contextHistoryStrategies

SUPPORT · constant · Runtime value

Import

TypeScript

import { contextHistoryStrategies } from '@jangts/agent-core/support';

JavaScript

import { contextHistoryStrategies } from '@jangts/agent-core/support';

Other public entry points:@jangts/agent-core/support, @jangts/agent-core/support/context.

Definition

const contextHistoryStrategies: Readonly<{ compact: Readonly<{ targetRatio: 0.25; keepGroups: 1; }>; balanced: Readonly<{ targetRatio: 0.5; keepGroups: 3; }>; extended: Readonly<{ targetRatio: 0.75; keepGroups: 6; }>; }>

Field structure

Field	Type	Required	Description
compact	Readonly<{ targetRatio: 0.25; keepGroups: 1; }>	Required	See the type definition and usage context.
balanced	Readonly<{ targetRatio: 0.5; keepGroups: 3; }>	Required	See the type definition and usage context.
extended	Readonly<{ targetRatio: 0.75; keepGroups: 6; }>	Required	See the type definition and usage context.

Examples

• Generate processing strategies from history semantics: Reuse fragment identity and hard budgets to generate complete steps and references for recent or continuity.

Reuse an existing fragment to generate a recent-history strategy

Beginner · Node.js

TypeScript

import { Support } from '@jangts/agent-core';
const fragment = { id: 'history', maxChars: 4000 };
const strategy = Support.createContextStrategy({ kind: 'recent', fragment, field: 'messages' });
console.log(strategy.policy, strategy.compressors);

JavaScript

import { Support } from '@jangts/agent-core';
const fragment = { id: 'history', maxChars: 4000 };
const strategy = Support.createContextStrategy({ kind: 'recent', fragment, field: 'messages' });
console.log(strategy.policy, strategy.compressors);

Add kept groups and target size to the same configuration

Configuration · Node.js

TypeScript

import { Support } from '@jangts/agent-core';
const fragment = { id: 'history', maxChars: 4000 };
const strategy = Support.createContextStrategy({ kind: 'recent', fragment, field: 'messages',
  keepGroups: 3, targetChars: 2500, grouping: { kind: 'user-turn' },
});
console.log(strategy.policy);

JavaScript

import { Support } from '@jangts/agent-core';
const fragment = { id: 'history', maxChars: 4000 };
const strategy = Support.createContextStrategy({ kind: 'recent', fragment, field: 'messages',
    keepGroups: 3, targetChars: 2500, grouping: { kind: 'user-turn' },
});
console.log(strategy.policy);

Supply a compression algorithm explicitly when old topics must be carried forward

Extension · Node.js

This example only assembles the strategy. The policy/compressors/selectors are used as configuration for existing context nodes; no new request is sent and no extra budget is created here.

TypeScript

import { Support } from '@jangts/agent-core';
const compressor = Support.createContextCompressor({ id: 'history-summary',
  instruction: '按资料原意概括旧历史，保留事实、时间和未完成事项。',
  transport: 'core:plain-text', maxOutputTokens: 500,
  parse(value: unknown) { if (typeof value !== 'string' || !value.trim()) throw new TypeError('需要摘要'); return { messages: [{ role: 'user', content: value }] }; },
});
const strategy = Support.createContextStrategy({ kind: 'continuity',
  fragment: { id: 'history', maxChars: 4000 }, field: 'messages', compressor,
  targetChars: 2500, keepGroups: 2,
});
console.log(strategy.policy, strategy.compressors.map(item => item.id));

JavaScript

import { Support } from '@jangts/agent-core';
const compressor = Support.createContextCompressor({ id: 'history-summary',
    instruction: '按资料原意概括旧历史，保留事实、时间和未完成事项。',
    transport: 'core:plain-text', maxOutputTokens: 500,
    parse(value) { if (typeof value !== 'string' || !value.trim())
        throw new TypeError('需要摘要'); return { messages: [{ role: 'user', content: value }] }; },
});
const strategy = Support.createContextStrategy({ kind: 'continuity',
    fragment: { id: 'history', maxChars: 4000 }, field: 'messages', compressor,
    targetChars: 2500, keepGroups: 2,
});
console.log(strategy.policy, strategy.compressors.map(item => item.id));

Related policy source

• Scenario catalog, generated steps, and precise overrides