mirror of
https://github.com/QwenLM/qwen-code.git
synced 2025-12-21 09:17:53 +00:00
fix: compression tool (#935)
This commit is contained in:
tanzhenxin
GitHub
372
packages/core/src/services/chatCompressionService.test.ts
Normal file
372
packages/core/src/services/chatCompressionService.test.ts
Normal file
@@ -0,0 +1,372 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
|
||||
import {
|
||||
ChatCompressionService,
|
||||
findCompressSplitPoint,
|
||||
} from './chatCompressionService.js';
|
||||
import type { Content, GenerateContentResponse } from '@google/genai';
|
||||
import { CompressionStatus } from '../core/turn.js';
|
||||
import { uiTelemetryService } from '../telemetry/uiTelemetry.js';
|
||||
import { tokenLimit } from '../core/tokenLimits.js';
|
||||
import type { GeminiChat } from '../core/geminiChat.js';
|
||||
import type { Config } from '../config/config.js';
|
||||
import { getInitialChatHistory } from '../utils/environmentContext.js';
|
||||
import type { ContentGenerator } from '../core/contentGenerator.js';
|
||||
|
||||
vi.mock('../telemetry/uiTelemetry.js');
|
||||
vi.mock('../core/tokenLimits.js');
|
||||
vi.mock('../telemetry/loggers.js');
|
||||
vi.mock('../utils/environmentContext.js');
|
||||
|
||||
describe('findCompressSplitPoint', () => {
|
||||
it('should throw an error for non-positive numbers', () => {
|
||||
expect(() => findCompressSplitPoint([], 0)).toThrow(
|
||||
'Fraction must be between 0 and 1',
|
||||
);
|
||||
});
|
||||
|
||||
it('should throw an error for a fraction greater than or equal to 1', () => {
|
||||
expect(() => findCompressSplitPoint([], 1)).toThrow(
|
||||
'Fraction must be between 0 and 1',
|
||||
);
|
||||
});
|
||||
|
||||
it('should handle an empty history', () => {
|
||||
expect(findCompressSplitPoint([], 0.5)).toBe(0);
|
||||
});
|
||||
|
||||
it('should handle a fraction in the middle', () => {
|
||||
const history: Content[] = [
|
||||
{ role: 'user', parts: [{ text: 'This is the first message.' }] }, // JSON length: 66 (19%)
|
||||
{ role: 'model', parts: [{ text: 'This is the second message.' }] }, // JSON length: 68 (40%)
|
||||
{ role: 'user', parts: [{ text: 'This is the third message.' }] }, // JSON length: 66 (60%)
|
||||
{ role: 'model', parts: [{ text: 'This is the fourth message.' }] }, // JSON length: 68 (80%)
|
||||
{ role: 'user', parts: [{ text: 'This is the fifth message.' }] }, // JSON length: 65 (100%)
|
||||
];
|
||||
expect(findCompressSplitPoint(history, 0.5)).toBe(4);
|
||||
});
|
||||
|
||||
it('should handle a fraction of last index', () => {
|
||||
const history: Content[] = [
|
||||
{ role: 'user', parts: [{ text: 'This is the first message.' }] }, // JSON length: 66 (19%)
|
||||
{ role: 'model', parts: [{ text: 'This is the second message.' }] }, // JSON length: 68 (40%)
|
||||
{ role: 'user', parts: [{ text: 'This is the third message.' }] }, // JSON length: 66 (60%)
|
||||
{ role: 'model', parts: [{ text: 'This is the fourth message.' }] }, // JSON length: 68 (80%)
|
||||
{ role: 'user', parts: [{ text: 'This is the fifth message.' }] }, // JSON length: 65 (100%)
|
||||
];
|
||||
expect(findCompressSplitPoint(history, 0.9)).toBe(4);
|
||||
});
|
||||
|
||||
it('should handle a fraction of after last index', () => {
|
||||
const history: Content[] = [
|
||||
{ role: 'user', parts: [{ text: 'This is the first message.' }] }, // JSON length: 66 (24%)
|
||||
{ role: 'model', parts: [{ text: 'This is the second message.' }] }, // JSON length: 68 (50%)
|
||||
{ role: 'user', parts: [{ text: 'This is the third message.' }] }, // JSON length: 66 (74%)
|
||||
{ role: 'model', parts: [{ text: 'This is the fourth message.' }] }, // JSON length: 68 (100%)
|
||||
];
|
||||
expect(findCompressSplitPoint(history, 0.8)).toBe(4);
|
||||
});
|
||||
|
||||
it('should return earlier splitpoint if no valid ones are after threshhold', () => {
|
||||
const history: Content[] = [
|
||||
{ role: 'user', parts: [{ text: 'This is the first message.' }] },
|
||||
{ role: 'model', parts: [{ text: 'This is the second message.' }] },
|
||||
{ role: 'user', parts: [{ text: 'This is the third message.' }] },
|
||||
{ role: 'model', parts: [{ functionCall: { name: 'foo', args: {} } }] },
|
||||
];
|
||||
// Can't return 4 because the previous item has a function call.
