@oh-my-pi/pi-ai 13.17.1 → 13.17.5

package/CHANGELOG.md

@@ -2,6 +2,23 @@
 
 ## [Unreleased]
 
+## [13.17.5] - 2026-04-01
+### Changed
+
+- Increased default first-event timeout from 15s to 45s to better accommodate longer request setup times
+- Modified first-event watchdog to inherit idle timeout when it exceeds the default, ensuring consistent timeout behavior across different configurations
+
+### Fixed
+
+- Fixed first-event watchdog initialization timing so it no longer starts before the actual stream request is created, preventing premature timeouts during request setup
+- Fixed first-event watchdog timing so OpenAI-family providers no longer count slow request setup against the first streamed event timeout, and raised the default first-event timeout to avoid false aborts after long tool turns
+
+## [13.17.2] - 2026-04-01
+
+### Fixed
+
+- Fixed OpenAI-family first-event timeouts to preserve provider-specific timeout errors for retry classification instead of flattening them to generic aborts ([#591](https://github.com/can1357/oh-my-pi/issues/591))
+
 ## [13.17.1] - 2026-04-01
 
 ### Added

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-ai",
-	"version": "13.17.1",
+	"version": "13.17.5",
 	"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": "13.17.1",
+		"@oh-my-pi/pi-utils": "13.17.5",
 		"@sinclair/typebox": "^0.34",
 		"@smithy/node-http-handler": "^4.4",
 		"ajv": "^8.18",

