ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(coding-agent): replace model registry with model runtime

Browse Source 
Move provider auth and OAuth flows onto pi-ai Models, compose models.json and extension overlays through ModelRuntime, and retain ModelRegistry as an extension compatibility facade.
This commit is contained in:
Mario Zechner
2026-07-14 17:48:45 +02:00
parent 6731a0ba9e
commit 9993c96907
133 changed files with 5103 additions and 4340 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/src/providers/vercel-ai-gateway.models.ts
+36 -138
View File
@@ -497,23 +497,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 200000,
maxTokens: 4096,
} satisfies Model<"anthropic-messages">,
"anthropic/claude-3.5-haiku": {
id: "anthropic/claude-3.5-haiku",
name: "Claude 3.5 Haiku",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.8,
output: 4,
cacheRead: 0.08,
cacheWrite: 1,
},
contextWindow: 200000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"anthropic/claude-fable-5": {
id: "anthropic/claude-fable-5",
name: "Claude Fable 5",
@@ -565,7 +548,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cacheWrite: 18.75,
},
contextWindow: 200000,
maxTokens: 32000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"anthropic/claude-opus-4.1": {
id: "anthropic/claude-opus-4.1",
@@ -673,7 +656,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cacheWrite: 3.75,
},
contextWindow: 1000000,
maxTokens: 64000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"anthropic/claude-sonnet-4.5": {
id: "anthropic/claude-sonnet-4.5",
@@ -730,23 +713,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"arcee-ai/trinity-large-preview": {
id: "arcee-ai/trinity-large-preview",
name: "Trinity Large Preview",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
input: ["text"],
cost: {
input: 0.25,
output: 1,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131000,
maxTokens: 131000,
} satisfies Model<"anthropic-messages">,
"arcee-ai/trinity-large-thinking": {
id: "arcee-ai/trinity-large-thinking",
name: "Trinity Large Thinking",
@@ -875,12 +841,12 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.6,
output: 1.7,
cacheRead: 0,
input: 0.21,
output: 0.79,
cacheRead: 0.13,
cacheWrite: 0,
},
contextWindow: 128000,
contextWindow: 163840,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"deepseek/deepseek-v3.1-terminus": {
@@ -945,7 +911,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.14,
output: 0.28,
cacheRead: 0.0028,
cacheRead: 0.028,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -1206,6 +1172,23 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 1000000,
maxTokens: 32000,
} satisfies Model<"anthropic-messages">,
"kwaipilot/kat-coder-air-v2.5": {
id: "kwaipilot/kat-coder-air-v2.5",
name: "Kat Coder Air V2.5",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0.03,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 80000,
} satisfies Model<"anthropic-messages">,
"kwaipilot/kat-coder-pro-v1": {
id: "kwaipilot/kat-coder-pro-v1",
name: "KAT-Coder-Pro V1",
@@ -1240,39 +1223,22 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 256000,
maxTokens: 256000,
} satisfies Model<"anthropic-messages">,
"meituan/longcat-flash-chat": {
id: "meituan/longcat-flash-chat",
name: "LongCat Flash Chat",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 100000,
} satisfies Model<"anthropic-messages">,
"meituan/longcat-flash-thinking-2601": {
id: "meituan/longcat-flash-thinking-2601",
name: "LongCat Flash Thinking 2601",
"kwaipilot/kat-coder-pro-v2.5": {
id: "kwaipilot/kat-coder-pro-v2.5",
name: "Kat Coder Pro V2.5",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
input: 0.74,
output: 2.96,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 32768,
contextWindow: 256000,
maxTokens: 80000,
} satisfies Model<"anthropic-messages">,
"meta/llama-3.1-70b": {
id: "meta/llama-3.1-70b",
@@ -1400,7 +1366,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
input: ["text", "image"],
cost: {
input: 1.25,
output: 4.25,
@@ -1580,23 +1546,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 256000,
maxTokens: 256000,
} satisfies Model<"anthropic-messages">,
"mistral/devstral-small": {
id: "mistral/devstral-small",
name: "Devstral Small 1.1",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
input: ["text"],
cost: {
input: 0.1,
output: 0.3,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 64000,
} satisfies Model<"anthropic-messages">,
"mistral/devstral-small-2": {
id: "mistral/devstral-small-2",
name: "Devstral Small 2",
@@ -1801,23 +1750,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 128000,
maxTokens: 4000,
} satisfies Model<"anthropic-messages">,
"mistral/pixtral-large": {
id: "mistral/pixtral-large",
name: "Pixtral Large",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
input: ["text", "image"],
cost: {
input: 2,
output: 6,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4000,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2": {
id: "moonshotai/kimi-k2",
name: "Kimi K2 Instruct",
@@ -2972,40 +2904,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 256000,
maxTokens: 256000,
} satisfies Model<"anthropic-messages">,
"xiaomi/mimo-v2-flash": {
id: "xiaomi/mimo-v2-flash",
name: "MiMo V2 Flash",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 0.1,
output: 0.3,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 32000,
} satisfies Model<"anthropic-messages">,
"xiaomi/mimo-v2-pro": {
id: "xiaomi/mimo-v2-pro",
name: "MiMo V2 Pro",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 1,
output: 3,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"xiaomi/mimo-v2.5": {
id: "xiaomi/mimo-v2.5",
name: "MiMo M2.5",
@@ -3270,9 +3168,9 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 3,
output: 10.25,
cacheRead: 0.5,
input: 2.1,
output: 6.6,
cacheRead: 0.21,
cacheWrite: 0,
},
contextWindow: 1000000,