|
||||
expect(findCompressSplitPoint(history, 0.99)).toBe(2);
|
||||
});
|
||||
|
||||
it('should handle a history with only one item', () => {
|
||||
const historyWithEmptyParts: Content[] = [
|
||||
{ role: 'user', parts: [{ text: 'Message 1' }] },
|
||||
];
|
||||
expect(findCompressSplitPoint(historyWithEmptyParts, 0.5)).toBe(0);
|
||||
});
|
||||
|
||||
it('should handle history with weird parts', () => {
|
||||
const historyWithEmptyParts: Content[] = [
|
||||
{ role: 'user', parts: [{ text: 'Message 1' }] },
|
||||
{
|
||||
role: 'model',
|
||||
parts: [{ fileData: { fileUri: 'derp', mimeType: 'text/plain' } }],
|
||||
},
|
||||
{ role: 'user', parts: [{ text: 'Message 2' }] },
|
||||
];
|
||||
expect(findCompressSplitPoint(historyWithEmptyParts, 0.5)).toBe(2);
|
||||
});
|
||||
});
|
||||
|
||||
describe('ChatCompressionService', () => {
|
||||
let service: ChatCompressionService;
|
||||
let mockChat: GeminiChat;
|
||||
let mockConfig: Config;
|
||||
const mockModel = 'gemini-pro';
|
||||
const mockPromptId = 'test-prompt-id';
|
||||
|
||||
beforeEach(() => {
|
||||
service = new ChatCompressionService();
|
||||
mockChat = {
|
||||
getHistory: vi.fn(),
|
||||
} as unknown as GeminiChat;
|
||||
mockConfig = {
|
||||
getChatCompression: vi.fn(),
|
||||
getContentGenerator: vi.fn(),
|
||||
} as unknown as Config;
|
||||
|
||||
vi.mocked(tokenLimit).mockReturnValue(1000);
|
||||
vi.mocked(uiTelemetryService.getLastPromptTokenCount).mockReturnValue(500);
|
||||
vi.mocked(getInitialChatHistory).mockImplementation(
|
||||
async (_config, extraHistory) => extraHistory || [],
|
||||
);
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
vi.restoreAllMocks();
|
||||
});
|
||||
|
||||
it('should return NOOP if history is empty', async () => {
|
||||
vi.mocked(mockChat.getHistory).mockReturnValue([]);
|
||||
const result = await service.compress(
|
||||
mockChat,
|
||||
mockPromptId,
|
||||
false,
|
||||
mockModel,
|
||||
mockConfig,
|
||||
false,
|
||||
);
|
||||
expect(result.info.compressionStatus).toBe(CompressionStatus.NOOP);
|
||||
expect(result.newHistory).toBeNull();
|
||||
});
|
||||
|
||||
it('should return NOOP if previously failed and not forced', async () => {
|
||||
vi.mocked(mockChat.getHistory).mockReturnValue([
|
||||
{ role: 'user', parts: [{ text: 'hi' }] },
|
||||
]);
|
||||
const result = await service.compress(
|
||||
mockChat,
|
||||
mockPromptId,
|
||||
false,
|
||||
mockModel,
|
||||
mockConfig,
|
||||
true,
|
||||
);
|
||||
expect(result.info.compressionStatus).toBe(CompressionStatus.NOOP);
|
||||
expect(result.newHistory).toBeNull();
|
||||
});
|
||||
|
||||
it('should return NOOP if under token threshold and not forced', async () => {
|
||||
vi.mocked(mockChat.getHistory).mockReturnValue([
|
||||
{ role: 'user', parts: [{ text: 'hi' }] },
|
||||
]);
|
||||
vi.mocked(uiTelemetryService.getLastPromptTokenCount).mockReturnValue(600);
|
||||
vi.mocked(tokenLimit).mockReturnValue(1000);
|
||||
// Threshold is 0.7 * 1000 = 700. 600 < 700, so NOOP.
