getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-21 16:01:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Release v0.12.10

Browse source
This commit is contained in:
Mario Zechner 2025-12-04 20:51:57 +01:00
parent 47bb302155
commit c7585e37c9
15 changed files with 101 additions and 128 deletions
Download patch file Download diff file Expand all files Collapse all files

6
packages/ai/CHANGELOG.md
View file

@ -2,6 +2,12 @@
## [Unreleased]
## [0.12.10] - 2025-12-04
### Added
- Added `gpt-5.1-codex-max` model support
### Fixed
- **OpenAI Token Counting**: Fixed `usage.input` to exclude cached tokens for OpenAI providers. Previously, `input` included cached tokens, causing double-counting when calculating total context size via `input + cacheRead`. Now `input` represents non-cached input tokens across all providers, making `input + output + cacheRead + cacheWrite` the correct formula for total context size.

2
packages/ai/package.json
View file

@ -1,6 +1,6 @@
{
"name": "@mariozechner/pi-ai",
"version": "0.12.9",
"version": "0.12.10",
"description": "Unified LLM API with automatic model discovery and provider configuration",
"type": "module",
"main": "./dist/index.js",

20
packages/ai/scripts/generate-models.ts
View file

@ -344,6 +344,26 @@ async function generateModels() {
});
}
if (!allModels.some(m => m.provider === "openai" && m.id === "gpt-5.1-codex-max")) {
allModels.push({
id: "gpt-5.1-codex-max",
name: "GPT-5.1 Codex Max",
api: "openai-responses",
baseUrl: "https://api.openai.com/v1",
provider: "openai",
reasoning: true,
input: ["text", "image"],
cost: {
input: 1.25,
output: 10,
cacheRead: 0.125,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
});
}
// Add missing Grok models
if (!allModels.some(m => m.provider === "xai" && m.id === "grok-code-fast-1")) {
allModels.push({

112
packages/ai/src/models.generated.ts
View file

@ -1199,6 +1199,23 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 16384,
} satisfies Model<"openai-responses">,
"gpt-5.1-codex-max": {
id: "gpt-5.1-codex-max",
name: "GPT-5.1 Codex Max",
api: "openai-responses",
provider: "openai",
baseUrl: "https://api.openai.com/v1",
reasoning: true,
input: ["text", "image"],
cost: {
input: 1.25,
output: 10,
cacheRead: 0.125,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
},
groq: {
"llama-3.1-8b-instant": {
@ -3861,23 +3878,6 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/magistral-small-2506": {
id: "mistralai/magistral-small-2506",
name: "Mistral: Magistral Small 2506",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: true,
input: ["text"],
cost: {
input: 0.5,
output: 1.5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 40000,
maxTokens: 40000,
} satisfies Model<"openai-completions">,
"mistralai/magistral-medium-2506:thinking": {
id: "mistralai/magistral-medium-2506:thinking",
name: "Mistral: Magistral Medium 2506 (thinking)",
@ -3895,23 +3895,6 @@ export const MODELS = {
contextWindow: 40960,
maxTokens: 40000,
} satisfies Model<"openai-completions">,
"mistralai/magistral-medium-2506": {
id: "mistralai/magistral-medium-2506",
name: "Mistral: Magistral Medium 2506",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: true,
input: ["text"],
cost: {
input: 2,
output: 5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 40960,
maxTokens: 40000,
} satisfies Model<"openai-completions">,
"google/gemini-2.5-pro-preview": {
id: "google/gemini-2.5-pro-preview",
name: "Google: Gemini 2.5 Pro Preview 06-05",
@ -3980,23 +3963,6 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 64000,
} satisfies Model<"openai-completions">,
"mistralai/devstral-small-2505": {
id: "mistralai/devstral-small-2505",
name: "Mistral: Devstral Small 2505",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.06,
output: 0.12,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"openai/codex-mini": {
id: "openai/codex-mini",
name: "OpenAI: Codex Mini",
@ -4397,13 +4363,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.19999999999999998,
output: 0.88,
cacheRead: 0.106,
input: 0.15,
output: 0.7,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 163840,
maxTokens: 4096,
contextWindow: 8192,
maxTokens: 7168,
} satisfies Model<"openai-completions">,
"mistralai/mistral-small-3.1-24b-instruct:free": {
id: "mistralai/mistral-small-3.1-24b-instruct:free",
@ -4711,23 +4677,6 @@ export const MODELS = {
contextWindow: 163840,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/codestral-2501": {
id: "mistralai/codestral-2501",
name: "Mistral: Codestral 2501",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.3,
output: 0.8999999999999999,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-chat": {
id: "deepseek/deepseek-chat",
name: "DeepSeek: DeepSeek V3",
@ -5595,23 +5544,6 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/mistral-small": {
id: "mistralai/mistral-small",
name: "Mistral Small",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.19999999999999998,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/mistral-tiny": {
id: "mistralai/mistral-tiny",
name: "Mistral Tiny",