getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-20 20:01:06 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge PR #264: Add Gemini 3 preview models to google-gemini-cli provider

Browse source
This commit is contained in:
Mario Zechner 2025-12-21 20:31:19 +01:00
commit 329b3a0a36
10 changed files with 166 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

46
packages/ai/src/models.generated.ts
View file

@ -6019,9 +6019,9 @@ export const MODELS = {
contextWindow: 32768,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"anthropic/claude-3.5-haiku": {
id: "anthropic/claude-3.5-haiku",
name: "Anthropic: Claude 3.5 Haiku",
"anthropic/claude-3.5-haiku-20241022": {
id: "anthropic/claude-3.5-haiku-20241022",
name: "Anthropic: Claude 3.5 Haiku (2024-10-22)",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
@ -6036,9 +6036,9 @@ export const MODELS = {
contextWindow: 200000,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"anthropic/claude-3.5-haiku-20241022": {
id: "anthropic/claude-3.5-haiku-20241022",
name: "Anthropic: Claude 3.5 Haiku (2024-10-22)",
"anthropic/claude-3.5-haiku": {
id: "anthropic/claude-3.5-haiku",
name: "Anthropic: Claude 3.5 Haiku",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
@ -6274,23 +6274,6 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3.1-405b-instruct": {
id: "meta-llama/llama-3.1-405b-instruct",
name: "Meta: Llama 3.1 405B Instruct",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 3.5,
output: 3.5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 130815,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3.1-8b-instruct": {
id: "meta-llama/llama-3.1-8b-instruct",
name: "Meta: Llama 3.1 8B Instruct",
@ -6308,6 +6291,23 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3.1-405b-instruct": {
id: "meta-llama/llama-3.1-405b-instruct",
name: "Meta: Llama 3.1 405B Instruct",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 3.5,
output: 3.5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 130815,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3.1-70b-instruct": {
id: "meta-llama/llama-3.1-70b-instruct",
name: "Meta: Llama 3.1 70B Instruct",

11
packages/ai/src/providers/google-gemini-cli.ts
View file

@ -23,10 +23,19 @@ import { convertMessages, convertTools, mapStopReasonString, mapToolChoice } fro
export interface GoogleGeminiCliOptions extends StreamOptions {
toolChoice?: "auto" | "none" | "any";
/**
* Thinking/reasoning configuration.
* - Gemini 2.x models: use `budgetTokens` to set the thinking budget
* - Gemini 3 models (gemini-3-pro-*, gemini-3-flash-*): use `level` instead
*
* When using `streamSimple`, this is handled automatically based on the model.
*/
thinking?: {
enabled: boolean;
/** Thinking budget in tokens. Use for Gemini 2.x models. */
budgetTokens?: number;
level?: ThinkingLevel; // For Gemini 3 models
/** Thinking level. Use for Gemini 3 models (LOW/HIGH for Pro, MINIMAL/LOW/MEDIUM/HIGH for Flash). */
level?: ThinkingLevel;
};
projectId?: string;
}