0.14.0

What's Changed

• configurable retries by @sonic182 in #66

Full Changelog: 0.13.1...0.14.0

0.13.1

What's Changed

• feat: ability to set http request headers (openrouter) by @NexPB in #64

New Contributors

• @NexPB made their first contribution in #64

Full Changelog: 0.13.0...0.13.1

0.13.0

Changed

• Replaced the previous auto function execution workflow with a manual process powered by FunctionExecutor and FunctionCallHelpers, and added README guidance for executing OpenAI/OpenRouter/Google function calls explicitly.

Breeaking Changes

• Removed the auto-execution helpers/tests and related documentation that assumed functions ran automatically.

0.12.2

What's Changed

• change license to MIT by @addUsername in #57
• a bit docs for custom params by @sonic182 in #56
• release version 0.12.2 by @sonic182 in #58

New Contributors

• @addUsername made their first contribution in #57

Full Changelog: 0.12.0...0.12.2

0.12.0

What's Changed

• feature/some tests by @sonic182 in #50
• feature/track costs general by @sonic182 in #52
• remove deprecations by @sonic182 in #54

Full Changelog: 0.11.2...0.12.0

0.11.1

• Added OpenRouter function-call support and provider message-mapping fixes; preserved assistant tool_calls during auto-executed functions.

0.11.0

• Implement multi-provider support with provider routing and failover:
  • Introduced a new :providers list in LlmComposer.Settings to replace deprecated :provider and :provider_opts keys.
  • Added validation in LlmComposer to enforce/suggest exclusive use of :providers and warn about deprecated keys.
  • Implemented LlmComposer.ProvidersRunner to handle provider execution, supporting multiple providers with fallback logic.
  • Added LlmComposer.ProviderRouter behaviour for routing strategies on provider selection, failure handling, and blocking.
  • Provided a simple default provider router LlmComposer.ProviderRouter.Simple with exponential backoff blocking on provider failures.
  • Refactored LlmComposer.run_completion/3 to delegate to ProvidersRunner for provider selection and execution.
• Optimized LlmComposer.Cache.Ets by switching put and delete calls to asynchronous casts, improving performance.
• Maintained backward compatibility with deprecated settings keys, issuing warnings and supporting legacy calls until version 0.12.0.
• Changed response_format key to response_schema for better structured output definition that works across multiple providers.
  • Structured outputs now available for OpenAI provider as well.
  • Default JSON module is JSON; falls back to Jason if JSON is not loaded.

0.10.0

• Add Google (Gemini) provider: Full feature support including chat, functions, streaming, and structured outputs.
• Add Vertex AI integration: Same Google provider but can be used with it's Vertex API. Enterprise support with OAuth 2.0 authentication via Goth library.

0.8.0

• Add tracking costs for OpenRouter provider: Introduced cost tracking functionality specifically for the OpenRouter provider to monitor API usage expenses.

0.7.0

• Add HttpClient module: Introduced a new HttpClient module for improved HTTP handling
• Add streaming read capability: Added the capability of streaming read for LLM providers completions.
• Documentation and config updates: Updates to README.md and configuration files.