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)
• feat: Add support for OpenAI-compatible LLM endpoints (Groq, Ollama, Azure OpenAI, etc.) feat: Add support for OpenAI-compatible LLM endpoints (Groq, Ollama, Azure OpenAI, etc.) #1198

2. Description of change:

Problem:
Not every developer has access to a premium model subscription — but every
developer deserves the ability to build robust, production-grade agent systems
that scale. ADK Java already provides a strong foundation with Gemini and the
contrib/langchain4j bridge. This PR extends that foundation with a
convention-based, zero-wiring path for any OpenAI-compatible provider.

Today, using alternative providers like Groq, Ollama, or OpenRouter requires
explicit registration at startup. This PR makes that optional — providers
self-register via META-INF/services, so adding one is just a Maven
dependency.

Why mix models? Use Gemini only where its built-in tools (GoogleSearchTool,
code execution) are genuinely needed. Route heavy generation to fast free-tier
models like Groq or OpenRouter. Run lightweight steps — classification, critique,
formatting — on local Ollama at zero cost. The result is a more capable system
at a fraction of the cost of running every agent on a premium model. Individual
developers and open-source projects can build production-grade multi-agent
pipelines with no enterprise AI subscription required.

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.

This PR introduces a ServiceLoader-based SPI as a contrib module.
Adding a provider is a single Maven dependency — no application code changes.

<dependency>
  <groupId>com.google.adk.contrib</groupId>
  <artifactId>model-prism-groq</artifactId>
</dependency>

Then just use the model by name:

LlmAgent.builder().model("groq/llama3").build()

What's included

Tests

13 unit tests, all passing. See PR description for full list.

Manual E2E verified with Groq and Ollama.

Proposed core integration (one line)

// In Runner or AdkWebServer.start()
ModelProviderRegistry.registerAll();

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/:

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.