luulam/9router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(headroom): report effective payload savings

Browse Source 
Break out tool schema and tool-history bytes in the size snapshot and
add an effective byte-savings percentage so token-saved logs reflect
the actual outbound payload reduction, not just processed content.
This commit is contained in:
minhnhat166
2026-08-05 11:29:07 +07:00
committed by decolua
parent 13ed14568d
commit da8691f866
2 changed files with 20 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
open-sse/rtk/headroom.js
View File

@@ -25,9 +25,17 @@ function messagePayload(body) {
function captureSizeSnapshot(body) { function captureSizeSnapshot(body) {
const messages = messagePayload(body); const messages = messagePayload(body);
const toolHistory = messages?.filter((message) =>
message?.role === "tool"
|| message?.role === "function"
|| message?.tool_calls?.length
|| message?.content?.some?.((part) => part?.type === "tool_use" || part?.type === "tool_result")
) || [];
return { return {
bodyBytes: jsonBytes(body), bodyBytes: jsonBytes(body),
messageBytes: messages ? jsonBytes(messages) : 0, messageBytes: messages ? jsonBytes(messages) : 0,
toolSchemaBytes: jsonBytes(body?.tools || []),
toolHistoryBytes: jsonBytes(toolHistory),
}; };
} }
@@ -336,7 +344,10 @@ export function formatHeadroomSizeLog(diagnostics) {
const before = diagnostics?.before; const before = diagnostics?.before;
const after = diagnostics?.after; const after = diagnostics?.after;
if (!before || !after) return ""; if (!before || !after) return "";
return `body=${before.bodyBytes}B→${after.bodyBytes}B messages=${before.messageBytes}B→${after.messageBytes}B`; const effective = before.bodyBytes > 0
? (((before.bodyBytes - after.bodyBytes) / before.bodyBytes) * 100).toFixed(1)
: "0.0";
return `body=${before.bodyBytes}B→${after.bodyBytes}B messages=${before.messageBytes}B→${after.messageBytes}B tools=${before.toolSchemaBytes || 0}B→${after.toolSchemaBytes || 0}B toolHistory=${before.toolHistoryBytes || 0}B→${after.toolHistoryBytes || 0}B effective=${effective}%`;
} }
export function isHeadroomPhantomSavings(stats, diagnostics, minShrinkRatio = 0.05) { export function isHeadroomPhantomSavings(stats, diagnostics, minShrinkRatio = 0.05) {

9
tests/unit/headroom.test.js
View File

@@ -1,5 +1,5 @@
import { describe, it, expect, vi, afterEach } from "vitest"; import { describe, it, expect, vi, afterEach } from "vitest";
import { compressWithHeadroom, formatHeadroomLog } from "../../open-sse/rtk/headroom.js"; import { compressWithHeadroom, formatHeadroomLog, formatHeadroomSizeLog } from "../../open-sse/rtk/headroom.js";
afterEach(() => { afterEach(() => {
vi.restoreAllMocks(); vi.restoreAllMocks();
@@ -209,4 +209,11 @@ describe("formatHeadroomLog", () => {
expect(formatHeadroomLog({ tokens_before: 100, tokens_after: 25, tokens_saved: 75 })) expect(formatHeadroomLog({ tokens_before: 100, tokens_after: 25, tokens_saved: 75 }))
.toBe("reported token delta=75 before=100 after=25 (75.0%)"); .toBe("reported token delta=75 before=100 after=25 (75.0%)");
}); });
it("reports effective payload, tool-schema, and tool-history sizes", () => {
expect(formatHeadroomSizeLog({
before: { bodyBytes: 1000, messageBytes: 800, toolSchemaBytes: 100, toolHistoryBytes: 500 },
after: { bodyBytes: 900, messageBytes: 700, toolSchemaBytes: 100, toolHistoryBytes: 400 },
})).toContain("tools=100B→100B toolHistory=500B→400B effective=10.0%");
});
}); });