package/src/models.json

@@ -8117,7 +8117,7 @@
 		},
 		"anthropic/claude-opus-4": {
 			"id": "anthropic/claude-opus-4",
-			"name": "Claude Opus 4",
+			"name": "Claude Opus 4 (latest)",
 			"api": "openai-completions",
 			"provider": "kilo",
 			"baseUrl": "https://api.kilo.ai/api/gateway",
@@ -8133,7 +8133,7 @@
 				"cacheWrite": 0
 			},
 			"contextWindow": 200000,
-			"maxTokens": 64000,
+			"maxTokens": 32000,
 			"thinking": {
 				"mode": "effort",
 				"minLevel": "minimal",
@@ -8366,6 +8366,25 @@
 			"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": "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
+		},
 		"arcee-ai/trinity-mini": {
 			"id": "arcee-ai/trinity-mini",
 			"name": "Arcee AI: Trinity Mini",
@@ -9233,7 +9252,7 @@
 		},
 		"google/gemini-3-pro-image-preview": {
 			"id": "google/gemini-3-pro-image-preview",
-			"name": "Gemini 3 Pro Image Preview",
+			"name": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)",
 			"api": "openai-completions",
 			"provider": "kilo",
 			"baseUrl": "https://api.kilo.ai/api/gateway",
@@ -9248,8 +9267,8 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": 1048000,
-			"maxTokens": 64000,
+			"contextWindow": 222222,
+			"maxTokens": 8888,
 			"thinking": {
 				"mode": "effort",
 				"minLevel": "low",
@@ -9485,6 +9504,44 @@
 			"contextWindow": 128000,
 			"maxTokens": 4096
 		},
+		"google/lyria-3-clip-preview": {
+			"id": "google/lyria-3-clip-preview",
+			"name": "Google: Lyria 3 Clip Preview",
+			"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/lyria-3-pro-preview": {
+			"id": "google/lyria-3-pro-preview",
+			"name": "Google: Lyria 3 Pro Preview",
+			"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
+		},
 		"gryphe/mythomax-l2-13b": {
 			"id": "gryphe/mythomax-l2-13b",
 			"name": "MythoMax 13B",
@@ -13813,6 +13870,25 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"qwen/qwen3.6-plus-preview:free": {
+			"id": "qwen/qwen3.6-plus-preview:free",
+			"name": "Qwen: Qwen3.6 Plus Preview (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",
@@ -13870,6 +13946,44 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"rekaai/reka-edge": {
+			"id": "rekaai/reka-edge",
+			"name": "Reka Edge",
+			"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
+		},
+		"rekaai/reka-flash-3": {
+			"id": "rekaai/reka-flash-3",
+			"name": "Reka Flash 3",
+			"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
+		},
 		"relace/relace-apply-3": {
 			"id": "relace/relace-apply-3",
 			"name": "Relace: Relace Apply 3",
@@ -14382,6 +14496,25 @@
 				"maxLevel": "xhigh"
 			}
 		},
+		"x-ai/grok-4.20": {
+			"id": "x-ai/grok-4.20",
+			"name": "xAI: Grok 4.20",
+			"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
+		},
 		"x-ai/grok-4.20-beta": {
 			"id": "x-ai/grok-4.20-beta",
 			"name": "xAI: Grok 4.20 Beta",
@@ -14401,6 +14534,25 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"x-ai/grok-4.20-multi-agent": {
+			"id": "x-ai/grok-4.20-multi-agent",
+			"name": "xAI: Grok 4.20 Multi-Agent",
+			"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
+		},
 		"x-ai/grok-4.20-multi-agent-beta": {
 			"id": "x-ai/grok-4.20-multi-agent-beta",
 			"name": "xAI: Grok 4.20 Multi-Agent Beta",
@@ -14446,7 +14598,7 @@
 		},
 		"x-ai/grok-code-fast-1:optimized:free": {
 			"id": "x-ai/grok-code-fast-1:optimized:free",
-			"name": "xAI: Grok Code Fast 1 Optimized (experimental, free)",
+			"name": "xAI: Grok Code Fast 1 Optimized (free)",
 			"api": "openai-completions",
 			"provider": "kilo",
 			"baseUrl": "https://api.kilo.ai/api/gateway",
@@ -14814,6 +14966,25 @@
 				"minLevel": "minimal",
 				"maxLevel": "xhigh"
 			}
+		},
+		"z-ai/glm-5v-turbo": {
+			"id": "z-ai/glm-5v-turbo",
+			"name": "Z.ai: GLM 5V Turbo",
+			"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
 		}
 	},
 	"kimi-code": {
@@ -17444,25 +17615,55 @@
 			"contextWindow": 128000,
 			"maxTokens": 16384
 		},
+		"mistral-small-2603": {
+			"id": "mistral-small-2603",
+			"name": "Mistral Small 4",
+			"api": "openai-completions",
+			"provider": "mistral",
+			"baseUrl": "https://api.mistral.ai/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.15,
+				"output": 0.6,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 256000,
+			"maxTokens": 256000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
+		},
 		"mistral-small-latest": {
 			"id": "mistral-small-latest",
 			"name": "Mistral Small (latest)",
 			"api": "openai-completions",
 			"provider": "mistral",
 			"baseUrl": "https://api.mistral.ai/v1",
-			"reasoning": false,
+			"reasoning": true,
 			"input": [
 				"text",
 				"image"
 			],
 			"cost": {
-				"input": 0.1,
-				"output": 0.3,
+				"input": 0.15,
+				"output": 0.6,
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": 128000,
-			"maxTokens": 16384
+			"contextWindow": 256000,
+			"maxTokens": 256000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
 		},
 		"open-mistral-7b": {
 			"id": "open-mistral-7b",
@@ -17930,6 +18131,25 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"anthropic/claude-haiku-latest": {
+			"id": "anthropic/claude-haiku-latest",
+			"name": "anthropic/claude-haiku-latest",
+			"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
+		},
 		"anthropic/claude-opus-4.6": {
 			"id": "anthropic/claude-opus-4.6",
 			"name": "Claude Opus 4.6",
@@ -17955,6 +18175,25 @@
 				"maxLevel": "xhigh"
 			}
 		},
+		"anthropic/claude-opus-latest": {
