public/galaxy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Improve provider reliability and usage visibility

Browse Source
This commit is contained in:
rkw6086
2026-08-21 19:12:14 -05:00
parent 19b2c5f687
commit be1dbb600a
28 changed files with 1070 additions and 592 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/src/ai/openai/response_translator.rs
+14 -9
View File
@@ -39,6 +39,9 @@ pub(crate) struct StreamUsage {
pub(crate) output_tokens: i32,
pub(crate) cache_read_tokens: i32,
pub(crate) cache_write_tokens: i32,
/// Input currently occupying the model context. When absent, the
/// per-request token fields above are used.
pub(crate) current_context_tokens: Option<i32>,
pub(crate) cost_in_cents: f32,
pub(crate) model_id: String,
pub(crate) max_context_tokens: Option<u32>,
@@ -376,14 +379,13 @@ pub fn openai_stream_to_response_events(
}
}
// If we got cache_read but no explicit cache_write, infer it:
// cache_write = prompt_tokens - cache_read (the non-cached input that will be cached)
if cache_read_tokens > 0 && cache_write_tokens == 0 {
cache_write_tokens = (input_tokens - cache_read_tokens).max(0);
}
let current_context_tokens = input_tokens;
let cache_miss_tokens = input_tokens
.saturating_sub(cache_read_tokens)
.saturating_sub(cache_write_tokens);
let cost = estimate_cost_cents(
input_tokens as u32,
cache_miss_tokens as u32,
output_tokens as u32,
cache_read_tokens as u32,
cache_write_tokens as u32,
@@ -392,10 +394,11 @@ pub fn openai_stream_to_response_events(
let finished_event = build_stream_finished(
stop_reason,
StreamUsage {
input_tokens,
input_tokens: cache_miss_tokens,
output_tokens,
cache_read_tokens,
cache_write_tokens,
current_context_tokens: Some(current_context_tokens),
cost_in_cents: cost,
model_id: model_id.clone(),
max_context_tokens,
@@ -545,6 +548,7 @@ pub(crate) fn build_stream_finished(
output_tokens,
cache_read_tokens,
cache_write_tokens,
current_context_tokens,
cost_in_cents,
model_id,
max_context_tokens,
@@ -577,7 +581,8 @@ pub(crate) fn build_stream_finished(
let max_context_tokens =
max_context_tokens.unwrap_or_else(|| context_window_for_model(&model_id));
// Context usage should reflect the full input including cached tokens
let effective_input = input_tokens + cache_read_tokens + cache_write_tokens;
let effective_input =
current_context_tokens.unwrap_or(input_tokens + cache_read_tokens + cache_write_tokens);
let context_usage = if max_context_tokens > 0 {
effective_input as f32 / max_context_tokens as f32
} else {
@@ -591,7 +596,7 @@ pub(crate) fn build_stream_finished(
summarized: false,
credits_spent: 0.0,
platform_credits_spent: 0.0,
total_input_tokens: input_tokens as u32,
total_input_tokens: effective_input.max(0) as u32,
token_usage: vec![],
tool_usage_metadata: None,
warp_token_usage: std::collections::HashMap::new(),