billion-context 0.1.75-pr.335.313 → 0.1.75-pr.424.312

package/dist/index.js

@@ -48328,33 +48328,64 @@ async function contextFromRegistry(model, host) {
 function peekRegistryContext(model, host) {
   return registryLookup(cache2, model, host);
 }
+var VARIANT_SUFFIXES = [
+  "-interleaved-thinking",
+  "-thinking",
+  "-reasoning",
+  "-extended",
+  "-fast",
+  "-high",
+  "-medium",
+  "-low"
+];
+function modelVariants(name) {
+  const variants = [name];
+  let current = name;
+  for (; ; ) {
+    let stripped = false;
+    for (const suffix of VARIANT_SUFFIXES) {
+      if (current.length > suffix.length && current.endsWith(suffix)) {
+        current = current.slice(0, -suffix.length);
+        variants.push(current);
+        stripped = true;
+        break;
+      }
+    }
+    if (!stripped) break;
+  }
+  return variants;
+}
 function registryLookup(reg, model, host) {
   if (!reg || !model) return void 0;
   const provider = host ? providerFromHost(host) : void 0;
-  const candidates = provider ? [`${provider}/${model}`, model] : [model];
-  for (const key of candidates) {
-    const entry = reg[key];
-    const ctx = entry?.limit?.context;
-    if (typeof ctx === "number" && ctx > 0) return ctx;
-  }
-  if (provider === void 0) {
-    const suffix = `/${model}`;
-    let max;
-    const distinct = /* @__PURE__ */ new Set();
-    const parts = [];
-    for (const key of Object.keys(reg)) {
-      if (!key.endsWith(suffix)) continue;
-      const ctx = reg[key].limit?.context;
-      if (typeof ctx !== "number" || ctx <= 0) continue;
-      if (max === void 0 || ctx > max) max = ctx;
-      distinct.add(ctx);
-      parts.push(`${key}=${ctx}`);
-    }
-    if (max !== void 0 && distinct.size > 1 && !warnedConflicts.has(model)) {
-      warnedConflicts.add(model);
-      log("warn", `[acp-registry] conflicting context windows for "${model}" (${parts.join(", ")}) \u2014 using max ${max}`);
+  for (const name of modelVariants(model)) {
+    const candidates = provider ? [`${provider}/${name}`, name] : [name];
+    for (const key of candidates) {
+      const entry = reg[key];
+      const ctx = entry?.limit?.context;
+      if (typeof ctx === "number" && ctx > 0) return ctx;
+    }
+    if (provider === void 0) {
+      const suffix = `/${name}`;
+      let max;
+      const distinct = /* @__PURE__ */ new Set();
+      const parts = [];
+      for (const key of Object.keys(reg)) {
+        if (!key.endsWith(suffix)) continue;
+        const ctx = reg[key].limit?.context;
+        if (typeof ctx !== "number" || ctx <= 0) continue;
+        if (max === void 0 || ctx > max) max = ctx;
+        distinct.add(ctx);
+        parts.push(`${key}=${ctx}`);
+      }
+      if (max !== void 0) {
+        if (distinct.size > 1 && !warnedConflicts.has(name)) {
+          warnedConflicts.add(name);
+          log("warn", `[acp-registry] conflicting context windows for "${name}" (${parts.join(", ")}) \u2014 using max ${max}`);
+        }
+        return max;
+      }
     }
-    return max;
   }
   return void 0;
 }
@@ -48479,14 +48510,11 @@ ${summary}` }]
   }
   return { items, replaced, dropped };
 }
-function codexCompactGatePre(session, effectiveLimit) {
-  if (effectiveLimit <= 0) return false;
+function codexCompactGate(session, effectiveLimit, transformOk) {
+  if (!transformOk || effectiveLimit <= 0) return false;
   if (session.stats.lastInputTokens >= effectiveLimit * 0.9) return false;
   return session.state.blocks.some((b2) => b2.active);
 }
-function codexCompactGate(session, effectiveLimit, transformOk) {