+			"id": "anthropic/claude-opus-latest",
+			"name": "anthropic/claude-opus-latest",
+			"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
+		},
 		"anthropic/claude-sonnet-4.6": {
 			"id": "anthropic/claude-sonnet-4.6",
 			"name": "Claude Sonnet 4.6",
@@ -17980,6 +18219,25 @@
 				"maxLevel": "xhigh"
 			}
 		},
+		"anthropic/claude-sonnet-latest": {
+			"id": "anthropic/claude-sonnet-latest",
+			"name": "anthropic/claude-sonnet-latest",
+			"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
+		},
 		"arcee-ai/trinity-large": {
 			"id": "arcee-ai/trinity-large",
 			"name": "arcee-ai/trinity-large",
@@ -21532,6 +21790,63 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"google/gemini-flash-latest": {
+			"id": "google/gemini-flash-latest",
+			"name": "google/gemini-flash-latest",
+			"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
+		},
+		"google/gemini-flash-lite-latest": {
+			"id": "google/gemini-flash-lite-latest",
+			"name": "google/gemini-flash-lite-latest",
+			"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
+		},
+		"google/gemini-pro-latest": {
+			"id": "google/gemini-pro-latest",
+			"name": "google/gemini-pro-latest",
+			"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
+		},
 		"grok-3-beta": {
 			"id": "grok-3-beta",
 			"name": "grok-3-beta",
@@ -21627,6 +21942,30 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"holo3-35b-a3b": {
+			"id": "holo3-35b-a3b",
+			"name": "holo3-35b-a3b",
+			"api": "openai-completions",
+			"provider": "nanogpt",
+			"baseUrl": "https://nano-gpt.com/api/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 222222,
+			"maxTokens": 8888,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
+		},
 		"huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated": {
 			"id": "huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated",
 			"name": "huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated",
@@ -25170,6 +25509,25 @@
 				"maxLevel": "xhigh"
 			}
 		},
+		"openai/gpt-latest": {
+			"id": "openai/gpt-latest",
+			"name": "openai/gpt-latest",
+			"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
+		},
 		"openai/gpt-oss-120b": {
 			"id": "openai/gpt-oss-120b",
 			"name": "GPT OSS 120B",
@@ -26429,6 +26787,44 @@
 				"maxLevel": "high"
 			}
 		},
+		"qwen3.5-omni-flash": {
+			"id": "qwen3.5-omni-flash",
+			"name": "qwen3.5-omni-flash",
+			"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
+		},
+		"qwen3.5-omni-plus": {
+			"id": "qwen3.5-omni-plus",
+			"name": "qwen3.5-omni-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
+		},
 		"qwq-32b": {
 			"id": "qwq-32b",
 			"name": "qwq-32b",
@@ -28145,6 +28541,25 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"x-ai/grok-4.20": {
+			"id": "x-ai/grok-4.20",
+			"name": "x-ai/grok-4.20",
+			"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
+		},
 		"x-ai/grok-4.20-beta-non-reasoning": {
 			"id": "x-ai/grok-4.20-beta-non-reasoning",
 			"name": "x-ai/grok-4.20-beta-non-reasoning",
@@ -28183,6 +28598,25 @@
 			"contextWindow": 222222,
 			"maxTokens": 8888
 		},
+		"x-ai/grok-4.20-multi-agent": {
+			"id": "x-ai/grok-4.20-multi-agent",
+			"name": "x-ai/grok-4.20-multi-agent",
+			"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
+		},
 		"x-ai/grok-4.20-multi-agent-beta": {
 			"id": "x-ai/grok-4.20-multi-agent-beta",
 			"name": "x-ai/grok-4.20-multi-agent-beta",
@@ -30682,6 +31116,26 @@
 				"maxLevel": "xhigh"
 			}
 		},
+		"gpt-5.3-chat-latest": {
+			"id": "gpt-5.3-chat-latest",
+			"name": "GPT-5.3 Chat (latest)",
+			"api": "openai-responses",
+			"provider": "openai",
+			"baseUrl": "https://api.openai.com/v1",
+			"reasoning": false,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 1.75,
+				"output": 14,
+				"cacheRead": 0.175,
+				"cacheWrite": 0
+			},
+			"contextWindow": 128000,
+			"maxTokens": 16384
+		},
 		"gpt-5.3-codex": {
 			"id": "gpt-5.3-codex",
 			"name": "GPT-5.3 Codex",
@@ -32616,6 +33070,30 @@
 				"maxLevel": "xhigh"
 			}
 		},
+		"qwen3.6-plus-free": {
+			"id": "qwen3.6-plus-free",
+			"name": "Qwen3.6 Plus Free",
+			"api": "openai-completions",
+			"provider": "opencode-zen",
+			"baseUrl": "https://opencode.ai/zen/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1048576,
+			"maxTokens": 64000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
+		},
 		"trinity-large-preview-free": {
 			"id": "trinity-large-preview-free",
 			"name": "Trinity Large Preview",
@@ -32947,7 +33425,7 @@
 		},
 		"anthropic/claude-opus-4": {
 			"id": "anthropic/claude-opus-4",
-			"name": "Claude Opus 4",
+			"name": "Claude Opus 4 (latest)",
 			"api": "openai-completions",
 			"baseUrl": "https://openrouter.ai/api/v1",
 			"provider": "openrouter",
@@ -32963,7 +33441,7 @@
 				"cacheWrite": 18.75
 			},
 			"contextWindow": 200000,
-			"maxTokens": 64000,
+			"maxTokens": 32000,
 			"thinking": {
 				"mode": "effort",
 				"minLevel": "minimal",
@@ -33142,6 +33620,30 @@
 				"supportsToolChoice": false
 			}
 		},
+		"arcee-ai/trinity-large-thinking": {
+			"id": "arcee-ai/trinity-large-thinking",
+			"name": "Arcee AI: Trinity Large Thinking",
+			"api": "openai-completions",
+			"provider": "openrouter",
+			"baseUrl": "https://openrouter.ai/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": "high"
+			}
+		},
 		"arcee-ai/trinity-mini": {
 			"id": "arcee-ai/trinity-mini",
 			"name": "Arcee AI: Trinity Mini",
