contrib/model-prism: pluggable LLM backend SPI for ADK Java via ServiceLoader

[svetanis]

Add model-prism: pluggable LLM backend SPI for ADK Java via ServiceLoader

Please ensure you have read the contribution guide before creating a pull request.

Link to Issue or Description of Change

1. Related discussion:

• Related: openai api support #350 (OpenAI API support)

2. Description of change:

Problem:
ADK Java ships with built-in Gemini support and already offers the contrib/langchain4j bridge for wrapping third-party providers. However, the LangChain4j bridge requires explicit per-application wiring code: you must construct the provider object and pass a wrapper to .model(langChain4jWrapper). This approach does not use LlmRegistry and does not support model name strings — "groq/llama3" cannot be passed to .model("groq/...") without first calling LlmRegistry.registerLlm(...) somewhere in application startup. There is currently no convention-based, zero-code mechanism for classpath-driven provider discovery.

Solution:
Introduce a ServiceLoader SPI pattern (ModelProvider interface + ModelProviderRegistry) as a contrib module. Provider JARs self-register via META-INF/services — adding or removing a provider is a single Maven dependency change with zero application code modifications. A single call to ModelProviderRegistry.registerAll() in Runner or AdkWebServer.start() enables automatic discovery for all ADK applications.

Testing Plan

Unit Tests:

• I have added or updated unit tests for my change.
• All unit tests pass locally.

Tests run: 13, Failures: 0, Errors: 0, Skipped: 0

DefaultOpenAiMessageSerializerTest (9 tests):
  [OK] processStreamLines_textChunks_emitsPartialsThenFinal
  [OK] processStreamLines_emptyStream_emitsFinalEmptyResponse
  [OK] processStreamLines_nonDataLinesIgnored
  [OK] processStreamLines_toolCall_assemblesArgumentsAcrossChunks
  [OK] processStreamLines_multipleToolCalls_assemblesBothByIndex
  [OK] processStreamLines_errorChunk_throwsIllegalArgumentException
  [OK] processStreamLines_malformedJsonChunk_skippedGracefully
  [OK] deserializeResponse_textContent_returnsLlmResponseWithText
  [OK] deserializeResponse_toolCallContent_returnsFunctionCallPart

ModelProviderRegistryTest (4 tests):
  [OK] registerAll_singleProvider_registersPatternWithLlmRegistry
  [OK] registerAll_multipleProviders_registersAll
  [OK] registerAll_noProviders_returnsEmptyListAndNothingRegistered
  [OK] registerAll_calledTwice_registersEachTimeIndependently

Manual End-to-End (E2E) Tests:

The model-prism-demo module includes 11 runnable demo classes. To verify end-to-end:

# Set your key (OpenRouter has a free tier)
export OPENROUTER_API_KEY=your_key_here

# Basic SPI discovery
mvn -pl model-prism-demo exec:java -Dexec.mainClass=com.google.adk.models.demo.DemoApp

# Streaming
mvn -pl model-prism-demo exec:java -Dexec.mainClass=com.google.adk.models.demo.StreamingDemoApp

# Tool calling
mvn -pl model-prism-demo exec:java -Dexec.mainClass=com.google.adk.models.demo.tools.ToolsDemoApp

# ADK dev web server (open http://localhost:8080)
mvn -pl model-prism-demo exec:java -Dexec.mainClass=com.google.adk.models.demo.WebServerDemoApp

For Ollama (no API key required): install Ollama, run ollama pull llama3, then use model name ollama/llama3.

Checklist

• I have read the CONTRIBUTING.md document.
• My pull request contains a single commit.
• I have performed a self-review of my own code.
• I have commented my code, particularly in hard-to-understand areas.
• I have added tests that prove my fix is effective or that my feature works.
• New and existing unit tests pass locally with my changes.
• I have manually tested my changes end-to-end.
• Any dependent changes have been merged and published in downstream modules.

Additional context

Modules added under contrib/model-prism/:

Module	Purpose
model-prism-core	ModelProvider SPI, ModelProviderRegistry, OpenAiCompatibleLlm base class
model-prism-groq	Groq provider (groq/.*)
model-prism-ollama	Ollama provider (ollama/.*, no API key)
model-prism-openrouter	OpenRouter provider (openrouter/.*, free tier available)
model-prism-demo	11 demo classes covering all major ADK features

Proposed ADK integration

1. Three files from adk-model-prism-core would go into google-adk.jar
   • ModelProvider.java - public SPI interface
   • ModelProviderRegistry.java - ServiceLoader wiring
   • OpenAiCompatibleLlm.java - reusable base class for Open-AI-format APIs
2. one line in Runner and AdkWebServer.start()

ModelProviderRegistry.registerAll(); // discovers all providers on the classpath

Provider JARs are published independently - no PRs to ADK core needed for new providers.