Files
asepharyana-hub-llm-api/src/application/chat/mod.rs
T
asepharyanaandClaude Opus 5 7cec411cba fix(stream): robust reasoning/content split + flush un-tagged output
The incremental </think> search missed tags split across tokens, inverting
reasoning/content classification. Detect the first </think> on the full
buffer and track the content boundary as a byte offset. If the model never
closes </think>, flush the buffered text as content so clients always
receive the response. Chat UI now renders reasoning_content too.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-03 11:03:26 +07:00

7 lines
176 B
Rust

pub mod use_cases;
pub use use_cases::{
build_prompt, build_sampler, clean_text, parse_tool_calls, split_stream_chunk, strip_markup,
validate_model, SamplerParams,
};