@@ -34377,9 +34879,9 @@
 				"text"
 			],
 			"cost": {
-				"input": 0.19,
-				"output": 1.15,
-				"cacheRead": 0.095,
+				"input": 0.12,
+				"output": 1,
+				"cacheRead": 0.06,
 				"cacheWrite": 0
 			},
 			"contextWindow": 204800,
@@ -36211,6 +36713,44 @@
 				"maxLevel": "xhigh"
 			}
 		},
+		"openai/gpt-audio": {
+			"id": "openai/gpt-audio",
+			"name": "OpenAI: GPT Audio",
+			"api": "openai-completions",
+			"provider": "openrouter",
+			"baseUrl": "https://openrouter.ai/api/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 2.5,
+				"output": 10,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 128000,
+			"maxTokens": 16384
+		},
+		"openai/gpt-audio-mini": {
+			"id": "openai/gpt-audio-mini",
+			"name": "OpenAI: GPT Audio Mini",
+			"api": "openai-completions",
+			"provider": "openrouter",
+			"baseUrl": "https://openrouter.ai/api/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.6,
+				"output": 2.4,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 128000,
+			"maxTokens": 16384
+		},
 		"openai/gpt-oss-120b": {
 			"id": "openai/gpt-oss-120b",
 			"name": "GPT OSS 120B",
@@ -37658,7 +38198,7 @@
 				"cacheWrite": 0
 			},
 			"contextWindow": 256000,
-			"maxTokens": 65536,
+			"maxTokens": 32768,
 			"thinking": {
 				"mode": "effort",
 				"minLevel": "minimal",
@@ -37715,6 +38255,30 @@
 				"maxLevel": "high"
 			}
 		},
+		"qwen/qwen3.6-plus-preview:free": {
+			"id": "qwen/qwen3.6-plus-preview:free",
+			"name": "Qwen: Qwen3.6 Plus Preview (free)",
+			"api": "openai-completions",
+			"provider": "openrouter",
+			"baseUrl": "https://openrouter.ai/api/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1000000,
+			"maxTokens": 32000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
+		},
 		"qwen/qwq-32b": {
 			"id": "qwen/qwq-32b",
 			"name": "Qwen: QwQ 32B",
@@ -37759,6 +38323,26 @@
 			"contextWindow": 16384,
 			"maxTokens": 16384
 		},
+		"rekaai/reka-edge": {
+			"id": "rekaai/reka-edge",
+			"name": "Reka Edge",
+			"api": "openai-completions",
+			"provider": "openrouter",
+			"baseUrl": "https://openrouter.ai/api/v1",
+			"reasoning": false,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.09999999999999999,
+				"output": 0.09999999999999999,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 16384,
+			"maxTokens": 16384
+		},
 		"relace/relace-search": {
 			"id": "relace/relace-search",
 			"name": "Relace: Relace Search",
@@ -38160,6 +38744,31 @@
 				"maxLevel": "high"
 			}
 		},
+		"x-ai/grok-4.20": {
+			"id": "x-ai/grok-4.20",
+			"name": "xAI: Grok 4.20",
+			"api": "openai-completions",
+			"provider": "openrouter",
+			"baseUrl": "https://openrouter.ai/api/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 2,
+				"output": 6,
+				"cacheRead": 0.19999999999999998,
+				"cacheWrite": 0
+			},
+			"contextWindow": 2000000,
+			"maxTokens": 8888,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
+		},
 		"x-ai/grok-4.20-beta": {
 			"id": "x-ai/grok-4.20-beta",
 			"name": "xAI: Grok 4.20 Beta",
@@ -38562,6 +39171,31 @@
 				"minLevel": "minimal",
 				"maxLevel": "high"
 			}
+		},
+		"z-ai/glm-5v-turbo": {
+			"id": "z-ai/glm-5v-turbo",
+			"name": "Z.ai: GLM 5V Turbo",
+			"api": "openai-completions",
+			"provider": "openrouter",
+			"baseUrl": "https://openrouter.ai/api/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 1.2,
+				"output": 4,
+				"cacheRead": 0.24,
+				"cacheWrite": 0
+			},
+			"contextWindow": 202752,
+			"maxTokens": 131072,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
 		}
 	},
 	"qianfan": {
@@ -38968,6 +39602,25 @@
 			},
 			"contextWindow": 196608,
 			"maxTokens": 8192
+		},
+		"hf:zai-org/GLM-5": {
+			"id": "hf:zai-org/GLM-5",
+			"name": "zai-org/GLM-5",
+			"api": "openai-completions",
+			"provider": "synthetic",
+			"baseUrl": "https://api.synthetic.new/openai/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 196608,
+			"maxTokens": 8192
 		}
 	},
 	"together": {
@@ -41077,7 +41730,7 @@
 		},
 		"anthropic/claude-opus-4": {
 			"id": "anthropic/claude-opus-4",
-			"name": "Claude Opus 4",
+			"name": "Claude Opus 4 (latest)",
 			"api": "anthropic-messages",
 			"baseUrl": "https://ai-gateway.vercel.sh",
 			"provider": "vercel-ai-gateway",
@@ -41093,7 +41746,7 @@
 				"cacheWrite": 18.75
 			},
 			"contextWindow": 200000,
-			"maxTokens": 64000,
+			"maxTokens": 32000,
 			"thinking": {
 				"mode": "budget",
 				"minLevel": "minimal",
@@ -44620,7 +45273,7 @@
 				"cacheWrite": 18.75
 			},
 			"contextWindow": 200000,
-			"maxTokens": 64000,
+			"maxTokens": 32000,
 			"thinking": {
 				"mode": "budget",
 				"minLevel": "minimal",
@@ -45434,6 +46087,25 @@
 			"contextWindow": 256000,
 			"maxTokens": 64000
 		},
+		"kuaishou/kat-coder-pro-v2": {
+			"id": "kuaishou/kat-coder-pro-v2",
+			"name": "KwaiKAT: KAT-Coder-Pro-V2",
+			"api": "openai-completions",
+			"provider": "zenmux",
+			"baseUrl": "https://zenmux.ai/api/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.3,
+				"output": 1.2,
+				"cacheRead": 0.06,
+				"cacheWrite": 0
+			},
+			"contextWindow": 256000,
+			"maxTokens": 8888
+		},
 		"meta/llama-3.3-70b-instruct": {
 			"id": "meta/llama-3.3-70b-instruct",
 			"name": "Llama 3.3 70b Instruct",
@@ -46531,7 +47203,7 @@
 				"input": 0.2,
 				"output": 1.6,
 				"cacheRead": 0.04,
-				"cacheWrite": 0
+				"cacheWrite": 0.25
 			},
 			"contextWindow": 262144,
 			"maxTokens": 8888,

