feat(pxpipe): PXPIPE token saver — multimodal prompt compression (#2465)

Add pxpipe as an experimental fifth Token Saver: Claude-format request bodies above a configurable size threshold are rendered as dense PNGs via the pxpipe-proxy library API (transformAnthropicMessages) before dispatch, cutting estimated input tokens by ~35-60% on token-dense contexts. Integration follows the Headroom pattern: applied to the final body in chatCore just before dispatch, fail-open on any error/timeout. Managed npm install into DATA_DIR/pxpipe, dynamic loader with per-version cache-bust, JSONL event log with rotation, /api/pxpipe/* endpoints, Token Saver card (marked experimental) + /dashboard/pxpipe page, and per-request Activated/Skipped annotation in Request Details. Disabled by default.
2026-09-22 13:38:31 +00:00 · 2026-07-10 16:10:42 +07:00
parent e1f3399b73
commit dcf1927f22
26 changed files with 1324 additions and 7 deletions
@@ -0,0 +1,104 @@
+// PXPIPE: render bulky Claude-format context as dense PNGs via pxpipe-proxy's
+// library API (transformAnthropicMessages). Fail-open like every token saver:
+// any error/timeout returns { body: null, summary } and leaves the request untouched.
+import { FORMATS } from "../translator/formats.js";
+
+const DEFAULT_TIMEOUT_MS = 15000;
+const DEFAULT_MIN_CHARS = 25000;
+// pxpipe's own profitability gate assumes ~4 chars/token; reuse it for the
+// estimated before/after numbers surfaced in stats (marked "estimated" in UI).
+const EST_CHARS_PER_TOKEN = 4;
+
+function bodyChars(body) {
+  try {
+    return JSON.stringify(body)?.length || 0;
+  } catch {
+    return 0;
+  }
+}
+
+function estTokens(chars) {
+  return Math.round(chars / EST_CHARS_PER_TOKEN);
+}
+
+function skipped(reason, extra = {}) {
+  return { body: null, summary: { applied: false, reason, ...extra } };
+}
+
+// Transform a Claude-format request body through pxpipe. Returns
+// { body: <new body object> | null, summary } — body is null when nothing changed.
+// opts.transform is injected by the host (src side) so open-sse stays free of
+// filesystem/install concerns and remains usable standalone.
+export async function compressWithPxpipe(body, { enabled, format, model, minChars, timeoutMs, transform } = {}) {
+  if (!enabled) return skipped("disabled");
+  if (typeof transform !== "function") return skipped("not_installed");
+  if (!body) return skipped("missing_body");
+  if (format !== FORMATS.CLAUDE) return skipped("unsupported_format", { detail: format });
+
+  const startedAt = Date.now();
+  const originalChars = bodyChars(body);
+  const threshold = Number(minChars) > 0 ? Number(minChars) : DEFAULT_MIN_CHARS;
+  if (originalChars < threshold) {
+    return skipped("below_threshold", { originalChars, threshold });
+  }
+
+  try {
+    const encoded = new TextEncoder().encode(JSON.stringify(body));
+    const budget = Number(timeoutMs) > 0 ? Number(timeoutMs) : DEFAULT_TIMEOUT_MS;
+    // transformAnthropicMessages is local CPU work and can't be aborted; race a
+    // timer and discard the result if it loses (input body is never mutated).
+    const result = await Promise.race([
+      transform({
+        body: encoded,
+        model,
+        options: { minCompressChars: threshold },
+      }),
+      new Promise((resolve) => setTimeout(() => resolve(null), budget)),
+    ]);
+    if (!result) return skipped("timeout", { originalChars, durationMs: Date.now() - startedAt });
+    if (!result.applied) {
+      return skipped(result.reason || "passthrough", {
+        detail: result.detail,
+        originalChars,
+        durationMs: Date.now() - startedAt,
+      });
+    }
+
+    const newBody = JSON.parse(new TextDecoder().decode(result.body));
+    const compressedBodyChars = bodyChars(newBody);
+    const info = result.info || {};
+    const imagedChars = info.compressedChars || 0;
+    // The transformed body is BIGGER in bytes (base64 PNGs) but cheaper in tokens:
+    // images bill by pixels (Anthropic: pixels/750), not by encoded length. So the
+    // after-estimate is remaining-text tokens + image tokens — never chars/4 of the
+    // new body. Provider-billed usage recorded per request stays the ground truth.
+    const imageTokensEst = info.imageTokens
+      || (info.imagePixels ? Math.round(info.imagePixels / 750) : (info.imageCount || 0) * 4761);
+    const summary = {
+      applied: true,
+      reason: "applied",
+      originalChars,
+      compressedBodyChars,
+      imagedChars,
+      imageCount: info.imageCount || 0,
+      imageBytes: info.imageBytes || 0,
+      tokensBeforeEst: info.baselineTokens || estTokens(originalChars),
+      tokensAfterEst: estTokens(Math.max(0, originalChars - imagedChars)) + imageTokensEst,
+      durationMs: Date.now() - startedAt,
+      cacheOwnsControl: result.cache?.ownsCacheControl === true,
+    };
+    summary.tokensSavedEst = Math.max(0, summary.tokensBeforeEst - summary.tokensAfterEst);
+    summary.savedPct = summary.tokensBeforeEst > 0
+      ? +((summary.tokensSavedEst / summary.tokensBeforeEst) * 100).toFixed(2)
+      : 0;
+    return { body: newBody, summary };
+  } catch (e) {
+    return skipped("transform_error", { detail: e?.message || String(e), originalChars, durationMs: Date.now() - startedAt });
+  }
+}
+
+export function formatPxpipeLog(summary) {
+  if (!summary) return null;
+  if (!summary.applied) return null;
+  return `imaged ${summary.imagedChars}ch → ${summary.imageCount} image(s) | est ${summary.tokensBeforeEst}→${summary.tokensAfterEst} tokens (-${summary.savedPct}%) | ${summary.durationMs}ms`;
+}