Merge remote-tracking branch 'origin/release/v3.8.50' into feat/9571-plugin-streaming-usage-timing

The changelog fragment format requires the first non-empty line to be
a markdown bullet ("- "). YAML frontmatter was the first non-empty
line, causing the integrity check to fail.

changelog.d/features/9571-plugin-streaming-usage-timing.md

@@ -0,0 +1,11 @@
+- **feat(plugins):** add onStreamComplete built-in event exposing streaming usage and timing (#9571)
+
+  Adds a new `onStreamComplete` plugin event that fires after an SSE stream is fully
+  consumed, carrying usage token counts and timing metrics (latency, TTFT). Built-in
+  events now include `onStreamComplete` as a fire-and-forget lifecycle hook.
+
+  Payload: `status`, `usage` (prompt_tokens, completion_tokens, reasoning_tokens,
+  cache_read_input_tokens, cache_creation_input_tokens), `timing` (latencyMs, ttft),
+  `model`, `provider`, `errorCode`.
+
+  Non-breaking — existing `onResponse` hooks with `{ streamed: true }` remain unchanged.

changelog.d/fixes/9630-combo-false-503.md

@@ -1 +0,0 @@
-- fix(combo): distinguish pre-dispatch skips from genuine failures to prevent false 503 ALL_ACCOUNTS_INACTIVE (#9630)

open-sse/handlers/chatCore.ts

@@ -245,7 +245,10 @@ import { recordCompressionCacheStats } from "./chatCore/compressionCacheStats.ts
 import { writeCavemanOutputAnalytics } from "./chatCore/cavemanOutputAnalytics.ts";
 import { scheduleQuotaShareConsumption } from "./chatCore/quotaShareConsumption.ts";
 import { emitRequestGamificationEvent } from "./chatCore/gamificationEvent.ts";
-import { runPluginOnResponseHook } from "./chatCore/pluginOnResponse.ts";
+import {
+  runPluginOnResponseHook,
+  runPluginOnStreamCompleteHook,
+} from "./chatCore/pluginOnResponse.ts";
 import { scheduleStreamingQuotaShareConsumption } from "./chatCore/streamingQuotaShare.ts";
 import { recordStreamingUsageStats } from "./chatCore/streamingUsageStats.ts";
 import { recordStreamingCost } from "./chatCore/streamingCost.ts";
@@ -4895,6 +4898,17 @@ export async function handleChatCore({
       streamUsage,
       log,
     });
+
+    // Plugin onStreamComplete hook — fire-and-forget, fail-open (#9571)
+    runPluginOnStreamCompleteHook({
+      status: normalizedStreamStatus,
+      usage: streamUsage as Record<string, unknown> | undefined,
+      ttft,
+      model,
+      provider,
+      errorCode: streamErrorCode,
+      startTime,
+    });
   };
 
   const streamFailureFinalizers = streamFailure.createStreamFailureFinalizers({

open-sse/handlers/chatCore/pluginOnResponse.ts

@@ -43,3 +43,57 @@ export async function runPluginOnResponseHook(args: {
     /* plugin onResponse optional */
   }
 }
+
+/**
+ * Payload passed to plugin onStreamComplete hooks after a streaming response is consumed.
+ * Carries usage token counts, timing metrics (latency, TTFT), model, provider, and error code.
+ */
+export type PluginOnStreamCompletePayload = {
+  status: number;
+  usage?: {
+    prompt_tokens?: number;
+    completion_tokens?: number;
+    reasoning_tokens?: number;
+    cache_read_input_tokens?: number;
+    cache_creation_input_tokens?: number;
+  };
+  timing?: {
+    latencyMs: number;
+    ttft?: number;
+  };
+  model?: string;
+  provider?: string;
+  errorCode?: string;
+};
+
+/**
+ * Run plugin onStreamComplete hooks — fire-and-forget and fail-open.
+ * Called inside the onStreamComplete callback (chatCore.ts) where usage and timing data
+ * converge after an SSE stream is fully consumed.
+ */
+export async function runPluginOnStreamCompleteHook(args: {
+  status: number;
+  usage?: Record<string, unknown>;
+  ttft?: number;
+  model: string | null | undefined;
+  provider: string | null | undefined;
+  errorCode?: string | null | undefined;
+  startTime: number;
+}): Promise<void> {
+  try {
+    const { runOnStreamComplete } = await import("@/lib/plugins/hooks");
+    runOnStreamComplete({
+      status: args.status,
+      usage: args.usage as PluginOnStreamCompletePayload["usage"],
+      timing: {
+        latencyMs: Date.now() - args.startTime,
+        ttft: args.ttft,
+      },
+      model: args.model ?? undefined,
+      provider: args.provider ?? undefined,
+      errorCode: args.errorCode ?? undefined,
+    }).catch(() => {});
+  } catch (_) {
+    /* plugin onStreamComplete optional */
+  }
+}

