Lachlan Donald abed075b2e feat: add support for openai/gpt-5-pro model ...

Adds configuration for the new GPT-5 Pro model released by OpenAI.

Specifications from official docs:
- 400K context window
- 272K max output tokens (largest of GPT-5 family)
- Highest reasoning capability (5/5)
- Reasoning token support
- Vision input support (text+image input, text output only)
- No temperature support (fixed, like other reasoning models)
- Available via Responses API only (use_openai_response_api: true)
- Default reasoning effort: high

Accessible via alias 'gpt5pro'.

2025-10-07 16:02:37 +11:00

..

cli_clients

refactor: de-duplicate roles to avoid explosion when more CLIs get added

2025-10-06 08:54:33 +04:00

__init__.py

Complete PR review feedback implementation with clean importlib.resources approach

2025-08-10 22:13:25 +07:00

azure_models.json

feat: OpenAI/compatible models (such as Azure OpenAI) can declare if they use the response API instead via use_openai_responses_api

2025-10-04 21:20:47 +04:00

custom_models.json

feat!: breaking change - OpenRouter models are now read from conf/openrouter_models.json while Custom / Self-hosted models are read from conf/custom_models.json

2025-10-04 21:10:56 +04:00

openrouter_models.json

feat: add support for openai/gpt-5-pro model

2025-10-07 16:02:37 +11:00