feat(dashboard): per-key model restrictions, pin header routing, combo side-panel picker

- Endpoint: per-API-key model allowlist (schema v3) enforced on chat (403) and /v1/models; Full-access toggle + multi-select picker in Keys UI. - Providers: honor x-connection-id in /v1/chat/completions — pinned requests no longer rotate to another account on failure. - Providers: strategy saves merge into stored enabled:false override; Test All groups match grid sections; 1-by-1 skips disabled connections. - Dashboard: provider-card toggle syncs from server on failure; grid toggles always visible; connection rows get clear-✕ for stale error banners. - Combo editor: on desktop (xl+) the Add-Model picker opens as a floating side panel beside the untouched combo popup instead of stacking on top; mobile keeps the full-screen overlay. - Long API-key overflow fixed in key rows + provider model sections.
2026-08-27 09:26:17 +07:00
parent 1d56e2dbc5
commit f0adfb205a
42 changed files with 1028 additions and 339 deletions
--- a/open-sse/handlers/chatCore.js
+++ b/open-sse/handlers/chatCore.js
@@ -11,7 +11,7 @@ import { PROVIDERS } from "../config/providers.js";
 import { createErrorResult, parseUpstreamError, formatProviderError } from "../utils/error.js";
 import { HTTP_STATUS, TOKEN_SAVER_HEADER } from "../config/runtimeConfig.js";
 import { handleBypassRequest } from "../utils/bypassHandler.js";
-import { trackPendingRequest, appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
+import { trackPendingRequest, saveRequestDetail } from "@/lib/usageDb.js";
 import { getExecutor } from "../executors/index.js";
 import { supportsGrokCliReasoningEffort } from "../config/grokCli.js";
 import { buildRequestDetail, extractRequestConfig } from "./chatCore/requestDetail.js";
@@ -29,6 +29,7 @@ import { getCapabilitiesForModel } from "../providers/capabilities.js";
 import { stripUnsupportedModalities } from "../translator/concerns/modality.js";
 import { prefetchRemoteImages } from "../translator/concerns/prefetch.js";
 import { resolveSessionId } from "../utils/sessionManager.js";
+import { maybeRejectEarlyStreamError } from "../utils/streamErrorPeek.js";

 /**
 * Core chat handler - shared between SSE and Worker
@@ -57,7 +58,7 @@ export function stripContinuityFields(body) {
  return body;
 }

-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, capsOverride }) {
+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, capsOverride, streamErrorPatterns }) {
  const { provider, model } = modelInfo;
  const requestStartTime = Date.now();
  // Stable per-session color so all lines of one CLI conversation share a tag
@@ -100,7 +101,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
  if (providerThinking?.mode && providerThinking.mode !== "auto") {
    const mode = providerThinking.mode;
    if (mode === "on" && !body.thinking) {
-      console.log("Injecting provider-level thinking config override: on");
+      log?.debug?.("THINKING", `provider-level override: on`);
      body = { ...body, thinking: { type: "enabled", budget_tokens: 10000 } };
    } else if (mode === "off" && !body.thinking) {
      body = { ...body, thinking: { type: "disabled" } };
@@ -243,7 +244,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
  // RTK: compress tool_result content
  const rtkStats = compressMessages(translatedBody, tokenSaverEnabled && rtkEnabled);
  const rtkLine = formatRtkLog(rtkStats);
-  if (rtkLine) console.log(rtkLine);
+  if (rtkLine) log?.info?.("RTK", rtkLine.replace(/^\[RTK\] /, ""));

  // Headroom: optional external proxy compression; fail open if proxy is absent.
  const headroomDiagnostics = {};
@@ -293,7 +294,6 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred

  const executor = getExecutor(provider);
  trackPendingRequest(model, provider, connectionId, true);
-  appendRequestLog({ model, provider, connectionId, status: "PENDING" }).catch(() => { });

  const msgCount = translatedBody.messages?.length || translatedBody.input?.length || translatedBody.contents?.length || translatedBody.request?.contents?.length || 0;
  log?.debug?.("REQUEST", `${provider.toUpperCase()} | ${model} | ${msgCount} msgs`);
@@ -355,7 +355,6 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
    reqLogger.logTargetRequest(providerUrl, providerHeaders, finalBody);
  } catch (error) {
    trackPendingRequest(model, provider, connectionId, false, true);
-    appendRequestLog({ model, provider, connectionId, status: `FAILED ${error.name === "AbortError" ? 499 : HTTP_STATUS.BAD_GATEWAY}` }).catch(() => { });
    saveRequestDetail(buildRequestDetail({
      provider, model, connectionId,
      latency: { ttft: 0, total: Date.now() - requestStartTime },
@@ -415,11 +414,11 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
    }
  }

