diff --git a/packages/db/src/etl/normalizers.test.ts b/packages/db/src/etl/normalizers.test.ts
index a24ee6db..25022f8b 100644
--- a/packages/db/src/etl/normalizers.test.ts
+++ b/packages/db/src/etl/normalizers.test.ts
@@ -135,6 +135,21 @@ describe('resolveModelKey', () => {
     expect(resolveModelKey({ infmax_model_prefix: 'dsv4pro-fp8' })).toBe('dsv4');
   });
 
+  it('resolves AMD Kimi-K2.7-Code identifiers to the canonical kimik2.7-code key', () => {
+    // AMD AgentX sweeps emit the bare prefix `kimik2.7` (no `-code`) and the
+    // MXFP4 model path `amd/Kimi-K2.7-Code-MXFP4`; both must fold into the
+    // canonical `kimik2.7-code` DB bucket. Regression for GitHub Actions run
+    // 29975243963, whose overlay rendered nothing because every row was skipped
+    // as an unmapped model.
+    expect(resolveModelKey({ infmax_model_prefix: 'kimik2.7' })).toBe('kimik2.7-code');
+    expect(resolveModelKey({ infmax_model_prefix: 'kimik2.7-fp4' })).toBe('kimik2.7-code');
+    expect(resolveModelKey({ model_prefix: 'kimik2.7' })).toBe('kimik2.7-code');
+    expect(resolveModelKey({ model: 'amd/Kimi-K2.7-Code-MXFP4' })).toBe('kimik2.7-code');
+    // Canonical identifiers still resolve to the same bucket.
+    expect(resolveModelKey({ infmax_model_prefix: 'kimik2.7-code' })).toBe('kimik2.7-code');
+    expect(resolveModelKey({ model: 'moonshotai/Kimi-K2.7-Code' })).toBe('kimik2.7-code');
+  });
+
   it('falls back to MODEL_TO_KEY when prefix not present', () => {
     expect(resolveModelKey({ model: 'deepseek-ai/DeepSeek-R1' })).toBe('dsr1');
     expect(resolveModelKey({ model: 'nvidia/Llama-3.3-70B-Instruct-FP8' })).toBe('llama70b');
diff --git a/packages/db/src/etl/normalizers.ts b/packages/db/src/etl/normalizers.ts
index 275cd6ea..355629d9 100644
--- a/packages/db/src/etl/normalizers.ts
+++ b/packages/db/src/etl/normalizers.ts
@@ -45,6 +45,10 @@ const PRECISION_SUFFIX = /-(?:fp4|fp8|mxfp4|nvfp4)(?:-.*)?$/iu;
 const PREFIX_ALIASES: Record<string, string> = {
   gptoss: 'gptoss120b',
   dsv4pro: 'dsv4',
+  // AMD AgentX sweeps emit the bare prefix `kimik2.7` instead of the canonical
+  // `kimik2.7-code` DB key; alias it so those rows resolve (and precision-suffixed
+  // forms like `kimik2.7-fp4` fold in via PRECISION_SUFFIX stripping too).
+  'kimik2.7': 'kimik2.7-code',
 };
 
 function resolvePrefixToKey(prefix: string): string | null {
@@ -94,6 +98,7 @@ export const MODEL_TO_KEY: Record<string, string> = {
   'moonshotai/Kimi-K2.5': 'kimik2.5',
   'moonshotai/Kimi-K2.6': 'kimik2.6',
   'moonshotai/Kimi-K2.7-Code': 'kimik2.7-code',
+  'amd/Kimi-K2.7-Code-MXFP4': 'kimik2.7-code',
   // MiniMax-M2.5
   'MiniMaxAI/MiniMax-M2.5': 'minimaxm2.5',
   // MiniMax-M3 (428B, distinct architecture from the M2 series)