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.

open-sse/handlers/chatCore.js

@@ -24,6 +24,7 @@ import { injectCaveman } from "../rtk/caveman.js";
 import { injectPonytail } from "../rtk/ponytail.js";
 import { compressMessages, formatRtkLog } from "../rtk/index.js";
 import { compressWithHeadroom, formatHeadroomLog, formatHeadroomSizeLog, isHeadroomPhantomSavings } from "../rtk/headroom.js";
+import { compressWithPxpipe, formatPxpipeLog } from "../rtk/pxpipe.js";
 import { getCapabilitiesForModel } from "../providers/capabilities.js";
 import { stripUnsupportedModalities } from "../translator/concerns/modality.js";
 import { prefetchRemoteImages } from "../translator/concerns/prefetch.js";
@@ -35,7 +36,7 @@ import { prefetchRemoteImages } from "../translator/concerns/prefetch.js";
  * @param {object} options.credentials - Provider credentials
  * @param {string} options.sourceFormatOverride - Override detected source format (e.g. "openai-responses")
  */
-export async function handleChatCore({ body, modelInfo, credentials, log, onCredentialsRefreshed, onRequestSuccess, onDisconnect, clientRawRequest, connectionId, userAgent, apiKey, ccFilterNaming, rtkEnabled, headroomEnabled, headroomUrl, headroomCompressUserMessages, cavemanEnabled, cavemanLevel, ponytailEnabled, ponytailLevel, sourceFormatOverride, providerThinking }) {
+export async function handleChatCore({ body, modelInfo, credentials, log, onCredentialsRefreshed, onRequestSuccess, onDisconnect, clientRawRequest, connectionId, userAgent, apiKey, ccFilterNaming, rtkEnabled, headroomEnabled, headroomUrl, headroomCompressUserMessages, cavemanEnabled, cavemanLevel, ponytailEnabled, ponytailLevel, pxpipeEnabled, pxpipeMinChars, pxpipeTimeoutMs, pxpipeTransform, onPxpipeEvent, sourceFormatOverride, providerThinking }) {
   const { provider, model } = modelInfo;
   const requestStartTime = Date.now();
 
@@ -186,6 +187,21 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
     log?.debug?.("PONYTAIL", `${ponytailLevel} | ${finalFormat}`);
   }
 
+  // PXPIPE: image bulky context (Claude-format bodies only), last saver before dispatch
+  let pxpipeSummary = null;
+  if (pxpipeEnabled) {
+    const pxpipeResult = await compressWithPxpipe(translatedBody, {
+      enabled: true, format: finalFormat, model: upstreamModel,
+      minChars: pxpipeMinChars, timeoutMs: pxpipeTimeoutMs, transform: pxpipeTransform,
+    });
+    pxpipeSummary = pxpipeResult.summary;
+    if (pxpipeResult.body) translatedBody = pxpipeResult.body;
+    const pxpipeLine = formatPxpipeLog(pxpipeSummary);
+    if (pxpipeLine) log?.info?.("PXPIPE", pxpipeLine);
+    else log?.debug?.("PXPIPE", `skipped: ${pxpipeSummary.reason}${pxpipeSummary.detail ? ` (${pxpipeSummary.detail})` : ""}`);
+    try { onPxpipeEvent?.({ provider, model, ...pxpipeSummary }); } catch { /* stats must not break requests */ }
+  }
+
   const executor = getExecutor(provider);
   trackPendingRequest(model, provider, connectionId, true);
   appendRequestLog({ model, provider, connectionId, status: "PENDING" }).catch(() => { });
@@ -254,6 +270,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
       request: extractRequestConfig(body, stream),
       providerRequest: translatedBody || null,
       response: { error: error.message || String(error), status: error.name === "AbortError" ? 499 : 502, thinking: null },
+      pxpipe: pxpipeSummary,
       status: "error"
     })).catch(() => { });
 
@@ -300,6 +317,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
       request: extractRequestConfig(body, stream),
       providerRequest: finalBody || translatedBody || null,
       response: { error: message, status: statusCode, thinking: null },
+      pxpipe: pxpipeSummary,
       status: "error"
     })).catch(() => { });
 
@@ -309,7 +327,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
     return createErrorResult(statusCode, errMsg, resetsAtMs);
   }
 
-  const sharedCtx = { provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess };
+  const sharedCtx = { provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, pxpipe: pxpipeSummary };
   const appendLog = (extra) => appendRequestLog({ model, provider, connectionId, ...extra }).catch(() => { });
   const trackDone = () => trackPendingRequest(model, provider, connectionId, false);