Mario Zechner ee4c131873 fix(ai): Fix OpenAI Responses provider multi-turn conversation support ...

- Collect complete output items during streaming instead of building blocks incrementally
- Handle reasoning summary parts with proper newline separation
- Support refusal content in message outputs
- Preserve full reasoning items and message IDs for multi-turn resubmission
- Emit proper streaming events for text and thinking deltas

2025-08-31 22:11:08 +02:00

..

providers

fix(ai): Fix OpenAI Responses provider multi-turn conversation support

2025-08-31 22:11:08 +02:00

index.ts

feat(ai): Rename package to @mariozechner/pi-ai and improve documentation

2025-08-30 21:41:22 +02:00

models.generated.ts

fix(ai): Fix OpenAI Responses provider multi-turn conversation support

2025-08-30 22:55:29 +02:00

models.ts

feat(ai): Add cost tracking to LLM implementations

2025-08-30 00:45:08 +02:00

types.ts

refactor(ai): Update OpenAI Completions provider to new content block API

2025-08-31 20:59:57 +02:00