-  return transformOk && codexCompactGatePre(session, effectiveLimit);
-}
 function buildTriggerForgeBody(summaryText, usage, stream2) {
   const compactionItem = {
     type: "compaction",
@@ -54403,7 +54431,7 @@ function handlePluginStatus(conversationId2, res, fallbackLatest = false) {
   if (entry) entry.lastSeen = Date.now();
   const limit = session.metadata.effectiveContextLimit;
   const mem = remembered.get(session.id);
-  const modelContextLimit = typeof limit === "number" && limit > 0 ? limit : 2e5;
+  const modelContextLimit = typeof limit === "number" && limit > 0 ? limit : 0;
   let panel;
   try {
     panel = buildStatusPanel({
@@ -56395,6 +56423,9 @@ function logUnrecognizedPath(log2, url) {
     log2("info", `unrecognized path ${key}: forwarding unchanged; further occurrences suppressed`);
   }
 }
+function isModelDiscoveryPath(path17) {
+  return path17.replace(/\/+$/, "").endsWith("/models");
+}
 var BILI_HOP_HEADER = "x-bili-hop";
 function parseLauncherModelWindows(raw) {
   if (!raw) return {};
@@ -56938,11 +56969,11 @@ ${bodyBuffer.toString("utf8")}`);
       const pluginWindow = pluginReportedContextWindow(req.headers);
       const launcherWindow = launcherContextWindow(model);
       const configuredWindow = resolveConfiguredContextLimit(opts.routes, embeddedUrl, model);
-      const peekWindow = host ? peekRegistryContext(model, host) : void 0;
+      const peekWindow = peekRegistryContext(model, host);
       let native = betaWindow ?? pluginWindow ?? launcherWindow ?? configuredWindow ?? peekWindow ?? lookupContextLimit(model);
       const operatorWindowTuned = resolveCompress(opts.routes, embeddedUrl, model, opts.compress).modelContextLimit !== void 0;
       nativeFromFallback = !betaWindow && !pluginWindow && !launcherWindow && !peekWindow && !configuredWindow && !operatorWindowTuned;
-      if (!native && host) {
+      if (!native) {
         native = await contextFromRegistry(model, host);
         if (native) nativeFromFallback = false;
       }
@@ -57042,7 +57073,6 @@ ${bodyBuffer.toString("utf8")}`);
     if (pluginAgent && !pluginConversation) pluginConversation = conversation;
     if (pluginAgent) {
       if (session.metadata.pluginAgent !== pluginAgent) session.metadata.pluginAgent = pluginAgent;
-      session.metadata.effectiveContextLimit = reqConfig.modelContextLimit;
       recordPluginSession(pluginConversation ?? conversation, session.id);
     }
     if (protocol === "responses" || protocol === "openai" || protocol === "anthropic") {
@@ -57060,6 +57090,22 @@ ${bodyBuffer.toString("utf8")}`);
       reqConfig = { ...reqConfig, modelContextLimit: learnedLimit };
       nativeFromFallback = false;
       log2("info", `[${session.id}] self-healed context window: ${resolved} \u2192 ${learnedLimit} (learned from an upstream overflow)`);
+    } else if (nativeFromFallback && reqModel) {
+      const prevInput = session.stats.lastInputTokens ?? 0;
+      const prevWindow = session.metadata.lastTurnWindow;
+      const resolved = reqConfig.modelContextLimit;
+      if (prevWindow !== void 0 && prevInput > prevWindow && prevInput > resolved && prevInput >= 1e3) {
+        const map = session.metadata.learnedContextLimits ?? {};
+        const prev = map[reqModel];
+        if (prev === void 0 || prevInput > prev) {
+          map[reqModel] = prevInput;
+          session.metadata.learnedContextLimits = map;
+          markDirty(session);
+        }
+        reqConfig = { ...reqConfig, modelContextLimit: prevInput };
