mirror of
https://github.com/cline/cline.git
synced 2026-09-19 02:05:44 +08:00
fix: Solving Context window counting issues in gemini model family in openrouter and cline provider
This commit is contained in:
+41
-15
@@ -98,14 +98,26 @@ export class ClineHandler implements ApiHandler {
|
||||
totalCost = 0
|
||||
}
|
||||
|
||||
yield {
|
||||
type: "usage",
|
||||
cacheWriteTokens: 0,
|
||||
cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens || 0,
|
||||
inputTokens: chunk.usage.prompt_tokens || 0,
|
||||
outputTokens: chunk.usage.completion_tokens || 0,
|
||||
// @ts-ignore-next-line
|
||||
totalCost,
|
||||
if (modelId.includes("gemini")) {
|
||||
yield {
|
||||
type: "usage",
|
||||
cacheWriteTokens: 0,
|
||||
cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens || 0,
|
||||
inputTokens: (chunk.usage.prompt_tokens || 0) - (chunk.usage.prompt_tokens_details?.cached_tokens || 0),
|
||||
outputTokens: chunk.usage.completion_tokens || 0,
|
||||
// @ts-ignore-next-line
|
||||
totalCost,
|
||||
}
|
||||
} else {
|
||||
yield {
|
||||
type: "usage",
|
||||
cacheWriteTokens: 0,
|
||||
cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens || 0,
|
||||
inputTokens: chunk.usage.prompt_tokens || 0,
|
||||
outputTokens: chunk.usage.completion_tokens || 0,
|
||||
// @ts-ignore-next-line
|
||||
totalCost,
|
||||
}
|
||||
}
|
||||
didOutputUsage = true
|
||||
}
|
||||
@@ -131,13 +143,27 @@ export class ClineHandler implements ApiHandler {
|
||||
})
|
||||
|
||||
const generation = response.data
|
||||
return {
|
||||
type: "usage",
|
||||
cacheWriteTokens: 0,
|
||||
cacheReadTokens: generation?.native_tokens_cached || 0,
|
||||
inputTokens: generation?.native_tokens_prompt || 0,
|
||||
outputTokens: generation?.native_tokens_completion || 0,
|
||||
totalCost: generation?.total_cost || 0,
|
||||
let modelId = this.options.openRouterModelId
|
||||
if (modelId && modelId.includes("gemini")) {
|
||||
return {
|
||||
type: "usage",
|
||||
cacheWriteTokens: 0,
|
||||
cacheReadTokens: generation?.native_tokens_cached || 0,
|
||||
// openrouter generation endpoint fails often
|
||||
inputTokens: (generation?.native_tokens_prompt || 0) - (generation?.native_tokens_cached || 0),
|
||||
outputTokens: generation?.native_tokens_completion || 0,
|
||||
totalCost: generation?.total_cost || 0,
|
||||
}
|
||||
} else {
|
||||
return {
|
||||
type: "usage",
|
||||
cacheWriteTokens: 0,
|
||||
cacheReadTokens: generation?.native_tokens_cached || 0,
|
||||
// openrouter generation endpoint fails often
|
||||
inputTokens: generation?.native_tokens_prompt || 0,
|
||||
outputTokens: generation?.native_tokens_completion || 0,
|
||||
totalCost: generation?.total_cost || 0,
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
// ignore if fails
|
||||
|
||||
@@ -98,14 +98,27 @@ export class OpenRouterHandler implements ApiHandler {
|
||||
}
|
||||
|
||||
if (!didOutputUsage && chunk.usage) {
|
||||
yield {
|
||||
type: "usage",
|
||||
cacheWriteTokens: 0,
|
||||
cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens || 0,
|
||||
inputTokens: chunk.usage.prompt_tokens || 0,
|
||||
outputTokens: chunk.usage.completion_tokens || 0,
|
||||
// @ts-ignore-next-line
|
||||
totalCost: (chunk.usage.cost || 0) + (chunk.usage.cost_details?.upstream_inference_cost || 0),
|
||||
let modelId = this.options.openRouterModelId
|
||||
if (modelId && modelId.includes("gemini")) {
|
||||
yield {
|
||||
type: "usage",
|
||||
cacheWriteTokens: 0,
|
||||
cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens || 0,
|
||||
inputTokens: (chunk.usage.prompt_tokens || 0) - (chunk.usage.prompt_tokens_details?.cached_tokens || 0),
|
||||
outputTokens: chunk.usage.completion_tokens || 0,
|
||||
// @ts-ignore-next-line
|
||||
totalCost: (chunk.usage.cost || 0) + (chunk.usage.cost_details?.upstream_inference_cost || 0),
|
||||
}
|
||||
} else {
|
||||
yield {
|
||||
type: "usage",
|
||||
cacheWriteTokens: 0,
|
||||
cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens || 0,
|
||||
inputTokens: chunk.usage.prompt_tokens || 0,
|
||||
outputTokens: chunk.usage.completion_tokens || 0,
|
||||
// @ts-ignore-next-line
|
||||
totalCost: (chunk.usage.cost || 0) + (chunk.usage.cost_details?.upstream_inference_cost || 0),
|
||||
}
|
||||
}
|
||||
didOutputUsage = true
|
||||
}
|
||||
@@ -127,14 +140,27 @@ export class OpenRouterHandler implements ApiHandler {
|
||||
const generationIterator = this.fetchGenerationDetails(this.lastGenerationId)
|
||||
const generation = (await generationIterator.next()).value
|
||||
// console.log("OpenRouter generation details:", generation)
|
||||
return {
|
||||
type: "usage",
|
||||
cacheWriteTokens: 0,
|
||||
cacheReadTokens: generation?.native_tokens_cached || 0,
|
||||
// openrouter generation endpoint fails often
|
||||
inputTokens: generation?.native_tokens_prompt || 0,
|
||||
outputTokens: generation?.native_tokens_completion || 0,
|
||||
totalCost: generation?.total_cost || 0,
|
||||
let modelId = this.options.openRouterModelId
|
||||
if (modelId && modelId.includes("gemini")) {
|
||||
return {
|
||||
type: "usage",
|
||||
cacheWriteTokens: 0,
|
||||
cacheReadTokens: generation?.native_tokens_cached || 0,
|
||||
// openrouter generation endpoint fails often
|
||||
inputTokens: (generation?.native_tokens_prompt || 0) - (generation?.native_tokens_cached || 0),
|
||||
outputTokens: generation?.native_tokens_completion || 0,
|
||||
totalCost: generation?.total_cost || 0,
|
||||
}
|
||||
} else {
|
||||
return {
|
||||
type: "usage",
|
||||
cacheWriteTokens: 0,
|
||||
cacheReadTokens: generation?.native_tokens_cached || 0,
|
||||
// openrouter generation endpoint fails often
|
||||
inputTokens: generation?.native_tokens_prompt || 0,
|
||||
outputTokens: generation?.native_tokens_completion || 0,
|
||||
totalCost: generation?.total_cost || 0,
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
// ignore if fails
|
||||
|
||||
Reference in New Issue
Block a user