+
  // Provider returned error
  if (!providerResponse.ok) {
    trackPendingRequest(model, provider, connectionId, false, true);
    const { statusCode, message, resetsAtMs } = await parseUpstreamError(providerResponse, executor);
-    appendRequestLog({ model, provider, connectionId, status: `FAILED ${statusCode}` }).catch(() => { });
    saveRequestDetail(buildRequestDetail({
      provider, model, connectionId,
      latency: { ttft: 0, total: Date.now() - requestStartTime },
@@ -440,8 +439,31 @@ 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, pxpipe: pxpipeSummary, reqTag, log };
-  const appendLog = (extra) => appendRequestLog({ model, provider, connectionId, ...extra }).catch(() => { });
+  const appendLog = () => {}; // request log derived from usageHistory; kept as no-op seam for handlers
+  const sharedCtx = { provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, pxpipe: pxpipeSummary, reqTag, log, streamErrorPatterns };
+
+  // Early-peek streaming responses for configured in-stream error patterns.
+  // Some upstreams fail INSIDE a 200 SSE stream; without this the failure is
+  // piped to the client verbatim and account/combo fallback never triggers
+  // (see AGENTS.md "HTTP 200 in-stream errors"). Fail-open: no patterns → pass-through.
+  if (providerResponse.ok && stream) {
+    const peeked = await maybeRejectEarlyStreamError(
+      providerResponse,
+      streamErrorPatterns?.[provider],
+      { signal: streamController.signal },
+    );
+    if (!peeked.ok) {
+      const { message } = await parseUpstreamError(peeked).catch(() => ({ message: "Stream error pattern matched" }));
+      trackPendingRequest(model, provider, connectionId, false, true);
+      appendLog({ status: `FAILED ${HTTP_STATUS.BAD_GATEWAY}` });
+      if (log?.errorLine) {
+        log.errorLine(reqTag, "✗", `ERROR 502 · ${provider}/${model} · ${Date.now() - requestStartTime}ms (in-stream)\n    ${message}`);
+      }
+      return createErrorResult(HTTP_STATUS.BAD_GATEWAY, message);
+    }
+    providerResponse = peeked;
+  }
+
  const trackDone = () => trackPendingRequest(model, provider, connectionId, false);

  // Provider forced streaming but client wants JSON
--- a/open-sse/handlers/chatCore/nonStreamingHandler.js
+++ b/open-sse/handlers/chatCore/nonStreamingHandler.js
@@ -7,7 +7,8 @@ import { createErrorResult } from "../../utils/error.js";
 import { HTTP_STATUS } from "../../config/runtimeConfig.js";
 import { parseSSEToOpenAIResponse } from "./sseToJsonHandler.js";
 import { buildRequestDetail, extractRequestConfig, extractUsageFromResponse, saveUsageStats, formatDoneLine } from "./requestDetail.js";
-import { appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
+import { saveRequestDetail } from "@/lib/usageDb.js";
+import { matchStreamErrorPatterns } from "../../utils/streamErrorPatterns.js";
 import { decloakToolNames } from "../../utils/claudeCloaking.js";
 import { ROLE, RESPONSES_ITEM } from "../../translator/schema/index.js";

@@ -281,7 +282,7 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
 /**
 * Handle non-streaming response from provider.
 */
-export async function handleNonStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, customToolNames, trackDone, appendLog, pxpipe, reqTag, log }) {
+export async function handleNonStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, customToolNames, trackDone, appendLog, pxpipe, reqTag, log, streamErrorPatterns }) {
  trackDone();
  const contentType = providerResponse.headers.get("content-type") || "";
  let responseBody;
@@ -316,6 +317,21 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
  // Decloak tool_use names once on raw Claude body, before any translation (INPUT side)
  responseBody = decloakToolNames(responseBody, toolNameMap);

+  // Config-driven in-stream error detection: the HTTP call succeeded but the
+  // assembled content signals an upstream failure — treat it as an error so
+  // account/combo fallback and FAILED logging kick in (AGENTS.md hook #3).
+  const matchedPattern = matchStreamErrorPatterns(
+    streamErrorPatterns?.[provider],
+    responseBody?.choices?.[0]?.message?.content || responseBody?.content || "",
+  );
+  if (matchedPattern) {
+    appendLog({ status: `FAILED ${HTTP_STATUS.BAD_GATEWAY}` });
+    if (log?.errorLine) {
+      log.errorLine(reqTag, "✗", `ERROR 502 · ${provider}/${model} · ${Date.now() - requestStartTime}ms (in-stream)\n    Stream error pattern matched: ${matchedPattern}`);
+    }
+    return createErrorResult(HTTP_STATUS.BAD_GATEWAY, `Stream error pattern matched: ${matchedPattern}`);
+  }
+
  const usage = extractUsageFromResponse(responseBody);
  appendLog({ tokens: usage, status: "200 OK" });
  saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint, silent: true });
--- a/open-sse/handlers/chatCore/requestDetail.js
+++ b/open-sse/handlers/chatCore/requestDetail.js
@@ -1,4 +1,4 @@
-import { saveRequestUsage, appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
+import { saveRequestUsage, saveRequestDetail } from "@/lib/usageDb.js";
 import { COLORS } from "../../utils/stream.js";
 import { canonicalizeUsage } from "../../utils/usageTracking.js";

--- a/open-sse/handlers/chatCore/sseToJsonHandler.js
+++ b/open-sse/handlers/chatCore/sseToJsonHandler.js
@@ -5,12 +5,12 @@ import { HTTP_STATUS } from "../../config/runtimeConfig.js";
 import { FORMATS } from "../../translator/formats.js";
 import { PROVIDERS } from "../../config/providers.js";
 import { buildRequestDetail, extractRequestConfig, saveUsageStats, formatDoneLine } from "./requestDetail.js";
+import { saveRequestDetail } from "@/lib/usageDb.js";
 import { ROLE, RESPONSES_ITEM } from "../../translator/schema/index.js";

 // Responses-API providers (e.g. codex) may emit SSE without content-type + use Responses output shape
 const isResponsesProvider = (p) =>
 	PROVIDERS[p]?.format === FORMATS.OPENAI_RESPONSES;
-import { saveRequestDetail, appendRequestLog } from "@/lib/usageDb.js";

 function textFromResponsesMessageItem(item) {
 	if (!item?.content || !Array.isArray(item.content)) return "";