm-z1-air": {
 			"id": "glm-z1-air",
 			"name": "glm-z1-air",
@@ -21847,6 +22081,56 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"google/gemma-4-26b-a4b-it": {
+			"id": "google/gemma-4-26b-a4b-it",
+			"name": "Google: Gemma 4 26B A4B",
+			"api": "openai-completions",
+			"provider": "nanogpt",
+			"baseUrl": "https://nano-gpt.com/api/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.13,
+				"output": 0.39999999999999997,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 262144,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
+		},
+		"google/gemma-4-31b-it": {
+			"id": "google/gemma-4-31b-it",
+			"name": "Gemma-4-31B-IT",
+			"api": "openai-completions",
+			"provider": "nanogpt",
+			"baseUrl": "https://nano-gpt.com/api/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 256000,
+			"maxTokens": 16384,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
+		},
 		"grok-3-beta": {
 			"id": "grok-3-beta",
 			"name": "grok-3-beta",
@@ -25945,6 +26229,25 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"qwen-3.6-plus": {
+			"id": "qwen-3.6-plus",
+			"name": "qwen-3.6-plus",
+			"api": "openai-completions",
+			"provider": "nanogpt",
+			"baseUrl": "https://nano-gpt.com/api/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 222222,
+			"maxTokens": 8888
+		},
 		"qwen-long": {
 			"id": "qwen-long",
 			"name": "qwen-long",
@@ -27514,6 +27817,25 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"TEE/gemma4-31b": {
+			"id": "TEE/gemma4-31b",
+			"name": "TEE/gemma4-31b",
+			"api": "openai-completions",
+			"provider": "nanogpt",
+			"baseUrl": "https://nano-gpt.com/api/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 222222,
+			"maxTokens": 8888
+		},
 		"TEE/glm-4.6": {
 			"id": "TEE/glm-4.6",
 			"name": "TEE/glm-4.6",
@@ -28543,22 +28865,28 @@
 		},
 		"x-ai/grok-4.20": {
 			"id": "x-ai/grok-4.20",
-			"name": "x-ai/grok-4.20",
+			"name": "xAI: Grok 4.20",
 			"api": "openai-completions",
 			"provider": "nanogpt",
 			"baseUrl": "https://nano-gpt.com/api/v1",
-			"reasoning": false,
+			"reasoning": true,
 			"input": [
-				"text"
+				"text",
+				"image"
 			],
 			"cost": {
-				"input": 0,
-				"output": 0,
-				"cacheRead": 0,
+				"input": 2,
+				"output": 6,
+				"cacheRead": 0.19999999999999998,
 				"cacheWrite": 0
 			},
-			"contextWindow": 222222,
-			"maxTokens": 8888
+			"contextWindow": 2000000,
+			"maxTokens": 8888,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
 		},
 		"x-ai/grok-4.20-beta-non-reasoning": {
 			"id": "x-ai/grok-4.20-beta-non-reasoning",
@@ -28916,6 +29244,31 @@
 				"maxLevel": "xhigh"
 			}
 		},
+		"z-ai/glm-5v-turbo": {
+			"id": "z-ai/glm-5v-turbo",
+			"name": "GLM 5V Turbo",
+			"api": "openai-completions",
+			"provider": "nanogpt",
+			"baseUrl": "https://nano-gpt.com/api/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 200000,
+			"maxTokens": 128000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
+		},
 		"zai-org/glm-4.5": {
 			"id": "zai-org/glm-4.5",
 			"name": "zai-org/glm-4.5",
@@ -29486,6 +29839,31 @@
 			"contextWindow": 128000,
 			"maxTokens": 4096
 		},
+		"google/gemma-4-31b-it": {
+			"id": "google/gemma-4-31b-it",
+			"name": "Gemma-4-31B-IT",
+			"api": "openai-completions",
+			"provider": "nvidia",
+			"baseUrl": "https://integrate.api.nvidia.com/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 256000,
+			"maxTokens": 16384,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
+		},
 		"meta/llama-3.1-405b-instruct": {
 			"id": "meta/llama-3.1-405b-instruct",
 			"name": "Llama 3.1 405b Instruct",
@@ -32042,12 +32420,61 @@
 				"maxLevel": "xhigh"
 			}
 		},
+		"mimo-v2-omni": {
+			"id": "mimo-v2-omni",
+			"name": "MiMo V2 Omni",
+			"api": "openai-completions",
+			"provider": "opencode-go",
+			"baseUrl": "https://opencode.ai/zen/go/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.4,
+				"output": 2,
+				"cacheRead": 0.08,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 64000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
+		},
