Enhance configuration and model capabilities

open-sse/translator/concerns/thinkingUnified.js

@@ -40,6 +40,15 @@ export function parseSuffix(model) {
 export function extractThinking(body) {
   if (!body || typeof body !== "object") return null;
 
+  // Claude output_config.effort (explicit) — priority over adaptive thinking
+  const oc = body.output_config?.effort;
+  if (typeof oc === "string" && oc) {
+    const e = oc.toLowerCase();
+    if (e === "none" || e === "off") return { mode: "none" };
+    if (e === "auto") return { mode: "auto" };
+    return { mode: "level", level: e };
+  }
+
   // Claude shape
   const t = body.thinking;
   if (t && typeof t === "object") {
@@ -154,7 +163,7 @@ function applyFormat(fmt, body, cfg, caps) {
     case "openai": {
       if (none && canDisable) { body.reasoning_effort = "none"; break; }
       const level = toLevel(eff);
-      if (level) body.reasoning_effort = level;
+      if (level) body.reasoning_effort = level === "xhigh" || level === "max" ? "high" : level;
       break;
     }
     case "claude-adaptive": {

open-sse/translator/formats/claude.js

@@ -5,6 +5,8 @@ import { adjustMaxTokens } from "./maxTokens.js";
 import { applyCloaking } from "../../utils/claudeCloaking.js";
 import { resolveSessionId } from "../../utils/sessionManager.js";
 import { PROVIDERS } from "../../providers/index.js";
+import { getCapabilitiesForModel } from "../../providers/capabilities.js";
+import { DEFAULT_MAX_TOKENS } from "../../config/runtimeConfig.js";
 
 // Check if message has valid non-empty content
 export function hasValidContent(msg) {
@@ -130,12 +132,18 @@ export function normalizeClaudePassthrough(body, model = "") {
 // - Add thinking block for Anthropic endpoint (provider === "claude")
 // - Fix tool_use/tool_result ordering
 // - Apply cloaking (billing header + fake user ID) for OAuth tokens
-export function prepareClaudeRequest(body, provider = null, apiKey = null, connectionId = null) {
+export function prepareClaudeRequest(body, provider = null, apiKey = null, connectionId = null, rawHeaders = null, sessionId = null) {
   // quirk: MiniMax's Claude-compatible endpoint rejects Anthropic's output_config (400 invalid params)
   if (PROVIDERS[provider]?.quirks?.dropOutputConfig) {
     delete body.output_config;
   }
 
+  // Clamp max_tokens to the model output ceiling (never above DEFAULT_MAX_TOKENS)
+  if (body.max_tokens) {
+    const ceiling = Math.min(getCapabilitiesForModel(provider, body.model).maxOutput, DEFAULT_MAX_TOKENS);
+    if (body.max_tokens > ceiling) body.max_tokens = ceiling;
+  }
+
   // 1. System: remove all cache_control, add only to last block with ttl 1h
   if (body.system && Array.isArray(body.system)) {
     body.system = body.system.map((block, i) => {
@@ -252,8 +260,8 @@ export function prepareClaudeRequest(body, provider = null, apiKey = null, conne
   // Apply cloaking for OAuth tokens (billing header + fake user ID)
   // session_id in user_id must match X-Claude-Code-Session-Id for fingerprint consistency
   if ((provider === "claude" || provider?.startsWith("anthropic-compatible")) && apiKey) {
-    const sessionId = resolveSessionId({ body, connectionId, scope: "claude" });
-    body = applyCloaking(body, apiKey, sessionId);
+    const sid = sessionId || resolveSessionId({ headers: rawHeaders, body, connectionId, scope: "claude" });
+    body = applyCloaking(body, apiKey, sid);
   }
 
   return body;

open-sse/translator/formats/maxTokens.js

@@ -8,7 +8,7 @@ import { DEFAULT_MAX_TOKENS, DEFAULT_MIN_TOKENS } from "../../config/runtimeConf
 export function adjustMaxTokens(body) {
   let maxTokens = body.max_tokens || DEFAULT_MAX_TOKENS;
 
