ceos/opencode
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(ai): normalize Bedrock cache usage (#38427)

Browse source 
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
This commit is contained in:
opencode-agent[bot] 2026-07-22 21:42:53 -05:00 • committed by GitHub
commit 6e8aefcfa0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 114 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

19
packages/ai/src/protocols/bedrock-converse.ts
View file

@ -436,21 +436,22 @@ const mapFinishReason = (reason: string): FinishReason => {
return "unknown"
}
// AWS Bedrock Converse reports `inputTokens` (inclusive total) with
// `cacheReadInputTokens` and `cacheWriteInputTokens` as subsets. Pass
// the total through and derive the non-cached breakdown. Bedrock does
// not break reasoning out of `outputTokens` for any current model.
// AWS reports inputTokens separately from cache reads and writes.
// Bedrock does not break reasoning out of outputTokens for current models.
const mapUsage = (usage: BedrockUsageSchema | undefined): Usage | undefined => {
if (!usage) return undefined
const cacheTotal = (usage.cacheReadInputTokens ?? 0) + (usage.cacheWriteInputTokens ?? 0)
const nonCached = ProviderShared.subtractTokens(usage.inputTokens, cacheTotal)
const inputTokens = ProviderShared.sumTokens(
usage.inputTokens,
usage.cacheReadInputTokens,
usage.cacheWriteInputTokens,
)
return new Usage({
inputTokens: usage.inputTokens,
inputTokens,
outputTokens: usage.outputTokens,
nonCachedInputTokens: nonCached,
nonCachedInputTokens: usage.inputTokens,
cacheReadInputTokens: usage.cacheReadInputTokens,
cacheWriteInputTokens: usage.cacheWriteInputTokens,
totalTokens: ProviderShared.totalTokens(usage.inputTokens, usage.outputTokens, usage.totalTokens),
totalTokens: ProviderShared.totalTokens(inputTokens, usage.outputTokens, usage.totalTokens),
providerMetadata: { bedrock: usage },
})
}

7
packages/ai/src/schema/events.ts
View file

@ -34,11 +34,12 @@ import { ProviderFailureClassification } from "./errors"
*
* **Semantics by provider**:
*
* - OpenAI Chat / Responses / Gemini / Bedrock: provider reports inclusive
* - OpenAI Chat / Responses / Gemini: provider reports inclusive
* `inputTokens` and an inclusive `outputTokens`; mapper subtracts to
* derive the breakdown.
* - Anthropic: provider reports the breakdown natively (`input_tokens` is
* non-cached only); mapper sums to derive the inclusive `inputTokens`.
* - Anthropic and Bedrock report the input breakdown natively: Anthropic's
* `input_tokens` and Bedrock's `inputTokens` are non-cached only. Their
* mappers sum the breakdown to derive the inclusive `inputTokens`.
* Anthropic does *not* break extended-thinking out of `output_tokens`, so
* `reasoningTokens` is `undefined` and `outputTokens` carries the
* combined total — a documented limitation of the Anthropic API.