|
||||
|
||||
const result = await service.compress(
|
||||
mockChat,
|
||||
mockPromptId,
|
||||
false,
|
||||
mockModel,
|
||||
mockConfig,
|
||||
false,
|
||||
);
|
||||
expect(result.info.compressionStatus).toBe(CompressionStatus.NOOP);
|
||||
expect(result.newHistory).toBeNull();
|
||||
});
|
||||
|
||||
it('should compress if over token threshold', async () => {
|
||||
const history: Content[] = [
|
||||
{ role: 'user', parts: [{ text: 'msg1' }] },
|
||||
{ role: 'model', parts: [{ text: 'msg2' }] },
|
||||
{ role: 'user', parts: [{ text: 'msg3' }] },
|
||||
{ role: 'model', parts: [{ text: 'msg4' }] },
|
||||
];
|
||||
vi.mocked(mockChat.getHistory).mockReturnValue(history);
|
||||
vi.mocked(uiTelemetryService.getLastPromptTokenCount).mockReturnValue(800);
|
||||
vi.mocked(tokenLimit).mockReturnValue(1000);
|
||||
const mockGenerateContent = vi.fn().mockResolvedValue({
|
||||
candidates: [
|
||||
{
|
||||
content: {
|
||||
parts: [{ text: 'Summary' }],
|
||||
},
|
||||
},
|
||||
],
|
||||
} as unknown as GenerateContentResponse);
|
||||
vi.mocked(mockConfig.getContentGenerator).mockReturnValue({
|
||||
generateContent: mockGenerateContent,
|
||||
} as unknown as ContentGenerator);
|
||||
|
||||
const result = await service.compress(
|
||||
mockChat,
|
||||
mockPromptId,
|
||||
false,
|
||||
mockModel,
|
||||
mockConfig,
|
||||
false,
|
||||
);
|
||||
|
||||
expect(result.info.compressionStatus).toBe(CompressionStatus.COMPRESSED);
|
||||
expect(result.newHistory).not.toBeNull();
|
||||
expect(result.newHistory![0].parts![0].text).toBe('Summary');
|
||||
expect(mockGenerateContent).toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('should force compress even if under threshold', async () => {
|
||||
const history: Content[] = [
|
||||
{ role: 'user', parts: [{ text: 'msg1' }] },
|
||||
{ role: 'model', parts: [{ text: 'msg2' }] },
|
||||
{ role: 'user', parts: [{ text: 'msg3' }] },
|
||||
{ role: 'model', parts: [{ text: 'msg4' }] },
|
||||
];
|
||||
vi.mocked(mockChat.getHistory).mockReturnValue(history);
|
||||
vi.mocked(uiTelemetryService.getLastPromptTokenCount).mockReturnValue(100);
|
||||
vi.mocked(tokenLimit).mockReturnValue(1000);
|
||||
|
||||
const mockGenerateContent = vi.fn().mockResolvedValue({
|
||||
candidates: [
|
||||
{
|
||||
content: {
|
||||
parts: [{ text: 'Summary' }],
|
||||
},
|
||||
},
|
||||
],
|
||||
} as unknown as GenerateContentResponse);
|
||||
vi.mocked(mockConfig.getContentGenerator).mockReturnValue({
|
||||
generateContent: mockGenerateContent,
|
||||
} as unknown as ContentGenerator);
|
||||
|
||||
const result = await service.compress(
|
||||
mockChat,
|
||||
mockPromptId,
|
||||
true, // forced
|
||||
mockModel,
|
||||
mockConfig,
|
||||
false,
|
||||
);
|
||||
|
||||
expect(result.info.compressionStatus).toBe(CompressionStatus.COMPRESSED);
|
||||
expect(result.newHistory).not.toBeNull();
|
||||
});
|
||||
|
||||
it('should return FAILED if new token count is inflated', async () => {
|
||||
const history: Content[] = [
|
||||
{ role: 'user', parts: [{ text: 'msg1' }] },
|
||||
{ role: 'model', parts: [{ text: 'msg2' }] },
|
||||
];
|
||||
vi.mocked(mockChat.getHistory).mockReturnValue(history);
|
||||
vi.mocked(uiTelemetryService.getLastPromptTokenCount).mockReturnValue(10);
|
||||
vi.mocked(tokenLimit).mockReturnValue(1000);
|
||||
|
||||
const longSummary = 'a'.repeat(1000); // Long summary to inflate token count
|
||||
const mockGenerateContent = vi.fn().mockResolvedValue({
|
||||
candidates: [
|
||||
{
|
||||
content: {
|
||||
parts: [{ text: longSummary }],
|
||||
},
|
||||
},
|
||||
],
|
||||
} as unknown as GenerateContentResponse);
|
||||
vi.mocked(mockConfig.getContentGenerator).mockReturnValue({
|
||||
generateContent: mockGenerateContent,
|
||||
} as unknown as ContentGenerator);
|
||||
|
||||
const result = await service.compress(
