Make LLM providers pluggable via auto-configuration

[MarcosLM11]

Closes #17

What

Make the providers/* modules self-register from the classpath the same way
the plugins/* modules do, instead of depending on the app's component scan.

Each provider now contributes its AgentOnboardingProvider through a Spring
Boot @AutoConfiguration class listed in the module's
META-INF/spring/…AutoConfiguration.imports. The ChatModel side was already
auto-configured by the Spring AI starters, so no change was needed there.

Changes

• anthropic: AnthropticClaudeCodeConfiguration @Configuration →
  @AutoConfiguration; onboarding provider moved to a @Bean in a new
  AnthropicAgentAutoConfiguration (keeps the Claude Code token condition).
• openai / ollama / google: drop @Component, add a small per-module
  @AutoConfiguration + .imports.
• Remove dead AgentProvider: it was never injected or called; its
  isConfigured stub returned false and getDefaultChatModel() would have
  thrown on an empty list. Active-model selection is handled centrally by
  spring.ai.model.chat.
• Tests: one test per provider asserting the bean registers via the
  auto-config and that the .imports file names it — currently the only guard
  for provider discovery, since OnboardingControllerTest mocks
  AgentOnboardingProviders.
• Docs: update AGENTS.md wording.

Notes

• No behavior change: providers are discovered exactly as before, just wired via
  auto-configuration. spring.ai.model.chat still selects the active model.
• Ollama needs no api-key gating — like the others, its ChatModel only loads
  when spring.ai.model.chat=ollama.
• Scope is classpath pluggability (parity with plugins). Runtime provider jars
  are intentionally left out.

Testing

./gradlew compileJava test — all modules green.

[arefbehboudi]

Great work.

I checked out the branch and verified: full build + all tests green, removing a provider from app/build.gradle still compiles and passes tests (true drop-in pluggability), all four providers register at runtime, and the Claude Code path still produces exactly one AnthropicChatModel.

One change requested before merge (auto-config ordering, see inline), the rest are minor.

Follow-up idea: switch the provider deps in app/build.gradle from implementation to runtimeOnly, so the compiler enforces that app never references provider classes directly.

[rdehuyss]

Really nice work!

Sorry for the delay, I was OOO. One last change and goot to merge!

Thanks for your contribution!

[MarcosLM11]

@arefbehboudi @rdehuyss All requested changes are addressed and pushed (commit a281139):

• Explicit auto-config ordering (@AutoConfiguration(before = AnthropicChatAutoConfiguration.class))
• @ConditionalOnMissingBean typed to the concrete provider class in all four modules
• Fixed the getResources() → getResource() test bug so each test only reads its own module's .imports file
• Deduplicated the imports-reading helper into a shared AutoConfigurationImportsTestSupport test fixture in base, used by all four provider tests

All review threads are resolved and ./gradlew compileJava test is green. Ready for another pass whenever you have a moment 🙏

[arefbehboudi]

Thank you @MarcosLM11!