+		"mimo-v2-pro": {
+			"id": "mimo-v2-pro",
+			"name": "MiMo V2 Pro",
+			"api": "openai-completions",
+			"provider": "opencode-go",
+			"baseUrl": "https://opencode.ai/zen/go/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 1,
+				"output": 3,
+				"cacheRead": 0.2,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1048576,
+			"maxTokens": 64000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
+		},
 		"minimax-m2.5": {
 			"id": "minimax-m2.5",
 			"name": "MiniMax M2.5",
-			"api": "anthropic-messages",
+			"api": "openai-completions",
 			"provider": "opencode-go",
-			"baseUrl": "https://opencode.ai/zen/go",
+			"baseUrl": "https://opencode.ai/zen/go/v1",
 			"reasoning": true,
 			"input": [
 				"text"
@@ -32061,7 +32488,7 @@
 			"contextWindow": 204800,
 			"maxTokens": 131072,
 			"thinking": {
-				"mode": "budget",
+				"mode": "effort",
 				"minLevel": "minimal",
 				"maxLevel": "xhigh"
 			}
@@ -33062,7 +33489,7 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": 1000000,
+			"contextWindow": 204800,
 			"maxTokens": 128000,
 			"thinking": {
 				"mode": "effort",
@@ -33631,13 +34058,13 @@
 				"text"
 			],
 			"cost": {
-				"input": 0.25,
-				"output": 0.8999999999999999,
+				"input": 0.22,
+				"output": 0.85,
 				"cacheRead": 0.06,
 				"cacheWrite": 0
 			},
 			"contextWindow": 262144,
-			"maxTokens": 80000,
+			"maxTokens": 262144,
 			"thinking": {
 				"mode": "effort",
 				"minLevel": "minimal",
@@ -34251,7 +34678,7 @@
 				"cacheWrite": 0.08333333333333334
 			},
 			"contextWindow": 1048576,
-			"maxTokens": 65536,
+			"maxTokens": 65535,
 			"thinking": {
 				"mode": "effort",
 				"minLevel": "minimal",
@@ -34523,6 +34950,56 @@
 			"contextWindow": 131072,
 			"maxTokens": 8192
 		},
+		"google/gemma-4-26b-a4b-it": {
+			"id": "google/gemma-4-26b-a4b-it",
+			"name": "Google: Gemma 4 26B A4B",
+			"api": "openai-completions",
+			"provider": "openrouter",
+			"baseUrl": "https://openrouter.ai/api/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.13,
+				"output": 0.39999999999999997,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 262144,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
+		},
+		"google/gemma-4-31b-it": {
+			"id": "google/gemma-4-31b-it",
+			"name": "Gemma-4-31B-IT",
+			"api": "openai-completions",
+			"provider": "openrouter",
+			"baseUrl": "https://openrouter.ai/api/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.14,
+				"output": 0.39999999999999997,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 256000,
+			"maxTokens": 16384,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
+		},
 		"inception/mercury": {
 			"id": "inception/mercury",
 			"name": "Inception: Mercury",
@@ -34879,9 +35356,9 @@
 				"text"
 			],
 			"cost": {
-				"input": 0.12,
-				"output": 1,
-				"cacheRead": 0.06,
+				"input": 0.118,
+				"output": 0.9900000000000001,
+				"cacheRead": 0.059,
 				"cacheWrite": 0
 			},
 			"contextWindow": 204800,
@@ -35527,9 +36004,9 @@
 				"image"
 			],
 			"cost": {
-				"input": 0.42,
-				"output": 2.2,
-				"cacheRead": 0.21,
+				"input": 0.3827,
+				"output": 1.72,
+				"cacheRead": 0.1935,
 				"cacheWrite": 0
 			},
 			"contextWindow": 262144,
@@ -38279,6 +38756,31 @@
 				"maxLevel": "high"
 			}
 		},
+		"qwen/qwen3.6-plus:free": {
+			"id": "qwen/qwen3.6-plus:free",
+			"name": "Qwen: Qwen3.6 Plus (free)",
+			"api": "openai-completions",
+			"provider": "openrouter",
+			"baseUrl": "https://openrouter.ai/api/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1000000,
+			"maxTokens": 65536,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
+		},
 		"qwen/qwq-32b": {
 			"id": "qwen/qwq-32b",
 			"name": "Qwen: QwQ 32B",
@@ -39174,7 +39676,7 @@
 		},
 		"z-ai/glm-5v-turbo": {
 			"id": "z-ai/glm-5v-turbo",
-			"name": "Z.ai: GLM 5V Turbo",
+			"name": "GLM 5V Turbo",
 			"api": "openai-completions",
 			"provider": "openrouter",
 			"baseUrl": "https://openrouter.ai/api/v1",
@@ -39189,8 +39691,8 @@
 				"cacheRead": 0.24,
 				"cacheWrite": 0
 			},
