mirror of
https://github.com/firebase/firebase-ios-sdk
synced 2026-11-10 22:45:59 +05:45
Andrew Heard
3796a55fdf
Implemented `GeminiLanguageModel`, providing an adapter for Google's Gemini models conforming to Apple's `FoundationModels.LanguageModel` protocol. This PR includes text to text generation capabilities; other modalities and Gemini features will be handled in follow-up PRs. **Note:** The `GeminiLanguageModel` implementation is guarded by the environment variable `GEMINI_LANGUAGE_MODEL`. By default none of the `GeminiLanguageModel` implementation is included. Key additions: - `GeminiLanguageModel`: Implements `LanguageModel` protocol with reasoning capabilities, configuring execution via `ModelResource` and `EndpointConfiguration`. - `GeminiLanguageModelExecutor`: Converts prompt instructions and history into Gemini streaming requests, yielding responses as `LanguageModelSession.ResponseStream`. - `GeminiTranscriptTranslator`: Translates Apple `Transcript` entries and segments into Gemini `Content` structures while preserving thought signatures and validating supported transcript features. - `GeminiLanguageModel.Error` and `GeminiErrorMapper`: Translates Gemini API, HTTP, and network errors into standard `LanguageModelError` cases (`rateLimited`, `timeout`, `guardrailViolation`, `refusal`, and `unsupportedLanguageOrLocale`) or `GeminiLanguageModel.Error` cases (`serviceUnavailable`, `networkFailure`, `modelNotFound`, `apiError`). The `APIError` payload is designed for seamless forward compatibility with both GenerateContent and the upcoming Interactions API. - Testing infrastructure: Adds `ConditionTrait.requireFoundationModels` to conditionally run Foundation Models tests only on supported platforms (macOS 27+, iOS 27+, watchOS 27+, visionOS 27+), along with shared test constants, mock fixtures, and comprehensive unit and integration test suites.
102 lines
4.0 KiB
Swift
102 lines
4.0 KiB
Swift
// Copyright 2026 Google LLC
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
|
|
import Foundation
|
|
|
|
/// An internal data model for `ThinkingConfig`.
|
|
///
|
|
/// ### Gemini Developer API
|
|
///
|
|
/// Type: `GoogleAiGenerativelanguageV1betaThinkingConfig`
|
|
///
|
|
/// Config for thinking features.
|
|
///
|
|
/// ### Gemini Enterprise Agent Platform
|
|
///
|
|
/// Type: `GoogleCloudAiplatformV1beta1GenerationConfigThinkingConfig`
|
|
///
|
|
/// Configuration for the model's thinking features.
|
|
///
|
|
/// "Thinking" is a process where the model breaks down a complex task into
|
|
/// smaller, manageable steps. This allows the model to reason about the task,
|
|
/// plan its approach, and execute the plan to generate a high-quality
|
|
/// response.
|
|
package struct ThinkingConfig: Codable, Sendable, Equatable, Hashable {
|
|
/// Indicates whether to include thoughts in the response.
|
|
///
|
|
/// ### Gemini Developer API
|
|
///
|
|
/// Indicates whether to include thoughts in the response.
|
|
/// If true, thoughts are returned only when available.
|
|
///
|
|
/// ### Gemini Enterprise Agent Platform
|
|
///
|
|
/// Optional. If true, the model will include its thoughts in the response. "Thoughts"
|
|
/// are the intermediate steps the model takes to arrive at the final
|
|
/// response. They can provide insights into the model's reasoning process
|
|
/// and help with debugging. If this is true, thoughts are returned only when
|
|
/// available.
|
|
package let includeThoughts: Bool?
|
|
|
|
/// The number of thoughts tokens that the model should generate.
|
|
///
|
|
/// ### Gemini Developer API
|
|
///
|
|
/// The number of thoughts tokens that the model should generate.
|
|
///
|
|
/// ### Gemini Enterprise Agent Platform
|
|
///
|
|
/// Optional. The token budget for the model's thinking process. The model will make a
|
|
/// best effort to stay within this budget. This can be used to control the
|
|
/// trade-off between response quality and latency.
|
|
package let thinkingBudget: Int?
|
|
|
|
/// Optional. Controls the maximum depth of the model's internal reasoning process before
|
|
///
|
|
/// ### Gemini Developer API
|
|
///
|
|
/// Optional. Controls the maximum depth of the model's internal reasoning process before
|
|
/// it produces a response. The default value is model-dependent. Refer to the
|
|
/// [Thinking levels
|
|
/// guide](https://ai.google.dev/gemini-api/docs/thinking#thinking-levels) for
|
|
/// more details. Recommended for Gemini 3 or later models. Use with earlier
|
|
/// models results in an error.
|
|
///
|
|
/// ### Gemini Enterprise Agent Platform
|
|
///
|
|
/// Optional. The number of thoughts tokens that the model should generate.
|
|
package let thinkingLevel: ThinkingLevel?
|
|
|
|
/// Creates a new `ThinkingConfig`.
|
|
///
|
|
/// - Parameters:
|
|
/// - includeThoughts: Indicates whether to include thoughts in the response. (behavior varies by backend). For more details, see ``includeThoughts``.
|
|
/// - thinkingBudget: The number of thoughts tokens that the model should generate. (behavior varies by backend). For more details, see ``thinkingBudget``.
|
|
/// - thinkingLevel: Optional. Controls the maximum depth of the model's internal reasoning process before (behavior varies by backend). For more details, see ``thinkingLevel``.
|
|
package init(
|
|
includeThoughts: Bool? = nil,
|
|
thinkingBudget: Int? = nil,
|
|
thinkingLevel: ThinkingLevel? = nil
|
|
) {
|
|
self.includeThoughts = includeThoughts
|
|
self.thinkingBudget = thinkingBudget
|
|
self.thinkingLevel = thinkingLevel
|
|
}
|
|
enum CodingKeys: String, CodingKey {
|
|
case includeThoughts = "includeThoughts"
|
|
case thinkingBudget = "thinkingBudget"
|
|
case thinkingLevel = "thinkingLevel"
|
|
}
|
|
}
|