package/src/providers/azure-openai-responses.ts

@@ -18,6 +18,7 @@ import {
 	type Tool,
 	type ToolChoice,
 } from "../types";
+import { createAbortSourceTracker } from "../utils/abort";
 import { AssistantMessageEventStream } from "../utils/event-stream";
 import { finalizeErrorMessage, type RawHttpRequestDump } from "../utils/http-inspector";
 import {
@@ -39,6 +40,8 @@ import {
 import { transformMessages } from "./transform-messages";
 
 const DEFAULT_AZURE_API_VERSION = "v1";
+const AZURE_OPENAI_RESPONSES_FIRST_EVENT_TIMEOUT_MESSAGE =
+	"Azure OpenAI responses stream timed out while waiting for the first event";
 
 function parseDeploymentNameMap(value: string | undefined): Map<string, string> {
 	const map = new Map<string, string>();
@@ -115,6 +118,9 @@ export const streamAzureOpenAIResponses: StreamFunction<"azure-openai-responses"
 			timestamp: Date.now(),
 		};
 		let rawRequestDump: RawHttpRequestDump | undefined;
+		const abortTracker = createAbortSourceTracker(options?.signal);
+		const firstEventTimeoutAbortError = new Error(AZURE_OPENAI_RESPONSES_FIRST_EVENT_TIMEOUT_MESSAGE);
+		const { requestAbortController, requestSignal } = abortTracker;
 
 		try {
 			// Create Azure OpenAI client
@@ -122,14 +128,7 @@ export const streamAzureOpenAIResponses: StreamFunction<"azure-openai-responses"
 			const client = createClient(model, apiKey, options);
 			const { baseUrl } = resolveAzureConfig(model, options);
 			const params = buildParams(model, context, options, deploymentName, baseUrl);
-			const requestAbortController = new AbortController();
-			const requestSignal = options?.signal
-				? AbortSignal.any([options.signal, requestAbortController.signal])
-				: requestAbortController.signal;
 			const idleTimeoutMs = getOpenAIStreamIdleTimeoutMs();
-			const firstEventWatchdog = createFirstEventWatchdog(getStreamFirstEventTimeoutMs(idleTimeoutMs), () =>
-				requestAbortController.abort(),
-			);
 			options?.onPayload?.(params);
 			rawRequestDump = {
 				provider: model.provider,
@@ -140,6 +139,9 @@ export const streamAzureOpenAIResponses: StreamFunction<"azure-openai-responses"
 				body: params,
 			};
 			const openaiStream = await client.responses.create(params, { signal: requestSignal });
+			const firstEventWatchdog = createFirstEventWatchdog(getStreamFirstEventTimeoutMs(idleTimeoutMs), () =>
+				abortTracker.abortLocally(firstEventTimeoutAbortError),
+			);
 			stream.push({ type: "start", partial: output });
 