-			"contextWindow": 202752,
-			"maxTokens": 131072,
+			"contextWindow": 200000,
+			"maxTokens": 128000,
 			"thinking": {
 				"mode": "effort",
 				"minLevel": "minimal",
@@ -39813,6 +40315,28 @@
 				"supportsUsageInStreaming": false
 			}
 		},
+		"arcee-trinity-large-thinking": {
+			"id": "arcee-trinity-large-thinking",
+			"name": "arcee-trinity-large-thinking",
+			"api": "openai-completions",
+			"provider": "venice",
+			"baseUrl": "https://api.venice.ai/api/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 222222,
+			"maxTokens": 8888,
+			"compat": {
+				"supportsUsageInStreaming": false
+			}
+		},
 		"claude-opus-4-5": {
 			"id": "claude-opus-4-5",
 			"name": "Claude Opus 4.5 (latest)",
@@ -40351,6 +40875,50 @@
 				"supportsUsageInStreaming": false
 			}
 		},
+		"google.gemma-4-26b-a4b-it": {
+			"id": "google.gemma-4-26b-a4b-it",
+			"name": "google.gemma-4-26b-a4b-it",
+			"api": "openai-completions",
+			"provider": "venice",
+			"baseUrl": "https://api.venice.ai/api/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 222222,
+			"maxTokens": 8888,
+			"compat": {
+				"supportsUsageInStreaming": false
+			}
+		},
+		"google.gemma-4-31b-it": {
+			"id": "google.gemma-4-31b-it",
+			"name": "google.gemma-4-31b-it",
+			"api": "openai-completions",
+			"provider": "venice",
+			"baseUrl": "https://api.venice.ai/api/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 222222,
+			"maxTokens": 8888,
+			"compat": {
+				"supportsUsageInStreaming": false
+			}
+		},
 		"grok-4-20-beta": {
 			"id": "grok-4-20-beta",
 			"name": "grok-4-20-beta",
@@ -45167,6 +45735,31 @@
 				"minLevel": "minimal",
 				"maxLevel": "xhigh"
 			}
+		},
+		"glm-5v-turbo": {
+			"id": "glm-5v-turbo",
+			"name": "glm-5v-turbo",
+			"api": "anthropic-messages",
+			"provider": "zai",
+			"baseUrl": "https://api.z.ai/api/anthropic",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 200000,
+			"maxTokens": 131072,
+			"thinking": {
+				"mode": "budget",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
 		}
 	},
 	"zenmux": {
@@ -45514,7 +46107,7 @@
 				"cacheRead": 0.056,
 				"cacheWrite": 0
 			},
-			"contextWindow": 128000,
+			"contextWindow": 163840,
 			"maxTokens": 8888
 		},
 		"deepseek/deepseek-r1-0528": {
@@ -46089,7 +46682,7 @@
 		},
 		"kuaishou/kat-coder-pro-v2": {
 			"id": "kuaishou/kat-coder-pro-v2",
-			"name": "KwaiKAT: KAT-Coder-Pro-V2",
+			"name": "KAT-Coder-Pro-V2",
 			"api": "openai-completions",
 			"provider": "zenmux",
 			"baseUrl": "https://zenmux.ai/api/v1",
@@ -46104,7 +46697,7 @@
 				"cacheWrite": 0
 			},
 			"contextWindow": 256000,
-			"maxTokens": 8888
+			"maxTokens": 80000
 		},
 		"meta/llama-3.3-70b-instruct": {
 			"id": "meta/llama-3.3-70b-instruct",
@@ -46344,7 +46937,7 @@
 				"cacheRead": 0.2,
 				"cacheWrite": 0.003
 			},
-			"contextWindow": 128000,
+			"contextWindow": 32768,
 			"maxTokens": 8888
 		},
 		"moonshotai/kimi-k2-0905": {
@@ -47258,6 +47851,30 @@
 				"maxLevel": "high"
 			}
 		},
+		"qwen/qwen3.6-plus": {
+			"id": "qwen/qwen3.6-plus",
+			"name": "Qwen3.6-Plus",
+			"api": "openai-completions",
+			"provider": "zenmux",
+			"baseUrl": "https://zenmux.ai/api/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.5,
+				"output": 3,
+				"cacheRead": 0.05,
+				"cacheWrite": 0.625
+			},
+			"contextWindow": 1000000,
+			"maxTokens": 64000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
+		},
 		"sapiens-ai/agnes-1.5-lite": {
 			"id": "sapiens-ai/agnes-1.5-lite",
 			"name": "Sapiens AI: Agnes-1.5-Lite",
@@ -48111,6 +48728,31 @@
 				"minLevel": "minimal",
 				"maxLevel": "xhigh"
 			}
+		},
+		"z-ai/glm-5v-turbo": {
+			"id": "z-ai/glm-5v-turbo",
+			"name": "GLM 5V Turbo",
+			"api": "openai-completions",
+			"provider": "zenmux",
+			"baseUrl": "https://zenmux.ai/api/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.726,
+				"output": 3.1946,
+				"cacheRead": 0.1743,
+				"cacheWrite": 0
+			},
+			"contextWindow": 200000,
+			"maxTokens": 128000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
 		}
 	}
 }