open-sse/services/antigravityProjectPersistence.ts

@@ -1,13 +0,0 @@
-/**
- * Re-export from `antigravityProjectPersist.ts` plus a connection-preference helper.
- */
-import { persistDiscoveredAntigravityProjectId } from "./antigravityProjectPersist.ts";
-export { persistDiscoveredAntigravityProjectId };
-
-export function preferAntigravityConnectionsWithStoredProject(
-  connections: Array<Record<string, unknown>>
-): Array<Record<string, unknown>> {
-  return connections.filter(
-    (conn) => conn != null && typeof conn.projectId === "string" && conn.projectId.trim().length > 0
-  );
-}

open-sse/services/combo.ts

@@ -2036,35 +2036,23 @@ export async function handleComboChat({
       if (setTry < maxSetRetries) continue;
 
       // All set retries exhausted — return the final error
-	      if (!lastStatus) {
-	        if (recordedAttempts === 0) {
-	          notifyWebhookEvent("request.failed", {
-	            combo: combo.name,
-	            reason: "ALL_TARGETS_SKIPPED",
-	            latencyMs,
-	            fallbackCount,
-	          });
-	          return errorResponseWithComboDiagnostics(
-	            503,
-	            "Service temporarily unavailable: all targets were skipped by pre-dispatch filters",
-	            buildComboDiag("all_targets_skipped"),
-	            { code: "ALL_TARGETS_SKIPPED", type: "service_unavailable" }
-	          );
-	        }
-	        notifyWebhookEvent("request.failed", {
-	          combo: combo.name,
-	          reason: "ALL_ACCOUNTS_INACTIVE",
-	          latencyMs,
-	          fallbackCount,
-	        });
-	        recordComboFailure(effectiveSessionId, combo.name);
-	        return errorResponseWithComboDiagnostics(
-	          503,
-	          "Service temporarily unavailable: all upstream accounts are inactive",
-	          buildComboDiag("all_accounts_inactive"),
-	          { code: "ALL_ACCOUNTS_INACTIVE", type: "service_unavailable" }
-	        );
-	      }
+      if (!lastStatus) {
+        notifyWebhookEvent("request.failed", {
+          combo: combo.name,
+          reason: "ALL_ACCOUNTS_INACTIVE",
+          latencyMs,
+          fallbackCount,
+        });
+        // Silent-stop fix: bump the failure counter so the session pin clears on the 3rd
+        // consecutive all-inactive cascade; buildRecoveryHint emits `switch-combo` with a
+        // next-step that points the user at /dashboard/providers.
+        recordComboFailure(effectiveSessionId, combo.name);
+        return errorResponseWithComboDiagnostics(
+          503,
+          "Service temporarily unavailable: all upstream accounts are inactive",
+          buildComboDiag("all_accounts_inactive"),
+          { code: "ALL_ACCOUNTS_INACTIVE", type: "service_unavailable" }
+        );
       }
 
       const status = lastStatus;
@@ -3016,30 +3004,18 @@ async function handleRoundRobinCombo({
     });
   }
 
-	  if (!lastStatus) {
-	    if (recordedAttempts === 0) {
-	      return new Response(
-	        JSON.stringify({
-	          error: {
-	            message: "Service temporarily unavailable: all targets were skipped by pre-dispatch filters",
-	            type: "service_unavailable",
-	            code: "ALL_TARGETS_SKIPPED",
-	          },
-	        }),
-	        { status: 503, headers: { "Content-Type": "application/json" } }
-	      );
-	    }
-	    return new Response(
-	      JSON.stringify({
-	        error: {
-	          message: "Service temporarily unavailable: all upstream accounts are inactive",
-	          type: "service_unavailable",
-	          code: "ALL_ACCOUNTS_INACTIVE",
-	        },
-	      }),
-	      { status: 503, headers: { "Content-Type": "application/json" } }
-	    );
-	  }
+  if (!lastStatus) {
+    return new Response(
+      JSON.stringify({
+        error: {
+          message: "Service temporarily unavailable: all upstream accounts are inactive",
+          type: "service_unavailable",
+          code: "ALL_ACCOUNTS_INACTIVE",
+        },
+      }),
+      { status: 503, headers: { "Content-Type": "application/json" } }
+    );
+  }
 