|
||||
mockChat,
|
||||
mockPromptId,
|
||||
true,
|
||||
mockModel,
|
||||
mockConfig,
|
||||
false,
|
||||
);
|
||||
|
||||
expect(result.info.compressionStatus).toBe(
|
||||
CompressionStatus.COMPRESSION_FAILED_INFLATED_TOKEN_COUNT,
|
||||
);
|
||||
expect(result.newHistory).toBeNull();
|
||||
});
|
||||
|
||||
it('should return FAILED if summary is empty string', async () => {
|
||||
const history: Content[] = [
|
||||
{ role: 'user', parts: [{ text: 'msg1' }] },
|
||||
{ role: 'model', parts: [{ text: 'msg2' }] },
|
||||
];
|
||||
vi.mocked(mockChat.getHistory).mockReturnValue(history);
|
||||
vi.mocked(uiTelemetryService.getLastPromptTokenCount).mockReturnValue(100);
|
||||
vi.mocked(tokenLimit).mockReturnValue(1000);
|
||||
|
||||
const mockGenerateContent = vi.fn().mockResolvedValue({
|
||||
candidates: [
|
||||
{
|
||||
content: {
|
||||
parts: [{ text: '' }], // Empty summary
|
||||
},
|
||||
},
|
||||
],
|
||||
} as unknown as GenerateContentResponse);
|
||||
vi.mocked(mockConfig.getContentGenerator).mockReturnValue({
|
||||
generateContent: mockGenerateContent,
|
||||
} as unknown as ContentGenerator);
|
||||
|
||||
const result = await service.compress(
|
||||
mockChat,
|
||||
mockPromptId,
|
||||
true,
|
||||
mockModel,
|
||||
mockConfig,
|
||||
false,
|
||||
);
|
||||
|
||||
expect(result.info.compressionStatus).toBe(
|
||||
CompressionStatus.COMPRESSION_FAILED_EMPTY_SUMMARY,
|
||||
);
|
||||
expect(result.newHistory).toBeNull();
|
||||
expect(result.info.originalTokenCount).toBe(100);
|
||||
expect(result.info.newTokenCount).toBe(100);
|
||||
});
|
||||
|
||||
it('should return FAILED if summary is only whitespace', async () => {
|
||||
const history: Content[] = [
|
||||
{ role: 'user', parts: [{ text: 'msg1' }] },
|
||||
{ role: 'model', parts: [{ text: 'msg2' }] },
|
||||
];
|
||||
vi.mocked(mockChat.getHistory).mockReturnValue(history);
|
||||
vi.mocked(uiTelemetryService.getLastPromptTokenCount).mockReturnValue(100);
|
||||
vi.mocked(tokenLimit).mockReturnValue(1000);
|
||||
|
||||
const mockGenerateContent = vi.fn().mockResolvedValue({
|
||||
candidates: [
|
||||
{
|
||||
content: {
|
||||
parts: [{ text: ' \n\t ' }], // Only whitespace
|
||||
},
|
||||
},
|
||||
],
|
||||
} as unknown as GenerateContentResponse);
|
||||
vi.mocked(mockConfig.getContentGenerator).mockReturnValue({
|
||||
generateContent: mockGenerateContent,
|
||||
} as unknown as ContentGenerator);
|
||||
|
||||
const result = await service.compress(
|
||||
mockChat,
|
||||
mockPromptId,
|
||||
true,
|
||||
mockModel,
|
||||
mockConfig,
|
||||
false,
|
||||
);
|
||||
|
||||
expect(result.info.compressionStatus).toBe(
|
||||
CompressionStatus.COMPRESSION_FAILED_EMPTY_SUMMARY,
|
||||
);
|
||||
expect(result.newHistory).toBeNull();
|
||||
});
|
||||
});
|
||||
235
packages/core/src/services/chatCompressionService.ts
Normal file
235
packages/core/src/services/chatCompressionService.ts
Normal file
@@ -0,0 +1,235 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { Content } from '@google/genai';
|
||||
import type { Config } from '../config/config.js';
|
||||
import type { GeminiChat } from '../core/geminiChat.js';
|
||||
import { type ChatCompressionInfo, CompressionStatus } from '../core/turn.js';
|
||||
import { uiTelemetryService } from '../telemetry/uiTelemetry.js';
|
||||
import { tokenLimit } from '../core/tokenLimits.js';
|
||||
import { getCompressionPrompt } from '../core/prompts.js';
|
||||
import { getResponseText } from '../utils/partUtils.js';
|
||||
import { logChatCompression } from '../telemetry/loggers.js';
|
||||
import { makeChatCompressionEvent } from '../telemetry/types.js';
|
||||
import { getInitialChatHistory } from '../utils/environmentContext.js';
|
||||
|
||||
/**
|
||||
* Threshold for compression token count as a fraction of the model's token limit.
