Skip to content

Fix Groq context window display #7839

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Sep 10, 2025
Merged

Fix Groq context window display #7839

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
417a40f
Fix Groq context window display
mrubens Sep 10, 2025
1993fdb
Update src/api/providers/__tests__/groq.spec.ts
mrubens Sep 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/api/providers/__tests__/groq.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,7 +149,7 @@ describe("GroqHandler", () => {
expect(firstChunk.done).toBe(false)
expect(firstChunk.value).toMatchObject({
type: "usage",
inputTokens: 70, // 100 total - 30 cached
inputTokens: 100, // Full token count, no longer subtracting cached tokens
outputTokens: 50,
cacheWriteTokens: 0,
cacheReadTokens: 30,
Expand Down
13 changes: 1 addition & 12 deletions src/api/providers/groq.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,20 +66,9 @@ export class GroqHandler extends BaseOpenAiCompatibleProvider<GroqModelId> {
// Calculate cost using OpenAI-compatible cost calculation
const totalCost = calculateApiCostOpenAI(info, inputTokens, outputTokens, cacheWriteTokens, cacheReadTokens)

// Calculate non-cached input tokens for proper reporting
const nonCachedInputTokens = Math.max(0, inputTokens - cacheReadTokens - cacheWriteTokens)

console.log("usage", {
inputTokens: nonCachedInputTokens,
outputTokens,
cacheWriteTokens,
cacheReadTokens,
totalCost,
})

yield {
type: "usage",
inputTokens: nonCachedInputTokens,
inputTokens,
Copy link
Contributor

@roomote roomote bot Sep 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Good to see the test was updated to match this change! However, could you clarify what specific issue this fixes? The PR title mentions "Fix Groq context window display" but it's not clear what was broken.

Also, is this token reporting approach intentional? This makes Groq's behavior different from how it previously worked (subtracting cached tokens from input tokens). The base OpenAI provider reports total tokens, but some other providers handle cached tokens differently. Could you explain the reasoning behind this change?

outputTokens,
cacheWriteTokens,
cacheReadTokens,
Expand Down
Loading