Bramha.dev 414b3304cd fix(core): split tool-result media into follow-up user message for strict OpenAI compat (#3617) ... Fixes #3616. Adds opt-in `splitToolMedia` flag (default false). When enabled, media parts (image / audio / video / file) returned by MCP tool calls are split into a follow-up `role: "user"` message instead of being embedded in the `role: "tool"` message. Required for strict OpenAI-compatible servers (e.g., LM Studio) that reject non-text content on tool messages with HTTP 400 "Invalid 'messages' in payload". Media from parallel tool responses is accumulated and emitted as a single follow-up user message after all tool messages, preserving OpenAI's contiguity requirement for tool responses. Default behavior is unchanged for permissive providers.		2026-04-27 23:01:02 +08:00
..
_meta.ts	feat: update docs	2025-12-15 22:12:34 +08:00
auth.md	fix(cli): add API Key option to qwen auth interactive menu (#3624)	2026-04-27 22:01:47 +08:00
model-providers.md	docs: clarify envKey and add env field examples to model-providers	2026-03-27 18:22:16 +08:00
qwen-ignore.md	Merge pull request #1266 from QwenLM/docs-fix	2025-12-17 22:04:27 +08:00
settings.md	fix(core): split tool-result media into follow-up user message for strict OpenAI compat (#3617)	2026-04-27 23:01:02 +08:00
themes.md	Merge pull request #1266 from QwenLM/docs-fix	2025-12-17 22:04:27 +08:00
trusted-folders.md	docs: updated all links, click and open in vscode, new showcase video in overview	2025-12-17 11:10:31 +08:00