 			await processResponsesStream(
@@ -158,7 +160,11 @@ export const streamAzureOpenAIResponses: StreamFunction<"azure-openai-responses"
 				},
 			);
 
-			if (options?.signal?.aborted) {
+			const firstEventTimeoutError = abortTracker.getLocalAbortReason();
+			if (firstEventTimeoutError) {
+				throw firstEventTimeoutError;
+			}
+			if (abortTracker.wasCallerAbort()) {
 				throw new Error("Request was aborted");
 			}
 
@@ -172,8 +178,9 @@ export const streamAzureOpenAIResponses: StreamFunction<"azure-openai-responses"
 			stream.end();
 		} catch (error) {
 			for (const block of output.content) delete (block as { index?: number }).index;
-			output.stopReason = options?.signal?.aborted ? "aborted" : "error";
-			output.errorMessage = await finalizeErrorMessage(error, rawRequestDump);
+			const firstEventTimeoutError = abortTracker.getLocalAbortReason();
+			output.stopReason = abortTracker.wasCallerAbort() ? "aborted" : "error";
+			output.errorMessage = firstEventTimeoutError?.message ?? (await finalizeErrorMessage(error, rawRequestDump));
 			output.duration = Date.now() - startTime;
 			if (firstTokenTime) output.ttft = firstTokenTime - startTime;
 			stream.push({ type: "error", reason: output.stopReason, error: output });

package/src/providers/openai-completions.ts

@@ -29,6 +29,7 @@ import {
 	type ToolChoice,
 	type ToolResultMessage,
 } from "../types";
+import { createAbortSourceTracker } from "../utils/abort";
 import { AssistantMessageEventStream } from "../utils/event-stream";
 import { finalizeErrorMessage, type RawHttpRequestDump } from "../utils/http-inspector";
 import {
@@ -162,6 +163,9 @@ function getTrailingPartialTag(text: string, tags: readonly string[]): string {
 	return text.slice(-maxLength);
 }
 
+const OPENAI_COMPLETIONS_FIRST_EVENT_TIMEOUT_MESSAGE =
+	"OpenAI completions stream timed out while waiting for the first event";
+
 export const streamOpenAICompletions: StreamFunction<"openai-completions"> = (
 	model: Model<"openai-completions">,
 	context: Context,
@@ -191,17 +195,13 @@ export const streamOpenAICompletions: StreamFunction<"openai-completions"> = (
 			timestamp: Date.now(),
 		};
 		let rawRequestDump: RawHttpRequestDump | undefined;
+		const abortTracker = createAbortSourceTracker(options?.signal);
+		const firstEventTimeoutAbortError = new Error(OPENAI_COMPLETIONS_FIRST_EVENT_TIMEOUT_MESSAGE);
+		const { requestAbortController, requestSignal } = abortTracker;
 
 		try {
 			const apiKey = options?.apiKey || getEnvApiKey(model.provider) || "";
-			const requestAbortController = new AbortController();
-			const requestSignal = options?.signal
-				? AbortSignal.any([options.signal, requestAbortController.signal])
-				: requestAbortController.signal;
 			const idleTimeoutMs = getOpenAIStreamIdleTimeoutMs();
-			const firstEventWatchdog = createFirstEventWatchdog(getStreamFirstEventTimeoutMs(idleTimeoutMs), () =>
-				requestAbortController.abort(),
-			);
 			const { client, copilotPremiumRequests, baseUrl } = await createClient(
 				model,
 				context,
@@ -220,6 +220,9 @@ export const streamOpenAICompletions: StreamFunction<"openai-completions"> = (
 				body: params,
 			};
 			const openaiStream = await client.chat.completions.create(params, { signal: requestSignal });
+			const firstEventWatchdog = createFirstEventWatchdog(getStreamFirstEventTimeoutMs(idleTimeoutMs), () =>
+				abortTracker.abortLocally(firstEventTimeoutAbortError),
+			);
 			if (copilotPremiumRequests !== undefined) output.usage.premiumRequests = copilotPremiumRequests;
 			stream.push({ type: "start", partial: output });
 