|
||||
* If the chat history exceeds this threshold, it will be compressed.
|
||||
*/
|
||||
export const COMPRESSION_TOKEN_THRESHOLD = 0.7;
|
||||
|
||||
/**
|
||||
* The fraction of the latest chat history to keep. A value of 0.3
|
||||
* means that only the last 30% of the chat history will be kept after compression.
|
||||
*/
|
||||
export const COMPRESSION_PRESERVE_THRESHOLD = 0.3;
|
||||
|
||||
/**
|
||||
* Returns the index of the oldest item to keep when compressing. May return
|
||||
* contents.length which indicates that everything should be compressed.
|
||||
*
|
||||
* Exported for testing purposes.
|
||||
*/
|
||||
export function findCompressSplitPoint(
|
||||
contents: Content[],
|
||||
fraction: number,
|
||||
): number {
|
||||
if (fraction <= 0 || fraction >= 1) {
|
||||
throw new Error('Fraction must be between 0 and 1');
|
||||
}
|
||||
|
||||
const charCounts = contents.map((content) => JSON.stringify(content).length);
|
||||
const totalCharCount = charCounts.reduce((a, b) => a + b, 0);
|
||||
const targetCharCount = totalCharCount * fraction;
|
||||
|
||||
let lastSplitPoint = 0; // 0 is always valid (compress nothing)
|
||||
let cumulativeCharCount = 0;
|
||||
for (let i = 0; i < contents.length; i++) {
|
||||
const content = contents[i];
|
||||
if (
|
||||
content.role === 'user' &&
|
||||
!content.parts?.some((part) => !!part.functionResponse)
|
||||
) {
|
||||
if (cumulativeCharCount >= targetCharCount) {
|
||||
return i;
|
||||
}
|
||||
lastSplitPoint = i;
|
||||
}
|
||||
cumulativeCharCount += charCounts[i];
|
||||
}
|
||||
|
||||
// We found no split points after targetCharCount.
|
||||
// Check if it's safe to compress everything.
|
||||
const lastContent = contents[contents.length - 1];
|
||||
if (
|
||||
lastContent?.role === 'model' &&
|
||||
!lastContent?.parts?.some((part) => part.functionCall)
|
||||
) {
|
||||
return contents.length;
|
||||
}
|
||||
|
||||
// Can't compress everything so just compress at last splitpoint.
|
||||
return lastSplitPoint;
|
||||
}
|
||||
|
||||
export class ChatCompressionService {
|
||||
async compress(
|
||||
chat: GeminiChat,
|
||||
promptId: string,
|
||||
force: boolean,
|
||||
model: string,
|
||||
config: Config,
|
||||
hasFailedCompressionAttempt: boolean,
|
||||
): Promise<{ newHistory: Content[] | null; info: ChatCompressionInfo }> {
|
||||
const curatedHistory = chat.getHistory(true);
|
||||
|
||||
// Regardless of `force`, don't do anything if the history is empty.
|
||||
if (
|
||||
curatedHistory.length === 0 ||
|
||||
(hasFailedCompressionAttempt && !force)
|
||||
) {
|
||||
return {
|
||||
newHistory: null,
|
||||
info: {
|
||||
originalTokenCount: 0,
|
||||
newTokenCount: 0,
|
||||
compressionStatus: CompressionStatus.NOOP,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
const originalTokenCount = uiTelemetryService.getLastPromptTokenCount();
|
||||
|
||||
const contextPercentageThreshold =
|
||||
config.getChatCompression()?.contextPercentageThreshold;
|
||||
|
||||
// Don't compress if not forced and we are under the limit.
