feat(vertexai): Add repetition penalties to GenerationConfig

[andrewheard]

Description

Added support for repetition penalties (presencePenalty and frequencyPenalty) in GenerationConfig in the Vertex AI in Firebase SDK. This brings it in alignment with the other SDKs.

AI Prompt

The initial commit was generated with Jules using the following prompt:

I need you to add two new instance variables (presencePenalty and frequencyPenalty) to GenerationConfig in the file packages/firebase_vertexai/firebase_vertexai/lib/src
/api.dart . Both of them should be double values in Dart.

To help you out, this is the equivalent implementation of GenerationConfig in the Swift SDK:

/// A struct defining model parameters to be used when sending generative AI
/// requests to the backend model.
@available(iOS 15.0, macOS 12.0, macCatalyst 15.0, tvOS 15.0, watchOS 8.0, *)
public struct GenerationConfig: Sendable {
/// Controls the degree of randomness in token selection.
let temperature: Float?

/// Controls diversity of generated text.
let topP: Float?

/// Limits the number of highest probability words considered.
let topK: Int?

/// The number of response variations to return.
let candidateCount: Int?

/// Maximum number of tokens that can be generated in the response.
let maxOutputTokens: Int?

/// Controls the likelihood of repeating the same words or phrases already generated in the text.
let presencePenalty: Float?

/// Controls the likelihood of repeating words, with the penalty increasing for each repetition.
let frequencyPenalty: Float?

/// A set of up to 5 `String`s that will stop output generation.
let stopSequences: [String]?

/// Output response MIME type of the generated candidate text.
let responseMIMEType: String?

/// Output schema of the generated candidate text.
let responseSchema: Schema?