-  // Auto-increase for tool calling to prevent truncated arguments
+  // Auto-increase for tool calling to prevent truncated arguments (min never above max)
   if (body.tools && Array.isArray(body.tools) && body.tools.length > 0) {
     if (maxTokens < DEFAULT_MIN_TOKENS) {
       maxTokens = DEFAULT_MIN_TOKENS;
@@ -22,6 +22,9 @@ export function adjustMaxTokens(body) {
     maxTokens = body.thinking.budget_tokens + 1024;
   }
 
+  // Never exceed the global ceiling
+  if (maxTokens > DEFAULT_MAX_TOKENS) maxTokens = DEFAULT_MAX_TOKENS;
+
   return maxTokens;
 }
 

open-sse/translator/index.js

@@ -5,6 +5,7 @@ import { cloakClaudeTools } from "../utils/claudeCloaking.js";
 import { filterToOpenAIFormat } from "./formats/openai.js";
 import { normalizeThinkingConfig } from "../services/provider.js";
 import { applyThinking, captureThinking } from "./concerns/thinkingUnified.js";
+import { captureSessionId } from "../utils/sessionManager.js";
 import { AntigravityExecutor } from "../executors/antigravity.js";
 import { PROVIDERS } from "../providers/index.js";
 
@@ -68,6 +69,11 @@ export function translateRequest(sourceFormat, targetFormat, model, body, stream
   // format conversion strips/renames the fields. Applied after translation.
   const thinkingIntent = captureThinking(result);
 
+  // Capture session id from the original body (envelope still intact, e.g. antigravity request.sessionId)
+  const clientSessionId = captureSessionId(result, credentials, connectionId, targetFormat);
+  // Expose to downstream translators (gemini-cli/antigravity envelopes) that run after envelope is stripped
+  if (credentials) credentials._clientSessionId = clientSessionId;
+
   // If same format, skip translation steps
   if (sourceFormat !== targetFormat) {
     // Step 1: source -> openai (if source is not openai)
@@ -101,7 +107,7 @@ export function translateRequest(sourceFormat, targetFormat, model, body, stream
   // Final step: prepare request for Claude format endpoints
   if (targetFormat === FORMATS.CLAUDE) {
     const apiKey = credentials?.accessToken || credentials?.apiKey || null;
-    result = prepareClaudeRequest(result, provider, apiKey, connectionId);
+    result = prepareClaudeRequest(result, provider, apiKey, connectionId, credentials?.rawHeaders, clientSessionId);
   }
 
   // Claude cloaking: rename client tools with _cc suffix (anti-ban)

open-sse/translator/request/openai-to-gemini.js

@@ -17,7 +17,7 @@ import {
   generateProjectId,
   cleanJSONSchemaForAntigravity
 } from "../formats/gemini.js";
-import { deriveSessionId } from "../../utils/sessionManager.js";
+import { deriveSessionId, toNumericSessionId } from "../../utils/sessionManager.js";
 import { ROLE, GEMINI_ROLE, OPENAI_BLOCK, CLAUDE_BLOCK } from "../schema/index.js";
 
 // Sanitize function names for Gemini API.
@@ -259,7 +259,7 @@ function wrapInCloudCodeEnvelope(model, geminiCLI, credentials = null, isAntigra
     userAgent: isAntigravity ? "antigravity" : "gemini-cli",
     requestId: isAntigravity ? `agent-${generateUUID()}` : generateRequestId(),
     request: {
-      sessionId: isAntigravity ? deriveSessionId(credentials?.email || credentials?.connectionId) : generateSessionId(),
+      sessionId: toNumericSessionId(credentials?._clientSessionId) || (isAntigravity ? deriveSessionId(credentials?.email || credentials?.connectionId) : generateSessionId()),
       contents: geminiCLI.contents,
       systemInstruction: geminiCLI.systemInstruction,
       generationConfig: geminiCLI.generationConfig,
@@ -309,7 +309,7 @@ function wrapInCloudCodeEnvelopeForClaude(model, claudeRequest, credentials = nu
     requestId: `agent-${generateUUID()}`,
     requestType: "agent",
     request: {
-      sessionId: deriveSessionId(credentials?.email || credentials?.connectionId),
+      sessionId: toNumericSessionId(credentials?._clientSessionId) || deriveSessionId(credentials?.email || credentials?.connectionId),
       contents: [],
       generationConfig: {
         temperature: claudeRequest.temperature || 1,