chore: audit unreleased changelogs

This commit is contained in:
Mario Zechner
2026-04-27 21:25:57 +02:00
parent b8238a77a5
commit 69206f5390
2 changed files with 26 additions and 1 deletions

View File

@@ -2,15 +2,21 @@
## [Unreleased]
### Added
- Added Azure Cognitive Services endpoint support for Azure OpenAI Responses base URLs ([#3799](https://github.com/badlogic/pi-mono/pull/3799) by [@marcbloech](https://github.com/marcbloech)).
### Changed
- Changed OpenAI Codex Responses default text verbosity to `low` when no verbosity is specified.
### Fixed
- Fixed API-key environment discovery to fall back to `/proc/self/environ` when Bun's sandbox leaves `process.env` empty ([#3801](https://github.com/badlogic/pi-mono/pull/3801) by [@mdsjip](https://github.com/mdsjip)).
- Fixed Bedrock prompt-caching and adaptive-thinking capability checks to use the model name when the model id is an inference profile ARN ([#3527](https://github.com/badlogic/pi-mono/pull/3527) by [@anirudhmarc](https://github.com/anirudhmarc)).
- Fixed Anthropic SSE parsing to ignore unknown proxy events such as OpenAI-style `done` terminators ([#3708](https://github.com/badlogic/pi-mono/issues/3708)).
- Fixed OpenAI-compatible prompt cache tests to cover proxies that explicitly disable long cache retention.
- Stopped sending `tools: []` on OpenAI-compatible, Anthropic, OpenAI Responses, OpenAI Codex Responses, and Azure OpenAI Responses requests when no tools are active (e.g. `pi --no-tools`). DashScope/Aliyun Qwen (OpenAI-compatible) rejects empty tools arrays with `"[] is too short - 'tools'"` (HTTP 400); the field is now omitted unless the conversation has tool history (the existing LiteLLM/Anthropic-proxy workaround).
- Stopped sending `tools: []` on OpenAI-compatible, Anthropic, OpenAI Responses, OpenAI Codex Responses, and Azure OpenAI Responses requests when no tools are active (e.g. `pi --no-tools`). DashScope/Aliyun Qwen (OpenAI-compatible) rejects empty tools arrays with `"[] is too short - 'tools'"` (HTTP 400); the field is now omitted unless the conversation has tool history (the existing LiteLLM/Anthropic-proxy workaround) ([#3650](https://github.com/badlogic/pi-mono/pull/3650) by [@HQidea](https://github.com/HQidea)).
- Fixed `supportsXhigh()` to recognize DeepSeek V4 Pro, preserving `xhigh` reasoning requests so they map to DeepSeek's `max` effort ([#3662](https://github.com/badlogic/pi-mono/issues/3662))
- Fixed OpenAI-compatible DeepSeek V4 model replay to include empty `reasoning_content` on assistant messages when needed, preventing OpenRouter DeepSeek V4 sessions from failing after responses without reasoning deltas ([#3668](https://github.com/badlogic/pi-mono/issues/3668))