|
||||
if (!force) {
|
||||
const threshold =
|
||||
contextPercentageThreshold ?? COMPRESSION_TOKEN_THRESHOLD;
|
||||
if (originalTokenCount < threshold * tokenLimit(model)) {
|
||||
return {
|
||||
newHistory: null,
|
||||
info: {
|
||||
originalTokenCount,
|
||||
newTokenCount: originalTokenCount,
|
||||
compressionStatus: CompressionStatus.NOOP,
|
||||
},
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
const splitPoint = findCompressSplitPoint(
|
||||
curatedHistory,
|
||||
1 - COMPRESSION_PRESERVE_THRESHOLD,
|
||||
);
|
||||
|
||||
const historyToCompress = curatedHistory.slice(0, splitPoint);
|
||||
const historyToKeep = curatedHistory.slice(splitPoint);
|
||||
|
||||
if (historyToCompress.length === 0) {
|
||||
return {
|
||||
newHistory: null,
|
||||
info: {
|
||||
originalTokenCount,
|
||||
newTokenCount: originalTokenCount,
|
||||
compressionStatus: CompressionStatus.NOOP,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
const summaryResponse = await config.getContentGenerator().generateContent(
|
||||
{
|
||||
model,
|
||||
contents: [
|
||||
...historyToCompress,
|
||||
{
|
||||
role: 'user',
|
||||
parts: [
|
||||
{
|
||||
text: 'First, reason in your scratchpad. Then, generate the <state_snapshot>.',
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
config: {
|
||||
systemInstruction: getCompressionPrompt(),
|
||||
},
|
||||
},
|
||||
promptId,
|
||||
);
|
||||
const summary = getResponseText(summaryResponse) ?? '';
|
||||
const isSummaryEmpty = !summary || summary.trim().length === 0;
|
||||
|
||||
let newTokenCount = originalTokenCount;
|
||||
let extraHistory: Content[] = [];
|
||||
|
||||
if (!isSummaryEmpty) {
|
||||
extraHistory = [
|
||||
{
|
||||
role: 'user',
|
||||
parts: [{ text: summary }],
|
||||
},
|
||||
{
|
||||
role: 'model',
|
||||
parts: [{ text: 'Got it. Thanks for the additional context!' }],
|
||||
},
|
||||
...historyToKeep,
|
||||
];
|
||||
|
||||
// Use a shared utility to construct the initial history for an accurate token count.
|
||||
const fullNewHistory = await getInitialChatHistory(config, extraHistory);
|
||||
|
||||
// Estimate token count 1 token ≈ 4 characters
|
||||
newTokenCount = Math.floor(
|
||||
fullNewHistory.reduce(
|
||||
(total, content) => total + JSON.stringify(content).length,
|
||||
0,
|
||||
) / 4,
|
||||
);
|
||||
}
|
||||
|
||||
logChatCompression(
|
||||
config,
|
||||
makeChatCompressionEvent({
|
||||
tokens_before: originalTokenCount,
|
||||
tokens_after: newTokenCount,
|
||||
}),
|
||||
);
|
||||
|
||||
if (isSummaryEmpty) {
|
||||
return {
|
||||
newHistory: null,
|
||||
info: {
|
||||
originalTokenCount,
|
||||
newTokenCount: originalTokenCount,
|
||||
compressionStatus: CompressionStatus.COMPRESSION_FAILED_EMPTY_SUMMARY,
|
||||
},
|
||||
};
|
||||
} else if (newTokenCount > originalTokenCount) {
|
||||
return {
|
||||
newHistory: null,
|
||||
info: {
|
||||
originalTokenCount,
|
||||
newTokenCount,
|
||||
compressionStatus:
|
||||
CompressionStatus.COMPRESSION_FAILED_INFLATED_TOKEN_COUNT,
|
||||
},
|
||||
};
|
||||
} else {
|
||||
uiTelemetryService.setLastPromptTokenCount(newTokenCount);
|
||||
return {
|
||||
newHistory: extraHistory,
|
||||
info: {
|
||||
originalTokenCount,
|
||||
newTokenCount,
|
||||
compressionStatus: CompressionStatus.COMPRESSED,
|
||||
},
|
||||
};
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user