feat: add cache-ttl pruning mode

This commit is contained in:
Peter Steinberger
2026-01-21 19:44:20 +00:00
parent c415ccaed5
commit 9f59ff325b
18 changed files with 164 additions and 123 deletions

View File

@@ -135,12 +135,15 @@ describe("context-pruning", () => {
});
it("never prunes tool results before the first user message", () => {
const settings = computeEffectiveSettings({
mode: "aggressive",
const settings = {
...DEFAULT_CONTEXT_PRUNING_SETTINGS,
keepLastAssistants: 0,
hardClear: { placeholder: "[cleared]" },
});
if (!settings) throw new Error("expected settings");
softTrimRatio: 0.0,
hardClearRatio: 0.0,
minPrunableToolChars: 0,
hardClear: { enabled: true, placeholder: "[cleared]" },
softTrim: { maxChars: 10, headChars: 3, tailChars: 3 },
};
const messages: AgentMessage[] = [
makeAssistant("bootstrap tool calls"),
@@ -170,7 +173,7 @@ describe("context-pruning", () => {
expect(toolText(findToolResult(next, "t1"))).toBe("[cleared]");
});
it("mode aggressive clears eligible tool results before cutoff", () => {
it("hard-clear removes eligible tool results before cutoff", () => {
const messages: AgentMessage[] = [
makeUser("u1"),
makeAssistant("a1"),
@@ -195,9 +198,11 @@ describe("context-pruning", () => {
const settings = {
...DEFAULT_CONTEXT_PRUNING_SETTINGS,
mode: "aggressive",
keepLastAssistants: 1,
hardClear: { enabled: false, placeholder: "[cleared]" },
softTrimRatio: 10.0,
hardClearRatio: 0.0,
minPrunableToolChars: 0,
hardClear: { enabled: true, placeholder: "[cleared]" },
};
const ctx = {
@@ -258,6 +263,7 @@ describe("context-pruning", () => {
},
contextWindowTokens: 1000,
isToolPrunable: () => true,
lastCacheTouchAt: Date.now() - DEFAULT_CONTEXT_PRUNING_SETTINGS.ttlMs - 1000,
});
const messages: AgentMessage[] = [

View File

@@ -9,6 +9,17 @@ export default function contextPruningExtension(api: ExtensionAPI): void {
const runtime = getContextPruningRuntime(ctx.sessionManager);
if (!runtime) return undefined;
if (runtime.settings.mode === "cache-ttl") {
const ttlMs = runtime.settings.ttlMs;
const lastTouch = runtime.lastCacheTouchAt ?? null;
if (!lastTouch || ttlMs <= 0) {
return undefined;
}
if (ttlMs > 0 && Date.now() - lastTouch < ttlMs) {
return undefined;
}
}
const next = pruneContextMessages({
messages: event.messages as AgentMessage[],
settings: runtime.settings,

View File

@@ -211,34 +211,6 @@ export function pruneContextMessages(params: {
const isToolPrunable = params.isToolPrunable ?? makeToolPrunablePredicate(settings.tools);
if (settings.mode === "aggressive") {
let next: AgentMessage[] | null = null;
for (let i = pruneStartIndex; i < cutoffIndex; i++) {
const msg = messages[i];
if (!msg || msg.role !== "toolResult") continue;
if (!isToolPrunable(msg.toolName)) continue;
if (hasImageBlocks(msg.content)) {
continue;
}
const alreadyCleared =
msg.content.length === 1 &&
msg.content[0]?.type === "text" &&
msg.content[0].text === settings.hardClear.placeholder;
if (alreadyCleared) continue;
const cleared: ToolResultMessage = {
...msg,
content: [asText(settings.hardClear.placeholder)],
};
if (!next) next = messages.slice();
next[i] = cleared as unknown as AgentMessage;
}
return next ?? messages;
}
const totalCharsBefore = estimateContextChars(messages);
let totalChars = totalCharsBefore;
let ratio = totalChars / charWindow;

View File

@@ -4,6 +4,7 @@ export type ContextPruningRuntimeValue = {
settings: EffectiveContextPruningSettings;
contextWindowTokens?: number | null;
isToolPrunable: (toolName: string) => boolean;
lastCacheTouchAt?: number | null;
};
// Session-scoped runtime registry keyed by object identity.

View File

@@ -1,12 +1,15 @@
import { parseDurationMs } from "../../../cli/parse-duration.js";
export type ContextPruningToolMatch = {
allow?: string[];
deny?: string[];
};
export type ContextPruningMode = "off" | "adaptive" | "aggressive";
export type ContextPruningMode = "off" | "cache-ttl";
export type ContextPruningConfig = {
mode?: ContextPruningMode;
/** TTL to consider cache expired (duration string, default unit: minutes). */
ttl?: string;
keepLastAssistants?: number;
softTrimRatio?: number;
hardClearRatio?: number;
@@ -25,6 +28,7 @@ export type ContextPruningConfig = {
export type EffectiveContextPruningSettings = {
mode: Exclude<ContextPruningMode, "off">;
ttlMs: number;
keepLastAssistants: number;
softTrimRatio: number;
hardClearRatio: number;
@@ -42,7 +46,8 @@ export type EffectiveContextPruningSettings = {
};
export const DEFAULT_CONTEXT_PRUNING_SETTINGS: EffectiveContextPruningSettings = {
mode: "adaptive",
mode: "cache-ttl",
ttlMs: 5 * 60 * 1000,
keepLastAssistants: 3,
softTrimRatio: 0.3,
hardClearRatio: 0.5,
@@ -62,11 +67,19 @@ export const DEFAULT_CONTEXT_PRUNING_SETTINGS: EffectiveContextPruningSettings =
export function computeEffectiveSettings(raw: unknown): EffectiveContextPruningSettings | null {
if (!raw || typeof raw !== "object") return null;
const cfg = raw as ContextPruningConfig;
if (cfg.mode !== "adaptive" && cfg.mode !== "aggressive") return null;
if (cfg.mode !== "cache-ttl") return null;
const s: EffectiveContextPruningSettings = structuredClone(DEFAULT_CONTEXT_PRUNING_SETTINGS);
s.mode = cfg.mode;
if (typeof cfg.ttl === "string") {
try {
s.ttlMs = parseDurationMs(cfg.ttl, { defaultUnit: "m" });
} catch {
// keep default ttl
}
}
if (typeof cfg.keepLastAssistants === "number" && Number.isFinite(cfg.keepLastAssistants)) {
s.keepLastAssistants = Math.max(0, Math.floor(cfg.keepLastAssistants));
}
@@ -94,7 +107,7 @@ export function computeEffectiveSettings(raw: unknown): EffectiveContextPruningS
}
}
if (cfg.hardClear) {
if (s.mode === "adaptive" && typeof cfg.hardClear.enabled === "boolean") {
if (typeof cfg.hardClear.enabled === "boolean") {
s.hardClear.enabled = cfg.hardClear.enabled;
}
if (typeof cfg.hardClear.placeholder === "string" && cfg.hardClear.placeholder.trim()) {