symfony/ai-open-ai-platform

Changelog (v0.11.0...v0.12.0)

• minor #2358 Prepare version constraints for release of v0.12.0 (@chr-hertel)
• minor #2351 Throw MaxOutputTokensException for non-streamed OpenResponses truncation (@chr-hertel)
• feature #2335 Report OpenResponses output limit truncation (@fabpot)

Changelog (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)
• feature #2313 Update model catalogs (@github-actions)
• feature #2248 Convert OpenAI Responses built-in tool output items to typed results (@OskarStark)
• feature #2224 Replace retired OpenAI DALL-E with gpt-image (rename bridge to Image, add editing) (@chr-hertel)
• minor #2223 Fold OpenAI GPT handling onto OpenResponses bridge (@chr-hertel)
• bug #2210 Skip built-in tool-call output items in OpenAI result converters (@OskarStark)
• minor #2218 Update model catalogs (@github-actions)
• 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 (v0.9.0...v0.10.0)

• bug #2184 Throw ModelNotFoundException on 404 responses (@chr-hertel)
• bug #2163 Replace malformed UTF-8 in request bodies instead of abort… (@fabpot)
• bug #2162 Fix incomplete stream terminal events (@fabpot)
• feature #2165 Throw ExceedContextSizeException when a request exceeds the model's context window (@fabpot)
• data #2141 Update model catalogs (@github-actions)
• bug #2138 Fix red CI: gpt-5.5-pro capabilities mismatch and class_exists() on Validator interface (@chr-hertel)

Changelog (v0.8.0...v0.9.0)

• bug #2067 Surface API error message on RateLimitExceededException (@chr-hertel)
• bug #2032 Fix structured output for reasoning models (@chr-hertel)

Changelog (v0.7.0...v0.8.0)

• feature #1968 Expose API errors uniformly across bridges through a shared trait (@Amoifr)
• feature #1923 Introduce Provider abstraction and model routing layer (@chr-hertel)

Changelog (v0.6.0...v0.7.0)

• feature #1884 Add ThinkingStart and Anthropic example (@chr-hertel)
• feature #1849 Add reasoning content streaming support (@Amoifr)
• feature #943 Introduce Speech support (@Guikingone, @chr-hertel)
• feature #1851 Add token usage extraction for embeddings (@Amoifr)
• feature #1759 Replace untyped stream chunks with semantic DeltaInterface deltas (@fabpot, @chr-hertel)
• feature #1807 Add gpt-5.4-mini and gpt-5.4-nano to ModelCatalog (@Quentinmse80)

Changelog (v0.5.0...v0.6.0)

• feature #1644 Add support for prompt caching (@fabpot)
• feature #1719 Replace Chat Completions client with Responses API client (@paulkothmair)
• bug #1711 Throw InvalidArgumentException when ModelClient receives a string payload (@fabpot)

Changelog (v0.4.0...v0.5.0)

• no significant changes

Changelog (v0.3.3...v0.4.0)

• feature #1571 Introduce Open Responses Platform Bridge by extracting from OpenAI (chr-hertel)
• bug #1530 Add missing EMBEDDINGS capability to embedding models (@RamyHakam)