Track prompt cache write token usage (#33454)

## What changed

- Parse `cache_write_tokens` from response input token details and carry it through token usage aggregation.
- Expose `cache_write_input_tokens` in protocol, app-server, exec, and TypeScript SDK usage events, defaulting it to zero for compatibility with older payloads.
- Report cache-write usage in analytics, metrics, traces, and rollout data alongside existing cache-read usage.

## Testing

- Add coverage for response parsing, usage event output, aggregation, analytics, metrics, and telemetry fields.

GitOrigin-RevId: 634e4fbe3086a8923c0ee13b622573e7d9d221bd
This commit is contained in:
Eric Traut
2026-07-16 00:22:53 +00:00
committed by copyberry
parent 78d4a563f9
commit 2edad72de3
46 changed files with 207 additions and 31 deletions
@@ -5192,6 +5192,11 @@
},
"TokenUsageBreakdown": {
"properties": {
"cacheWriteInputTokens": {
"default": 0,
"format": "int64",
"type": "integer"
},
"cachedInputTokens": {
"format": "int64",
"type": "integer"
@@ -20327,6 +20327,11 @@
},
"TokenUsageBreakdown": {
"properties": {
"cacheWriteInputTokens": {
"default": 0,
"format": "int64",
"type": "integer"
},
"cachedInputTokens": {
"format": "int64",
"type": "integer"
@@ -18106,6 +18106,11 @@
},
"TokenUsageBreakdown": {
"properties": {
"cacheWriteInputTokens": {
"default": 0,
"format": "int64",
"type": "integer"
},
"cachedInputTokens": {
"format": "int64",
"type": "integer"
@@ -25,6 +25,11 @@
},
"TokenUsageBreakdown": {
"properties": {
"cacheWriteInputTokens": {
"default": 0,
"format": "int64",
"type": "integer"
},
"cachedInputTokens": {
"format": "int64",
"type": "integer"
@@ -2,4 +2,4 @@
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
export type TokenUsageBreakdown = { totalTokens: number, inputTokens: number, cachedInputTokens: number, outputTokens: number, reasoningOutputTokens: number, };
export type TokenUsageBreakdown = { totalTokens: number, inputTokens: number, cachedInputTokens: number, cacheWriteInputTokens: number, outputTokens: number, reasoningOutputTokens: number, };
@@ -1453,6 +1453,9 @@ pub struct TokenUsageBreakdown {
pub input_tokens: i64,
#[ts(type = "number")]
pub cached_input_tokens: i64,
#[serde(default)]
#[ts(type = "number")]
pub cache_write_input_tokens: i64,
#[ts(type = "number")]
pub output_tokens: i64,
#[ts(type = "number")]
@@ -1465,6 +1468,7 @@ impl From<CoreTokenUsage> for TokenUsageBreakdown {
total_tokens: value.total_tokens,
input_tokens: value.input_tokens,
cached_input_tokens: value.cached_input_tokens,
cache_write_input_tokens: value.cache_write_input_tokens,
output_tokens: value.output_tokens,
reasoning_output_tokens: value.reasoning_output_tokens,
}