Ai Generic Platform Laravel Package

Changelog (https://github.com/symfony/ai-generic-platform/compare/v0.11.0...v0.12.0)

• minor #2358 Prepare version constraints for release of v0.12.0 (@chr-hertel)
• feature #2354 Report malformed tool call arguments across bridges (@chr-hertel)

Changelog (https://github.com/symfony/ai-generic-platform/compare/v0.10.0...v0.11.0)

• minor #2320 Prepare version constraints for release of v0.11.0 (@chr-hertel)
• feature #2290 Normalize finish_reason metadata across all bridges (@chr-hertel)
• bug #2275 Fix #2274: Preserve cache and reasoning tokens in Generic completions usage (@ineersa)
• bug #2251 Default tool_choice to "auto" in Generic completions when tools are provided (@Amoifr)
• bug #2273 Fix #2193: key streamed tool calls by provider index (@ineersa)
• feature #2276 Fix #2194: expose streamed finish_reason as metadata (@ineersa)
• feature #2215 Streamline base URL handling across bridges (@chr-hertel)
• bug #2220 Treat empty-string streamed tool-call id as a continuation (@soyuka)
• bug #2206 Add a retryable ServerException for transient 5xx and Anthropic overloaded errors (@fabpot)
• bug #2197 Raise an error on unhandled HTTP statuses before streaming (@fabpot)

Changelog (https://github.com/symfony/ai-generic-platform/compare/v0.9.0...v0.10.0)

• bug #2188 Fix OpenResponses null tool-call id and refresh deprecated example models (@chr-hertel)
• bug #2169 Throw IncompleteStreamException in more streaming bridges (@chr-hertel)
• bug #2168 Replace malformed UTF-8 in request bodies of the remaining LLM model clients (@chr-hertel)
• feature #2165 Throw ExceedContextSizeException when a request exceeds the model's context window (@fabpot)
• feature #2131 Request usage stats for streamed responses (@ineersa)

Changelog (https://github.com/symfony/ai-generic-platform/compare/v0.8.0...v0.9.0)

• bug #2067 Surface API error message on RateLimitExceededException (@chr-hertel)

Changelog (https://github.com/symfony/ai-generic-platform/compare/v0.7.0...v0.8.0)

• feature #1923 Introduce Provider abstraction and model routing layer (@chr-hertel)

Changelog (https://github.com/symfony/ai-generic-platform/compare/v0.6.0...v0.7.0)

• bug #1862 Fix interleaved reasoning in CompletionsConversionTrait (@ineersa)
• feature #1851 Add token usage extraction for embeddings (@Amoifr)
• feature #1759 Replace untyped stream chunks with semantic DeltaInterface deltas (@fabpot, @chr-hertel)
• bug #1814 Fix RateLimitExceededException TypeError in Generic Embeddings ResultConverter (@melkamar)
• bug #1792 Fix tool call without arguments (@guillaume-ro-fr)
• feature #1756 Extract duplicated completions conversion methods into CompletionsConversionTrait (@fabpot)

Changelog (https://github.com/symfony/ai-generic-platform/compare/v0.5.0...v0.6.0)

• feature #1644 Add support for prompt caching (@fabpot)
• bug #1714  Fix FallbackModelCatalog (@fabpot)
• bug #1711 Throw InvalidArgumentException when ModelClient receives a string payload (@fabpot)

Changelog (https://github.com/symfony/ai-generic-platform/compare/v0.4.0...v0.5.0)

• no significant changes

Changelog (https://github.com/symfony/ai-generic-platform/compare/v0.3.3...v0.4.0)

• feature #1520 Add support for token usage on generic bridge (@chr-hertel)