/// Creates a new `GenerationConfig` value.
///
/// See the
/// [Configure model parameters](https://firebase.google.com/docs/vertex-ai/model-parameters)
/// guide and the
/// [Cloud documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#generationconfig)
/// for more details.
///
/// - Parameters:
/// - temperature:Controls the randomness of the language model's output. Higher values (for
/// example, 1.0) make the text more random and creative, while lower values (for example,
/// 0.1) make it more focused and deterministic.
///
/// > Note: A temperature of 0 means that the highest probability tokens are always selected.
/// > In this case, responses for a given prompt are mostly deterministic, but a small amount
/// > of variation is still possible.
///
/// > Important: The range of supported temperature values depends on the model; see the
/// > [documentation](https://firebase.google.com/docs/vertex-ai/model-parameters?platform=ios#temperature)
/// > for more details.
/// - topP: Controls diversity of generated text. Higher values (e.g., 0.9) produce more diverse
/// text, while lower values (e.g., 0.5) make the output more focused.
///
/// The supported range is 0.0 to 1.0.
///
/// > Important: The default `topP` value depends on the model; see the
/// > [documentation](https://firebase.google.com/docs/vertex-ai/model-parameters?platform=ios#top-p)
/// > for more details.
/// - topK: Limits the number of highest probability words the model considers when generating
/// text. For example, a topK of 40 means only the 40 most likely words are considered for the
/// next token. A higher value increases diversity, while a lower value makes the output more
/// deterministic.
///
/// The supported range is 1 to 40.
///
/// > Important: Support for `topK` and the default value depends on the model; see the
/// [documentation](https://firebase.google.com/docs/vertex-ai/model-parameters?platform=ios#top-k)
/// for more details.
/// - candidateCount: The number of response variations to return; defaults to 1 if not set.
/// Support for multiple candidates depends on the model; see the
/// [Cloud documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#generationconfig)
/// for more details.
/// - maxOutputTokens: Maximum number of tokens that can be generated in the response.
/// See the configure model parameters [documentation](https://firebase.google.com/docs/vertex-ai/model-parameters?platform=ios#max-output-tokens)
/// for more details.
/// - presencePenalty: Controls the likelihood of repeating the same words or phrases already
/// generated in the text. Higher values increase the penalty of repetition, resulting in more
/// diverse output.
///
/// > Note: While both `presencePenalty` and `frequencyPenalty` discourage repetition,
/// > `presencePenalty` applies the same penalty regardless of how many times the word/phrase
/// > has already appeared, whereas `frequencyPenalty` increases the penalty for *each*
/// > repetition of a word/phrase.
///
/// > Important: The range of supported `presencePenalty` values depends on the model; see the
/// > [Cloud documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#generationconfig)
/// > for more details
/// - frequencyPenalty: Controls the likelihood of repeating words or phrases, with the penalty
/// increasing for each repetition. Higher values increase the penalty of repetition,
/// resulting in more diverse output.
///
/// > Note: While both `frequencyPenalty` and `presencePenalty` discourage repetition,
/// > `frequencyPenalty` increases the penalty for *each* repetition of a word/phrase, whereas
/// > `presencePenalty` applies the same penalty regardless of how many times the word/phrase
/// > has already appeared.
///
/// > Important: The range of supported `frequencyPenalty` values depends on the model; see
/// > the
/// > [Cloud documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#generationconfig)
/// > for more details
/// - stopSequences: A set of up to 5 `String`s that will stop output generation. If specified,
/// the API will stop at the first appearance of a stop sequence. The stop sequence will not
/// be included as part of the response. See the
/// [Cloud documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#generationconfig)
/// for more details.
/// - responseMIMEType: Output response MIME type of the generated candidate text.
///
/// Supported MIME types:
/// - `text/plain`: Text output; the default behavior if unspecified.
/// - `application/json`: JSON response in the candidates.
/// - `text/x.enum`: For classification tasks, output an enum value as defined in the
/// `responseSchema`.
/// - responseSchema: Output schema of the generated candidate text. If set, a compatible
/// `responseMIMEType` must also be set.
///
/// Compatible MIME types:
/// - `application/json`: Schema for JSON response.
///
/// Refer to the
/// [Generate structured
/// output](https://firebase.google.com/docs/vertex-ai/structured-output?platform=ios) guide
/// for more details.
public init(temperature: Float? = nil, topP: Float? = nil, topK: Int? = nil,
candidateCount: Int? = nil, maxOutputTokens: Int? = nil,
presencePenalty: Float? = nil, frequencyPenalty: Float? = nil,
stopSequences: [String]? = nil, responseMIMEType: String? = nil,
responseSchema: Schema? = nil) {
// Explicit init because otherwise if we re-arrange the above variables it changes the API
// surface.
self.temperature = temperature
self.topP = topP
self.topK = topK
self.candidateCount = candidateCount
self.maxOutputTokens = maxOutputTokens
self.presencePenalty = presencePenalty
self.frequencyPenalty = frequencyPenalty
self.stopSequences = stopSequences
self.responseMIMEType = responseMIMEType
self.responseSchema = responseSchema
}
}

Use the documentation and naming from Swift, where possible, but make sure to format it similarly to the existing Dart code in that class. Don't forget to add the new variables to the toJson method too.

Checklist

Before you create this PR confirm that it meets all requirements listed below by checking the relevant checkboxes ([x]).
This will ensure a smooth and quick review process. Updating the pubspec.yaml and changelogs is not required.

• I read the Contributor Guide and followed the process outlined there for submitting PRs.
• My PR includes unit or integration tests for all changed/updated/fixed behaviors (See Contributor Guide).
• All existing and new tests are passing.
• I updated/added relevant documentation (doc comments with ///).
• The analyzer (melos run analyze) does not report any problems on my PR.
• I read and followed the Flutter Style Guide.
• I signed the CLA.
• I am willing to follow-up on review comments in a timely manner.

Breaking Change

Does your PR require plugin users to manually update their apps to accommodate your change?

• Yes, this is a breaking change.
• No, this is not a breaking change.

[andrewheard]

cc: @cynthiajoan This isn't urgent but hopefully this will provide most or all of the code changes necessary for adding presencePenalty and frequencyPenalty (see internal Chat thread for context).

[cynthiajoan]

Actually, we should put them into the base configuration class so it can share with LiveConfig