   const status = lastStatus;
   const msg = lastError || "All round-robin combo models unavailable";

src/lib/db/migrationRunner.ts

@@ -465,13 +465,13 @@ function isSchemaAlreadyApplied(
       // exists the rebuild ran — skip re-executing the rename/copy/drop, which
       // would fail on the missing proxy_assignments_pre117 table.
       return hasColumn(db, "proxy_assignments", "position");
-    // Retroactive schema guards for migrations renumbered after release-branch collisions.
+    // Retroactive guard for the 135/136 renumber (#8523 landed onto slots already taken
+    // by #8908/#9515): a DB that ran these under the old numbers already has the column,
+    // and a bare ALTER TABLE ADD COLUMN would throw on the re-run under the new number.
     case "137":
       return hasColumn(db, "version_manager", "auto_restart_adopted");
     case "138":
       return hasColumn(db, "upstream_proxy_config", "fallback_backend");
-    case "139":
-      return hasTable(db, "ccr_blocks");
     default:
       return false;
   }

src/lib/db/migrationRunner/constants.ts

@@ -69,12 +69,6 @@ export const RENAMED_MIGRATION_COMPATIBILITY = [
     toVersion: "059",
     toName: "manifest_routing",
   },
-  {
-    fromVersion: "134",
-    fromName: "ccr_blocks",
-    toVersion: "139",
-    toName: "ccr_blocks",
-  },
 ] as const;
 
 export const LEGACY_VERSION_SLOT_MIGRATIONS = [

src/lib/plugins/hooks.ts

@@ -40,6 +40,7 @@ export const BUILTIN_EVENTS = [
   "onActivate",
   "onDeactivate",
   "onUninstall",
+  "onStreamComplete",
 ] as const;
 
 export type BuiltinEvent = (typeof BUILTIN_EVENTS)[number];
@@ -251,6 +252,35 @@ export interface Plugin {
   onActivate?: (payload: unknown) => Promise<void> | void;
   onDeactivate?: (payload: unknown) => Promise<void> | void;
   onUninstall?: (payload: unknown) => Promise<void> | void;
+  onStreamComplete?: (payload: PluginOnStreamCompletePayload) => Promise<void> | void;
+}
+
+// ── onStreamComplete event types ──
+
+export type PluginOnStreamCompletePayload = {
+  status: number;
+  usage?: {
+    prompt_tokens?: number;
+    completion_tokens?: number;
+    reasoning_tokens?: number;
+    cache_read_input_tokens?: number;
+    cache_creation_input_tokens?: number;
+  };
+  timing?: {
+    latencyMs: number;
+    ttft?: number;
+  };
+  model?: string;
+  provider?: string;
+  errorCode?: string;
+};
+
+/**
+ * Run onStreamComplete hooks — fire-and-forget notification with usage/timing data.
+ * Called when an SSE stream is fully consumed and usage/timing data is available.
+ */
+export async function runOnStreamComplete(payload: PluginOnStreamCompletePayload): Promise<void> {
+  await emitHook("onStreamComplete", payload);
 }
 
 /**

tests/unit/chatcore-plugin-onresponse.test.ts

@@ -7,9 +7,8 @@ import { test, after } from "node:test";
 import assert from "node:assert/strict";
 
 const { registerHook, unregisterHook } = await import("../../src/lib/plugins/hooks.ts");
-const { runPluginOnResponseHook } = await import(
-  "../../open-sse/handlers/chatCore/pluginOnResponse.ts"
-);
+const { runPluginOnResponseHook, runPluginOnStreamCompleteHook } =
+  await import("../../open-sse/handlers/chatCore/pluginOnResponse.ts");
 
 async function waitFor(pred: () => boolean, timeoutMs = 2000): Promise<void> {
   const deadline = Date.now() + timeoutMs;
@@ -20,6 +19,7 @@ async function waitFor(pred: () => boolean, timeoutMs = 2000): Promise<void> {
 
 after(() => {
   unregisterHook("onResponse", "test-onresponse-plugin");
+  unregisterHook("onStreamComplete", "test-onstreamcomplete-plugin");
 });
 
