feat(gateway): table the GLM-5.3-Flash window, drop GLM-4.7-cc

CHANGELOG.md

@@ -79,6 +79,12 @@ file is the human-readable summary of what changed and why.
 
 ### Gateway
 
+- **GLM-5.3-Flash gets its served window** — the model is served with the same
+  262,144-token window as MiniMax-M3, so it now has its own entry in the
+  built-in table instead of falling back to the safe 200K default. Signing in
+  (or re-running a configure flow) writes it the same context gauge and
+  compaction trigger the other large model gets; already-written configs are
+  not rewritten.
 - **The SSO provider is now AIGW** — signing in with SSO writes the gateway
   provider as `aigw`, shown as "AIGW" in the model picker, replacing the
   previous identity. Existing installs keep working: the old provider id stays

packages/codev-gateway/src/model-limits.ts

@@ -32,13 +32,14 @@ export const COMPACT_RESERVED = 40000
 export const COMPACT_PCT = 90
 
 // Known gateway models' context windows, keyed by the exact id `/v1/models`
-// reports. M3's window is capped at 262144 on the current deployment (the
-// model supports more, the gateway's resources don't). The 200K sibling is
-// deliberately absent: DEFAULT_WINDOW already describes it, and an entry
-// restating the default is one more thing to keep in sync.
+// reports. M3's and GLM-5.3-Flash's windows are capped at 262144 on the current
+// deployment (the models support more, the gateway's resources don't). Models
+// served at the 200K default are deliberately absent: DEFAULT_WINDOW already
+// describes them, and an entry restating the default is one more thing to keep
+// in sync.
 const TABLE: Record<string, number> = {
   "MiniMax/MiniMax-M3": 262144,
-  "zai-org/GLM-4.7-cc": 200000,
+  "zai-org/GLM-5.3-Flash": 262144,
 }
 
 // Unrecognized models are treated as 200K-class: it matches the smaller of the

packages/codev-gateway/test/config-block.test.ts

@@ -72,16 +72,18 @@ describe("buildGatewayConfig", () => {
     })
   })
 
-  // The per-model table: M3's 262144-token window (capped by the deployment,
+  // The per-model table: the 262144-token window (capped by the deployment,
   // not the model). Its 90% trigger + the 40000 reserve exceeds the window,
   // so declaredInput's clamp pins input at the window itself.
-  test("writes the table window for the known model", () => {
-    const config = buildGatewayConfig({ baseUrl: "https://gw.test", model: "MiniMax/MiniMax-M3" })
-    expect(config.provider.aigw.models["MiniMax/MiniMax-M3"].limit).toEqual({
-      context: 262144,
-      input: 262144,
-      output: 65536,
-    })
+  test("writes the table window for the known models", () => {
+    for (const id of ["MiniMax/MiniMax-M3", "zai-org/GLM-5.3-Flash"]) {
+      const config = buildGatewayConfig({ baseUrl: "https://gw.test", model: id })
+      expect(config.provider.aigw.models[id].limit).toEqual({
+        context: 262144,
+        input: 262144,
+        output: 65536,
+      })
+    }
   })
 
   // Without the declaration a custom-provider model resolves to text-only and

packages/codev-gateway/test/model-limits.test.ts

@@ -36,7 +36,7 @@ describe("limitsFor", () => {
   test("resolves the table's known models and defaults the rest", () => {
     // Triggers are always 90% of the window, whatever its source.
     expect(limitsFor("MiniMax/MiniMax-M3")).toEqual({ context: 262144, trigger: 235930 })
-    expect(limitsFor("zai-org/GLM-4.7-cc")).toEqual({ context: 200000, trigger: 180000 })
+    expect(limitsFor("zai-org/GLM-5.3-Flash")).toEqual({ context: 262144, trigger: 235930 })
     expect(limitsFor("anything/else")).toEqual(DEFAULT_LIMITS)
     expect(DEFAULT_LIMITS).toEqual({ context: 200000, trigger: 180000 })
   })