Skip to content

chore: [Orchestration] (and OpenAI) Migrate max_token parameter #629

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

chore: [Orchestration] (and OpenAI) Migrate max_token parameter #629

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
60cac7b
Initial
newtork Oct 24, 2025
ff4aa06
Update OpenAiChatModel
newtork Oct 24, 2025
bb0b819
Update tests
newtork Oct 24, 2025
07c15d4
Merge remote-tracking branch 'origin/main' into max-token-parameter
newtork Oct 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion ...s/openai/src/main/java/com/sap/ai/sdk/foundationmodels/openai/spring/OpenAiChatModel.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -183,7 +183,10 @@ private static Generation toGeneration(
@Nonnull
protected static OpenAiChatCompletionRequest extractOptions(
@Nonnull OpenAiChatCompletionRequest request, @Nonnull final ChatOptions options) {
request = request.withStop(options.getStopSequences()).withMaxTokens(options.getMaxTokens());
request =
request
.withStop(options.getStopSequences())
.withMaxCompletionTokens(options.getMaxTokens());
Copy link
Contributor

@CharlesDuboisSAP CharlesDuboisSAP Oct 24, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why change OpenAI, I thought only orchestration deprecated it.

Copy link
Contributor Author

@newtork newtork Oct 24, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Apparently we didn't even notice that OpenAI deprecated the field last year 😅

https://github.com/SAP/ai-sdk-java/blob/main/foundation-models/openai/src/main/resources/spec/openapi-2024-10-21.yaml#L621

if (options.getTemperature() != null) {
request = request.withTemperature(BigDecimal.valueOf(options.getTemperature()));
}
Expand Down
2 changes: 1 addition & 1 deletion orchestration/src/main/java/com/sap/ai/sdk/orchestration/OrchestrationAiModel.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -365,7 +365,7 @@ public <ValueT> OrchestrationAiModel withParam(
@FunctionalInterface
public interface Parameter<ValueT> {
/** The maximum number of tokens to generate. */
Parameter<Integer> MAX_TOKENS = () -> "max_tokens";
Parameter<Integer> MAX_TOKENS = () -> "max_completion_tokens";

/** The sampling temperature. */
Parameter<Number> TEMPERATURE = () -> "temperature";
Expand Down
2 changes: 1 addition & 1 deletion orchestration/src/test/resources/filteringLooseRequest.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
"name": "gpt-4o",
"params": {
"temperature": 0.1,
"max_tokens": 50,
"max_completion_tokens": 50,
"frequency_penalty": 0,
"presence_penalty": 0,
"top_p": 1,
Expand Down
2 changes: 1 addition & 1 deletion orchestration/src/test/resources/filteringLooseRequestStream.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
"name": "gpt-4o",
"params": {
"temperature": 0.1,
"max_tokens": 50,
"max_completion_tokens": 50,
"frequency_penalty": 0,
"presence_penalty": 0,
"top_p": 1,
Expand Down
2 changes: 1 addition & 1 deletion orchestration/src/test/resources/groundingHelpSapComRequest.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
"model": {
"name": "gpt-4o",
"params": {
"max_tokens": 50,
"max_completion_tokens": 50,
"temperature": 0.1,
"frequency_penalty": 0,
"presence_penalty": 0,
Expand Down
2 changes: 1 addition & 1 deletion orchestration/src/test/resources/groundingRequest.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
"model": {
"name": "gpt-4o",
"params": {
"max_tokens": 50,
"max_completion_tokens": 50,
"temperature": 0.1,
"frequency_penalty": 0,
"presence_penalty": 0,
Expand Down
2 changes: 1 addition & 1 deletion orchestration/src/test/resources/localTemplateRequest.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
"model": {
"name": "gpt-4o",
"params": {
"max_tokens": 50,
"max_completion_tokens": 50,
"temperature": 0.1,
"frequency_penalty": 0,
"presence_penalty": 0,
Expand Down
2 changes: 1 addition & 1 deletion orchestration/src/test/resources/maskingRequest.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
"params": {
"presence_penalty": 0,
"frequency_penalty": 0,
"max_tokens": 50,
"max_completion_tokens": 50,
"temperature": 0.1,
"top_p": 1,
"n": 1
Expand Down
2 changes: 1 addition & 1 deletion orchestration/src/test/resources/messagesHistoryRequest.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
"params": {
"presence_penalty": 0,
"frequency_penalty": 0,
"max_tokens": 50,
"max_completion_tokens": 50,
"temperature": 0.1,
"top_p": 1,
"n": 1
Expand Down
2 changes: 1 addition & 1 deletion orchestration/src/test/resources/templateReferenceByIdRequest.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
"model": {
"name": "gpt-4o",
"params": {
"max_tokens": 50,
"max_completion_tokens": 50,
"temperature": 0.1,
"frequency_penalty": 0,
"presence_penalty": 0,
Expand Down
2 changes: 1 addition & 1 deletion orchestration/src/test/resources/templateReferenceByScenarioRequest.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
"model": {
"name": "gpt-4o",
"params": {
"max_tokens": 50,
"max_completion_tokens": 50,
"temperature": 0.1,
"frequency_penalty": 0,
"presence_penalty": 0,
Expand Down
2 changes: 1 addition & 1 deletion orchestration/src/test/resources/templatingRequest.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
"model": {
"name": "gpt-4o",
"params": {
"max_tokens": 50,
"max_completion_tokens": 50,
"temperature": 0.1,
"frequency_penalty": 0,
"presence_penalty": 0,
Expand Down
Loading