 test("no registered hooks → resolves without throwing (no-op)", async () => {
@@ -101,3 +101,140 @@ test("a throwing hook never rejects the caller (fail-open)", async () => {
   );
   await new Promise((r) => setTimeout(r, 30));
 });
+
+// ── onStreamComplete hook tests (#9571) ──
+
+test("onStreamComplete: no registered hooks resolves without throwing (no-op)", async () => {
+  const start = Date.now();
+  await assert.doesNotReject(
+    runPluginOnStreamCompleteHook({
+      status: 200,
+      usage: { prompt_tokens: 10, completion_tokens: 20 },
+      ttft: 150,
+      model: "gpt-4",
+      provider: "openai",
+      errorCode: undefined,
+      startTime: start - 500,
+    })
+  );
+});
+
+test("onStreamComplete: registered hook receives usage + timing payload", async () => {
+  let captured: Record<string, unknown> | undefined;
+  registerHook(
+    "onStreamComplete",
+    "test-onstreamcomplete-plugin",
+    async (payload: Record<string, unknown>) => {
+      captured = payload;
+    }
+  );
+
+  const startTime = Date.now() - 500;
+  await runPluginOnStreamCompleteHook({
+    status: 200,
+    usage: { prompt_tokens: 42, completion_tokens: 100, reasoning_tokens: 5 },
+    ttft: 200,
+    model: "claude-3-opus",
+    provider: "anthropic",
+    errorCode: undefined,
+    startTime,
+  });
+
+  await waitFor(() => captured !== undefined);
+  assert.ok(captured, "expected onStreamComplete hook to be invoked");
+
+  // payload shape: status, usage, timing, model, provider
+  assert.equal(captured!.status, 200);
+  assert.ok(captured!.usage, "usage should be present");
+  assert.equal((captured!.usage as Record<string, number>).prompt_tokens, 42);
+  assert.equal((captured!.usage as Record<string, number>).completion_tokens, 100);
+  assert.equal((captured!.usage as Record<string, number>).reasoning_tokens, 5);
+
+  assert.ok(captured!.timing, "timing should be present");
+  const timing = captured!.timing as Record<string, number>;
+  assert.equal(timing.ttft, 200);
+  assert.ok(timing.latencyMs > 450, "latencyMs should be near 500");
+
+  assert.equal(captured!.model, "claude-3-opus");
+  assert.equal(captured!.provider, "anthropic");
+  assert.equal(captured!.errorCode, undefined);
+});
+
+test("onStreamComplete: payload includes cache token fields when present", async () => {
+  let captured: Record<string, unknown> | undefined;
+  registerHook(
+    "onStreamComplete",
+    "test-onstreamcomplete-plugin",
+    async (payload: Record<string, unknown>) => {
+      captured = payload;
+    }
+  );
+
+  await runPluginOnStreamCompleteHook({
+    status: 200,
+    usage: {
+      prompt_tokens: 50,
+      completion_tokens: 30,
+      cache_read_input_tokens: 20,
+      cache_creation_input_tokens: 10,
+    },
+    ttft: 100,
+    model: "gpt-4",
+    provider: "openai",
+    errorCode: undefined,
+    startTime: Date.now(),
+  });
+
+  await waitFor(() => captured !== undefined);
+  assert.ok(captured);
+  const usage = captured!.usage as Record<string, number>;
+  assert.equal(usage.cache_read_input_tokens, 20);
+  assert.equal(usage.cache_creation_input_tokens, 10);
+});
+
+test("onStreamComplete: throwing hook never rejects the caller (fail-open)", async () => {
+  registerHook("onStreamComplete", "test-onstreamcomplete-plugin", async () => {
+    throw new Error("stream-complete-boom");
+  });
+
+  await assert.doesNotReject(
+    runPluginOnStreamCompleteHook({
+      status: 500,
+      usage: undefined,
+      ttft: undefined,
+      model: "gpt-4",
+      provider: "openai",
+      errorCode: "upstream_error",
+      startTime: Date.now(),
+    })
+  );
+  await new Promise((r) => setTimeout(r, 30));
+});
+
+test("onStreamComplete: errorCode is passed through when provided", async () => {
+  let captured: Record<string, unknown> | undefined;
+  registerHook(
+    "onStreamComplete",
+    "test-onstreamcomplete-plugin",
+    async (payload: Record<string, unknown>) => {
+      captured = payload;
+    }
+  );
+
+  await runPluginOnStreamCompleteHook({
+    status: 502,
+    usage: undefined,
+    ttft: undefined,
+    model: "grok-3",
+    provider: "xai",
+    errorCode: "upstream_timeout",
+    startTime: Date.now(),
+  });
+
+  await waitFor(() => captured !== undefined);
+  assert.ok(captured);
+  assert.equal(captured!.status, 502);
+  assert.equal(captured!.errorCode, "upstream_timeout");
+  assert.equal(captured!.model, "grok-3");
+  assert.equal(captured!.provider, "xai");
+});