+        nativeFromFallback = false;
+        log2("info", `[${session.id}] self-healed context window upward: ${resolved} \u2192 ${prevInput} (a prior turn used ${prevInput} input tokens, exceeding the fallback window)`);
+      }
     }
     const nativeWindow = reqConfig.modelContextLimit;
     if (shouldReserveOutputHeadroom(protocol)) {
@@ -57073,25 +57119,12 @@ ${bodyBuffer.toString("utf8")}`);
       }
       if (reserved !== reqConfig.modelContextLimit) reqConfig = { ...reqConfig, modelContextLimit: reserved };
     }
+    session.metadata.effectiveContextLimit = reqConfig.modelContextLimit;
+    session.metadata.lastTurnWindow = reqConfig.modelContextLimit;
     acquireInFlight(session);
     try {
       await withSessionLock(session, async () => {
         const runPrepare = () => countTokens ? prepareCountTokens(parsed, core, reqConfig, log2, session) : protocol === "anthropic" ? prepareAnthropic(parsed, req, opts, core, reqConfig, reqPrompts, log2, session, pluginMode) : protocol === "openai" ? prepareOpenai(parsed, req, opts, core, reqConfig, reqPrompts, log2, session, pluginMode, nativeWindow) : responsesCompact ? prepareResponsesCompact(bodyBuffer, parsed, session, req, core, reqConfig, log2) : prepareResponses(parsed, req, opts, core, reqConfig, reqPrompts, log2, session, responsesIdentity, pluginMode, upstreamOrigin, nativeWindow);
-        const isCodexCompactTrigger = protocol === "responses" && !responsesCompact && isCodexClient(req.headers) && hasCompactionTrigger(parsed.input);
-        if (isCodexCompactTrigger) {
-          const mode = codexCompactMode();
-          const gatePre = codexCompactGatePre(session, reqConfig.modelContextLimit);
-          if (mode === "intercept" && gatePre) prepared = runPrepare();
-          if (prepared?.codexForge) {
-            await forward(req, res, opts, prepared.body, prepared, core, reqConfig, log2, route, instanceId, affinity);
-            rememberPluginMessages(sessionId, prepared.processedMessages, prepared.originalMessages, prepared.nudge);
-            return;
-          }
-          const why = mode !== "intercept" ? "BILI_CODEX_COMPACT=pass" : !gatePre ? "gate preconditions not met" : "transform/forge failed";
-          log2("info", `[${session.id}] codex compaction_trigger request not intercepted (${why}) \u2014 forwarding verbatim (no preflight, no rebuild, no window clamp)`);
-          await forward(req, res, opts, bodyBuffer, null, core, reqConfig, log2, route, instanceId, affinity);
-          return;
-        }
         prepared = runPrepare();
         if (!countTokens && !responsesCompact) {
           const outcome = await preflightCompressIfNeeded(
@@ -57137,7 +57170,7 @@ ${bodyBuffer.toString("utf8")}`);
     }
   }
   if (!prepared) {
-    if (protocol === null && !opts.passthrough) {
+    if (protocol === null && !opts.passthrough && !isModelDiscoveryPath(urlPath)) {
       logUnrecognizedPath(log2, req.url ?? "");
     }
     await forward(req, res, opts, bodyBuffer, null, core, reqConfig, log2, route, instanceId, void 0);
@@ -57537,7 +57570,7 @@ function prepareResponsesCompact(body, parsed, session, req, core, config, log2)
     compressInjected: false,
     resetAfterSuccess: true
   };
-  if (codexCompactMode() !== "intercept" || !isCodexClient(req.headers) || !Array.isArray(parsed.input) || !codexCompactGatePre(session, config.modelContextLimit)) {
+  if (codexCompactMode() !== "intercept" || !isCodexClient(req.headers) || !Array.isArray(parsed.input)) {
     return base;
   }
   const prevState = session.state;