hobokenchicken/GopherGate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: implement reasoning_tokens tracking and enhanced usage logging
Some checks failed
CI / Check (push) Has been cancelled
Details
CI / Clippy (push) Has been cancelled
Details
CI / Formatting (push) Has been cancelled
Details
CI / Test (push) Has been cancelled
Details
CI / Release Build (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Dustin Newkirk
2026-03-11 17:14:49 +00:00
parent 3ab00fb188
commit cc5eba1957
11 changed files with 75 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
src/server/mod.rs
View File

@@ -312,6 +312,14 @@ async fn chat_completions(
},
finish_reason: chunk.finish_reason,
}],
usage: chunk.usage.as_ref().map(|u| crate::models::Usage {
prompt_tokens: u.prompt_tokens,
completion_tokens: u.completion_tokens,
total_tokens: u.total_tokens,
reasoning_tokens: if u.reasoning_tokens > 0 { Some(u.reasoning_tokens) } else { None },
cache_read_tokens: if u.cache_read_tokens > 0 { Some(u.cache_read_tokens) } else { None },
cache_write_tokens: if u.cache_write_tokens > 0 { Some(u.cache_write_tokens) } else { None },
}),
};
// Use axum's Event directly, wrap in Ok
@@ -383,6 +391,7 @@ async fn chat_completions(
model: response.model.clone(),
prompt_tokens: response.prompt_tokens,
completion_tokens: response.completion_tokens,
reasoning_tokens: response.reasoning_tokens,
total_tokens: response.total_tokens,
cache_read_tokens: response.cache_read_tokens,
cache_write_tokens: response.cache_write_tokens,
@@ -423,6 +432,7 @@ async fn chat_completions(
prompt_tokens: response.prompt_tokens,
completion_tokens: response.completion_tokens,
total_tokens: response.total_tokens,
reasoning_tokens: if response.reasoning_tokens > 0 { Some(response.reasoning_tokens) } else { None },
cache_read_tokens: if response.cache_read_tokens > 0 { Some(response.cache_read_tokens) } else { None },
cache_write_tokens: if response.cache_write_tokens > 0 { Some(response.cache_write_tokens) } else { None },
}),
@@ -452,6 +462,7 @@ async fn chat_completions(
model: model.clone(),
prompt_tokens: 0,
completion_tokens: 0,
reasoning_tokens: 0,
total_tokens: 0,
cache_read_tokens: 0,
cache_write_tokens: 0,