tests/unit/db-ccr-migration-renumber-134.test.ts

@@ -1,79 +0,0 @@
-import test from "node:test";
-import assert from "node:assert/strict";
-import fs from "node:fs";
-import os from "node:os";
-import path from "node:path";
-import Database from "better-sqlite3";
-
-const migrationsDir = fs.mkdtempSync(path.join(os.tmpdir(), "omniroute-ccr-migration-"));
-const originalMigrationsDir = process.env.OMNIROUTE_MIGRATIONS_DIR;
-process.env.OMNIROUTE_MIGRATIONS_DIR = migrationsDir;
-
-fs.writeFileSync(
-  path.join(migrationsDir, "134_proxy_logs_egress_ip.sql"),
-  "ALTER TABLE proxy_logs ADD COLUMN egress_ip TEXT;"
-);
-fs.writeFileSync(
-  path.join(migrationsDir, "139_ccr_blocks.sql"),
-  "CREATE TABLE ccr_blocks (principal_id TEXT PRIMARY KEY);"
-);
-
-const { runMigrations } = await import("../../src/lib/db/migrationRunner.ts");
-
-function createLegacyDb(appliedName: string) {
-  const db = new Database(":memory:");
-  db.exec(`
-    CREATE TABLE proxy_logs (id TEXT PRIMARY KEY);
-    CREATE TABLE ccr_blocks (principal_id TEXT PRIMARY KEY);
-    CREATE TABLE _omniroute_migrations (
-      version TEXT PRIMARY KEY,
-      name TEXT NOT NULL,
-      applied_at TEXT NOT NULL DEFAULT (datetime('now'))
-    );
-  `);
-  db.prepare("INSERT INTO _omniroute_migrations (version, name) VALUES (?, ?)").run(
-    "134",
-    appliedName
-  );
-  return db;
-}
-
-test.after(() => {
-  fs.rmSync(migrationsDir, { recursive: true, force: true });
-  if (originalMigrationsDir === undefined) delete process.env.OMNIROUTE_MIGRATIONS_DIR;
-  else process.env.OMNIROUTE_MIGRATIONS_DIR = originalMigrationsDir;
-});
-
-test("renumbered CCR migration frees 134 for proxy_logs on existing databases", () => {
-  const db = createLegacyDb("ccr_blocks");
-  try {
-    assert.equal(runMigrations(db), 1);
-    assert.deepEqual(
-      db.prepare("SELECT version, name FROM _omniroute_migrations ORDER BY version").all(),
-      [
-        { version: "134", name: "proxy_logs_egress_ip" },
-        { version: "139", name: "ccr_blocks" },
-      ]
-    );
-    const columns = db.prepare("PRAGMA table_info(proxy_logs)").all() as Array<{ name: string }>;
-    assert.ok(columns.some((column) => column.name === "egress_ip"));
-  } finally {
-    db.close();
-  }
-});
-
-test("renumbered CCR migration marks an existing table without recreating it", () => {
-  const db = createLegacyDb("proxy_logs_egress_ip");
-  try {
-    assert.equal(runMigrations(db), 1);
-    assert.deepEqual(
-      db.prepare("SELECT version, name FROM _omniroute_migrations ORDER BY version").all(),
-      [
-        { version: "134", name: "proxy_logs_egress_ip" },
-        { version: "139", name: "ccr_blocks" },
-      ]
-    );
-  } finally {
-    db.close();
-  }
-});

tests/unit/db-migrationrunner-constants-split.test.ts

@@ -70,8 +70,8 @@ describe("migrationRunner/constants — exact small-table snapshots", () => {
 // ── large tables — count + shape + spot-checks (corruption guard) ─────────────
 
