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

Merge origin/main into model runtime changes

Browse Source
This commit is contained in:
Mario Zechner
2026-07-15 13:00:45 +02:00
parent bd9e09db44 dcfe36c797
commit 5e336cfa80
26 changed files with 244 additions and 163 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/src/api/openai-codex-responses.ts
+3 -2
View File
@@ -258,8 +258,9 @@ export const stream: StreamFunction<"openai-codex-responses", OpenAICodexRespons
if (nextBody !== undefined) {
body = nextBody as RequestBody;
}
const websocketRequestId = options?.sessionId || createCodexRequestId();
const sseHeaders = buildSSEHeaders(model.headers, options?.headers, accountId, apiKey, options?.sessionId);
const codexSessionId = clampOpenAIPromptCacheKey(options?.sessionId);
const websocketRequestId = codexSessionId || createCodexRequestId();
const sseHeaders = buildSSEHeaders(model.headers, options?.headers, accountId, apiKey, codexSessionId);
const websocketHeaders = buildWebSocketHeaders(
model.headers,
options?.headers,
packages/ai/src/providers/openrouter.models.ts
+57 -75
View File
@@ -462,24 +462,6 @@ export const OPENROUTER_MODELS = {
contextWindow: 262144,
maxTokens: 80000,
} satisfies Model<"openai-completions">,
"arcee-ai/trinity-mini": {
id: "arcee-ai/trinity-mini",
name: "Arcee AI: Trinity Mini",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
reasoning: true,
input: ["text"],
cost: {
input: 0.045,
output: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"arcee-ai/virtuoso-large": {
id: "arcee-ai/virtuoso-large",
name: "Arcee AI: Virtuoso Large",
@@ -688,8 +670,8 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.21,
output: 0.79,
input: 0.25,
output: 0.95,
cacheRead: 0.13,
cacheWrite: 0,
},
@@ -1122,13 +1104,13 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.12,
input: 0.06,
output: 0.35,
cacheRead: 0.09,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"google/gemma-4-31b-it:free": {
id: "google/gemma-4-31b-it:free",
@@ -1146,7 +1128,7 @@ export const OPENROUTER_MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 8192,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"ibm-granite/granite-4.1-8b": {
id: "ibm-granite/granite-4.1-8b",
@@ -1239,6 +1221,24 @@ export const OPENROUTER_MODELS = {
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"kwaipilot/kat-coder-air-v2.5": {
id: "kwaipilot/kat-coder-air-v2.5",
name: "Kwaipilot: KAT-Coder-Air V2.5",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
reasoning: false,
input: ["text"],
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0.03,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 80000,
} satisfies Model<"openai-completions">,
"kwaipilot/kat-coder-pro-v2": {
id: "kwaipilot/kat-coder-pro-v2",
name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -1257,23 +1257,23 @@ export const OPENROUTER_MODELS = {
contextWindow: 256000,
maxTokens: 80000,
} satisfies Model<"openai-completions">,
"liquid/lfm-2.5-1.2b-thinking:free": {
id: "liquid/lfm-2.5-1.2b-thinking:free",
name: "LiquidAI: LFM2.5-1.2B-Thinking (free)",
"kwaipilot/kat-coder-pro-v2.5": {
id: "kwaipilot/kat-coder-pro-v2.5",
name: "Kwaipilot: KAT-Coder-Pro V2.5",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
reasoning: true,
reasoning: false,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
input: 0.74,
output: 2.96,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 4096,
contextWindow: 256000,
maxTokens: 80000,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3.1-70b-instruct": {
id: "meta-llama/llama-3.1-70b-instruct",
@@ -1357,8 +1357,8 @@ export const OPENROUTER_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.15,
output: 0.6,
input: 0.2,
output: 0.8,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1866,7 +1866,7 @@ export const OPENROUTER_MODELS = {
cacheRead: 0.07,
cacheWrite: 0,
},
contextWindow: 256000,
contextWindow: 262144,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.6": {
@@ -1897,9 +1897,9 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.72,
input: 0.719,
output: 3.49,
cacheRead: 0.159,
cacheRead: 0.149,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -2457,11 +2457,11 @@ export const OPENROUTER_MODELS = {
cost: {
input: 0.05,
output: 0.4,
cacheRead: 0.01,
cacheRead: 0.005,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 4096,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"openai/gpt-5-pro": {
id: "openai/gpt-5-pro",
@@ -2493,7 +2493,7 @@ export const OPENROUTER_MODELS = {
cost: {
input: 1.25,
output: 10,
cacheRead: 0.13,
cacheRead: 0.125,
cacheWrite: 0,
},
contextWindow: 400000,
@@ -2977,26 +2977,8 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.036,
output: 0.18,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-120b:free": {
id: "openai/gpt-oss-120b:free",
name: "OpenAI: gpt-oss-120b (free)",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
compat: {"thinkingFormat":"openrouter"},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
input: 0.03,
output: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
@@ -3482,7 +3464,7 @@ export const OPENROUTER_MODELS = {
input: ["text"],
cost: {
input: 0.09,
output: 0.1,
output: 0.55,
cacheRead: 0,
cacheWrite: 0,
},
@@ -4075,13 +4057,13 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.285,
input: 0.289,
output: 2.4,
cacheRead: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262140,
maxTokens: 262140,
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-35b-a3b": {
id: "qwen/qwen3.6-35b-a3b",
@@ -4476,7 +4458,7 @@ export const OPENROUTER_MODELS = {
cacheRead: 0.028,
cacheWrite: 0,
},
contextWindow: 32000,
contextWindow: 262144,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"xiaomi/mimo-v2.5-pro": {
@@ -4562,12 +4544,12 @@ export const OPENROUTER_MODELS = {
input: ["text"],
cost: {
input: 0.43,
output: 1.74,
output: 1.75,
cacheRead: 0.08,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 131072,
contextWindow: 198000,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"z-ai/glm-4.6v": {
id: "z-ai/glm-4.6v",
@@ -4638,8 +4620,8 @@ export const OPENROUTER_MODELS = {
cacheRead: 0.119,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 4096,
contextWindow: 198000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"z-ai/glm-5-turbo": {
id: "z-ai/glm-5-turbo",
@@ -4688,9 +4670,9 @@ export const OPENROUTER_MODELS = {
thinkingLevelMap: {"xhigh":"xhigh"},
input: ["text"],
cost: {
input: 0.84,
output: 2.64,
cacheRead: 0.156,
input: 0.924,
output: 2.904,
cacheRead: 0.1716,
cacheWrite: 0,
},
contextWindow: 1024000,