@@ -485,7 +488,11 @@ export const streamOpenAICompletions: StreamFunction<"openai-completions"> = (
 
 			finishCurrentBlock(currentBlock);
 
-			if (options?.signal?.aborted) {
+			const firstEventTimeoutError = abortTracker.getLocalAbortReason();
+			if (firstEventTimeoutError) {
+				throw firstEventTimeoutError;
+			}
+			if (abortTracker.wasCallerAbort()) {
 				throw new Error("Request was aborted");
 			}
 
@@ -502,8 +509,9 @@ export const streamOpenAICompletions: StreamFunction<"openai-completions"> = (
 			stream.end();
 		} catch (error) {
 			for (const block of output.content) delete (block as any).index;
-			output.stopReason = options?.signal?.aborted ? "aborted" : "error";
-			output.errorMessage = await finalizeErrorMessage(error, rawRequestDump);
+			const firstEventTimeoutError = abortTracker.getLocalAbortReason();
+			output.stopReason = abortTracker.wasCallerAbort() ? "aborted" : "error";
+			output.errorMessage = firstEventTimeoutError?.message ?? (await finalizeErrorMessage(error, rawRequestDump));
 			// Some providers via OpenRouter include extra details here.
 			const rawMetadata = (error as { error?: { metadata?: { raw?: string } } })?.error?.metadata?.raw;
 			if (rawMetadata) output.errorMessage += `\n${rawMetadata}`;

package/src/providers/openai-responses.ts

@@ -28,6 +28,7 @@ import {
 	resolveCacheRetention,
 	sanitizeOpenAIResponsesHistoryItemsForReplay,
 } from "../utils";
+import { createAbortSourceTracker } from "../utils/abort";
 import { AssistantMessageEventStream } from "../utils/event-stream";
 import { finalizeErrorMessage, type RawHttpRequestDump } from "../utils/http-inspector";
 import {
@@ -82,6 +83,8 @@ export interface OpenAIResponsesOptions extends StreamOptions {
 }
 
 const OPENAI_RESPONSES_PROVIDER_SESSION_STATE_PREFIX = "openai-responses:";
+const OPENAI_RESPONSES_FIRST_EVENT_TIMEOUT_MESSAGE =
+	"OpenAI responses stream timed out while waiting for the first event";
 
 interface OpenAIResponsesProviderSessionState extends ProviderSessionState {
 	nativeHistoryReplayWarmed: boolean;
@@ -161,6 +164,9 @@ export const streamOpenAIResponses: StreamFunction<"openai-responses"> = (
 			timestamp: Date.now(),
 		};
 		let rawRequestDump: RawHttpRequestDump | undefined;
+		const abortTracker = createAbortSourceTracker(options?.signal);
+		const firstEventTimeoutAbortError = new Error(OPENAI_RESPONSES_FIRST_EVENT_TIMEOUT_MESSAGE);
+		const { requestAbortController, requestSignal } = abortTracker;
 
 		try {
 			// Create OpenAI client
@@ -174,14 +180,7 @@ export const streamOpenAIResponses: StreamFunction<"openai-responses"> = (
 			);
 			const providerSessionState = getOpenAIResponsesProviderSessionState(model, options?.providerSessionState);
 			const { params } = buildParams(model, context, options, providerSessionState, baseUrl);
-			const requestAbortController = new AbortController();
-			const requestSignal = options?.signal
-				? AbortSignal.any([options.signal, requestAbortController.signal])
-				: requestAbortController.signal;
 			const idleTimeoutMs = getOpenAIStreamIdleTimeoutMs();
-			const firstEventWatchdog = createFirstEventWatchdog(getStreamFirstEventTimeoutMs(idleTimeoutMs), () =>
-				requestAbortController.abort(),
-			);
 			options?.onPayload?.(params);
 			rawRequestDump = {
 				provider: model.provider,
@@ -192,6 +191,9 @@ export const streamOpenAIResponses: StreamFunction<"openai-responses"> = (
 				body: params,
 			};
 			const openaiStream = await client.responses.create(params, { signal: requestSignal });
+			const firstEventWatchdog = createFirstEventWatchdog(getStreamFirstEventTimeoutMs(idleTimeoutMs), () =>
+				abortTracker.abortLocally(firstEventTimeoutAbortError),
+			);
 			if (copilotPremiumRequests !== undefined) output.usage.premiumRequests = copilotPremiumRequests;
 			stream.push({ type: "start", partial: output });
 