 describe("migrationRunner/constants — large-table integrity", () => {
-  it("RENAMED_MIGRATION_COMPATIBILITY has 11 well-formed entries", () => {
-    assert.equal(RENAMED_MIGRATION_COMPATIBILITY.length, 11);
+  it("RENAMED_MIGRATION_COMPATIBILITY has 10 well-formed entries", () => {
+    assert.equal(RENAMED_MIGRATION_COMPATIBILITY.length, 10);
     for (const e of RENAMED_MIGRATION_COMPATIBILITY) {
       assert.equal(typeof e.fromVersion, "string");
       assert.equal(typeof e.fromName, "string");
@@ -91,12 +91,6 @@ describe("migrationRunner/constants — large-table integrity", () => {
     // both manifest_routing collisions (052→059 and 056→059) must survive
     const manifest = RENAMED_MIGRATION_COMPATIBILITY.filter((e) => e.toName === "manifest_routing");
     assert.deepEqual(manifest.map((e) => e.fromVersion).sort(), ["052", "056"]);
-    assert.deepEqual(RENAMED_MIGRATION_COMPATIBILITY.at(-1), {
-      fromVersion: "134",
-      fromName: "ccr_blocks",
-      toVersion: "139",
-      toName: "ccr_blocks",
-    });
   });
 
   it("PHYSICAL_SCHEMA_SENTINELS has 15 well-formed entries incl. the newest 064", () => {

tests/unit/repro-9630-combo-false-503.test.ts

@@ -1,79 +0,0 @@
-import test from "node:test";
-import assert from "node:assert/strict";
-import {
-  handleComboChat,
-} from "../../open-sse/services/combo.ts";
-import { getCircuitBreaker, STATE } from "../../src/shared/utils/circuitBreaker.js";
-
-function okResponse() {
-  return new Response(JSON.stringify({ ok: true }), {
-    status: 200,
-    headers: { "Content-Type": "application/json" },
-  });
-}
-
-test("#9630: combo returns 503 when circuit breaker is OPEN but other healthy targets exist", async () => {
-  const cb = getCircuitBreaker("openai");
-  cb.state = STATE.OPEN;
-  cb.resetTimeout = 60000;
-  cb.failureCount = 5;
-  cb.failureThreshold = 3;
-  cb.lastFailureTime = Date.now();
-
-  const result = await handleComboChat({
-    body: { messages: [{ role: "user", content: "hello" }] },
-    combo: {
-      name: "repro-9630",
-      strategy: "priority",
-      models: ["openai/gpt-4", "anthropic/claude-opus-5"],
-    },
-    handleSingleModel: async (_body: any, modelStr: string) => {
-      assert.equal(modelStr, "anthropic/claude-opus-5", "should skip openai breaker and try anthropic");
-      return okResponse();
-    },
-    isModelAvailable: async () => true,
-    log: { info: () => {}, warn: () => {}, debug: () => {}, error: () => {} } as any,
-    settings: null,
-    relayOptions: null as any,
-    allCombos: null,
-  });
-
-  assert.ok(result.ok, "should succeed via anthropic fallback when openai breaker is open");
-});
-
-test("#9630: combo returns truthful error, not false ALL_ACCOUNTS_INACTIVE, when ALL targets are breaker-open", async () => {
-  const cb = getCircuitBreaker("openai");
-  cb.state = STATE.OPEN;
-  cb.resetTimeout = 60000;
-  cb.failureCount = 5;
-  cb.failureThreshold = 3;
-  cb.lastFailureTime = Date.now();
-
-  const cb2 = getCircuitBreaker("anthropic");
-  cb2.state = STATE.OPEN;
-  cb2.resetTimeout = 60000;
-  cb2.failureCount = 5;
-  cb2.failureThreshold = 3;
-  cb2.lastFailureTime = Date.now();
-
-  const result = await handleComboChat({
-    body: { messages: [{ role: "user", content: "hello" }] },
-    combo: {
-      name: "repro-9630-all-breaker",
-      strategy: "priority",
-      models: ["openai/gpt-4", "anthropic/claude-opus-5"],
-    },
-    handleSingleModel: async () => { throw new Error("should not be called"); },
-    isModelAvailable: async () => true,
-    log: { info: () => {}, warn: () => {}, debug: () => {}, error: () => {} } as any,
-    settings: null,
-    relayOptions: null as any,
-    allCombos: null,
-  });
-
-  assert.equal(result.status, 503);
-  const body = await result.json();
-  // The diagnostic should NOT claim ALL_ACCOUNTS_INACTIVE when no real dispatch was attempted
-  assert.notEqual(body.error?.code, "ALL_ACCOUNTS_INACTIVE", 
-    "should not claim ALL_ACCOUNTS_INACTIVE when all targets were gated by pre-dispatch checks");
-});