package/src/provider-models/openai-compat.ts

@@ -1519,9 +1519,9 @@ export function githubCopilotModelManagerOptions(config?: GithubCopilotModelMana
 						const contextWindow = toPositiveNumber(
 							entry.context_length,
 							toPositiveNumber(
-								copilotLimits.maxPromptTokens,
+								copilotLimits.maxContextWindowTokens,
 								toPositiveNumber(
-									copilotLimits.maxContextWindowTokens,
+									copilotLimits.maxPromptTokens,
 									reference?.contextWindow ?? defaults.contextWindow,
 								),
 							),

package/src/providers/anthropic.ts

@@ -415,6 +415,7 @@ export type AnthropicClientOptionsResult = {
 	maxRetries: number;
 	dangerouslyAllowBrowser: boolean;
 	defaultHeaders: Record<string, string>;
+	logLevel: AnthropicSdkClientOptions["logLevel"];
 	fetchOptions?: AnthropicSdkClientOptions["fetchOptions"];
 };
 
@@ -557,6 +558,10 @@ function mergeHeaders(...headerSources: (Record<string, string> | undefined)[]):
 	return merged;
 }
 
+// The Anthropic SDK logs malformed SSE frames directly before rethrowing them.
+// We surface the resulting provider error ourselves, so keep the SDK quiet.
+const ANTHROPIC_SDK_LOG_LEVEL = "off" as const;
+
 const PROVIDER_MAX_RETRIES = 3;
 const PROVIDER_BASE_DELAY_MS = 2000;
 
@@ -1024,6 +1029,7 @@ export function buildAnthropicClientOptions(args: AnthropicClientOptionsArgs): A
 			maxRetries: 5,
 			dangerouslyAllowBrowser: true,
 			defaultHeaders,
+			logLevel: ANTHROPIC_SDK_LOG_LEVEL,
 			...(tlsFetchOptions ? { fetchOptions: tlsFetchOptions } : {}),
 		};
 	}
@@ -1050,6 +1056,7 @@ export function buildAnthropicClientOptions(args: AnthropicClientOptionsArgs): A
 		maxRetries: 5,
 		dangerouslyAllowBrowser: true,
 		defaultHeaders,
+		logLevel: ANTHROPIC_SDK_LOG_LEVEL,
 		...(tlsFetchOptions ? { fetchOptions: tlsFetchOptions } : {}),
 	};
 }

package/src/stream.ts

@@ -78,6 +78,7 @@ const serviceProviderMap: Record<string, KeyResolver> = {
 	"opencode-go": "OPENCODE_API_KEY",
 	"opencode-zen": "OPENCODE_API_KEY",
 	cursor: "CURSOR_ACCESS_TOKEN",
+	"openai-codex": "OPENAI_CODEX_OAUTH_TOKEN",
 	"azure-openai-responses": "AZURE_OPENAI_API_KEY",
 	exa: "EXA_API_KEY",
 	jina: "JINA_API_KEY",