@@ -216,7 +218,11 @@ export const streamOpenAIResponses: StreamFunction<"openai-responses"> = (
 			);
 			if (copilotPremiumRequests !== undefined) output.usage.premiumRequests = copilotPremiumRequests;
 
-			if (options?.signal?.aborted) {
+			const firstEventTimeoutError = abortTracker.getLocalAbortReason();
+			if (firstEventTimeoutError) {
+				throw firstEventTimeoutError;
+			}
+			if (abortTracker.wasCallerAbort()) {
 				throw new Error("Request was aborted");
 			}
 
@@ -233,8 +239,9 @@ export const streamOpenAIResponses: StreamFunction<"openai-responses"> = (
 			stream.end();
 		} catch (error) {
 			for (const block of output.content) delete (block as { index?: number }).index;
-			output.stopReason = options?.signal?.aborted ? "aborted" : "error";
-			output.errorMessage = await finalizeErrorMessage(error, rawRequestDump);
+			const firstEventTimeoutError = abortTracker.getLocalAbortReason();
+			output.stopReason = abortTracker.wasCallerAbort() ? "aborted" : "error";
+			output.errorMessage = firstEventTimeoutError?.message ?? (await finalizeErrorMessage(error, rawRequestDump));
 			output.duration = Date.now() - startTime;
 			if (firstTokenTime) output.ttft = firstTokenTime - startTime;
 			stream.push({ type: "error", reason: output.stopReason, error: output });

package/src/utils/abort.ts

@@ -0,0 +1,36 @@
+export interface AbortSourceTracker {
+	requestAbortController: AbortController;
+	requestSignal: AbortSignal;
+	abortLocally(reason: Error): Error;
+	getLocalAbortReason(): Error | undefined;
+	wasCallerAbort(): boolean;
+}
+
+/**
+ * Tracks whether a merged request signal was aborted by the caller or by provider-local logic.
+ */
+export function createAbortSourceTracker(callerSignal?: AbortSignal): AbortSourceTracker {
+	const requestAbortController = new AbortController();
+	const requestSignal = callerSignal
+		? AbortSignal.any([callerSignal, requestAbortController.signal])
+		: requestAbortController.signal;
+	let localAbortReason: Error | undefined;
+
+	return {
+		requestAbortController,
+		requestSignal,
+		abortLocally(reason) {
+			localAbortReason = reason;
+			requestAbortController.abort(reason);
+			return reason;
+		},
+		getLocalAbortReason() {
+			if (!localAbortReason) return undefined;
+			return requestSignal.reason === localAbortReason ? localAbortReason : undefined;
+		},
+		wasCallerAbort() {
+			if (!callerSignal?.aborted) return false;
+			return requestSignal.reason !== localAbortReason;
+		},
+	};
+}

package/src/utils/idle-iterator.ts

@@ -1,7 +1,7 @@
 import { $env } from "@oh-my-pi/pi-utils";
 
 const DEFAULT_OPENAI_STREAM_IDLE_TIMEOUT_MS = 45_000;
-const DEFAULT_STREAM_FIRST_EVENT_TIMEOUT_MS = 15_000;
+const DEFAULT_STREAM_FIRST_EVENT_TIMEOUT_MS = 45_000;
 
 function normalizeIdleTimeoutMs(value: string | undefined, fallback: number): number | undefined {
 	if (value === undefined) return fallback;
@@ -22,14 +22,16 @@ export function getOpenAIStreamIdleTimeoutMs(): number | undefined {
 
 /**
  * Returns the timeout used while waiting for the first stream event.
+ * The first token can legitimately take longer than later inter-event gaps,
+ * so the default never undershoots the steady-state idle timeout.
  *
  * Set `PI_STREAM_FIRST_EVENT_TIMEOUT_MS=0` to disable the watchdog.
  */
 export function getStreamFirstEventTimeoutMs(idleTimeoutMs?: number): number | undefined {
-	const fallback = Math.min(
-		DEFAULT_STREAM_FIRST_EVENT_TIMEOUT_MS,
-		idleTimeoutMs ?? DEFAULT_STREAM_FIRST_EVENT_TIMEOUT_MS,
-	);
+	const fallback =
+		idleTimeoutMs === undefined
+			? DEFAULT_STREAM_FIRST_EVENT_TIMEOUT_MS
+			: Math.max(DEFAULT_STREAM_FIRST_EVENT_TIMEOUT_MS, idleTimeoutMs);
 	return normalizeIdleTimeoutMs($env.PI_STREAM_FIRST_EVENT_TIMEOUT_MS, fallback);
 }