feat(pricing): add default pricing for Qwen coder-model on qw provider (#4488)

Rebuilt onto release/v3.8.33 (squash-base-stale). Integrated into release/v3.8.33.

CHANGELOG.md

@@ -41,6 +41,7 @@ _In development — bullets added per PR; finalized at release._
 - **feat(models): opt-in low-noise `/v1/models` catalog mode** — a new opt-in mode trims the `/v1/models` response to a quieter, lower-noise catalog for clients that choke on or don't need the full provider/model list. ([#4427](https://github.com/diegosouzapw/OmniRoute/pull/4427) — thanks @Rahulsharma0810)
 - **feat(ui): expose a `targetFormat` selector in the custom-models form** — the custom-models form now lets you pick the upstream target format explicitly, so a custom model can be pinned to the right wire format instead of relying on inference. ([#4475](https://github.com/diegosouzapw/OmniRoute/pull/4475) — thanks @adivekar-utexas)
 - **feat(providers): expose `gpt-4o` on the built-in GitHub Copilot (`gh`) provider** — GitHub Copilot still serves the original `gpt-4o` chat model via its `/chat/completions` endpoint, but the OmniRoute registry only shipped the GPT-5.x family, so clients that explicitly request `gpt-4o` against `gh` got an unknown-model error. `gpt-4o` is now registered under the `github` provider next to the GPT-5.x lineup (chat/completions, 128k context — no `openai-responses` targetFormat). Ported from [9router#98](https://github.com/decolua/9router/pull/98). (thanks @I3eka)
+- **feat(pricing): default pricing for Qwen `coder-model` on the `qw` provider** — the Qwen Coder Free (`qw`) registry already exposed the `coder-model` id (Qwen3.5/3.6 Coder Model) but `DEFAULT_PRICING.qw` was missing the row, so usage tracking reported `$0.00` for that model. The pricing row is now added with the same shape as the sibling `vision-model` tier, restoring non-zero cost tracking. Ported from upstream 9router PR [decolua/9router#156](https://github.com/decolua/9router/pull/156). (thanks @LinearSakana)
 
 ### 🐛 Fixed
 

src/shared/constants/pricing.ts

@@ -425,6 +425,15 @@ export const DEFAULT_PRICING = {
       reasoning: 9.0,
       cache_creation: 1.5,
     },
+    // Qwen3.5/3.6 Coder Model — ported from upstream 9router PR #156 (zx07).
+    // Priced identically to the vision tier per upstream defaults.
+    "coder-model": {
+      input: 1.5,
+      output: 6.0,
+      cached: 0.75,
+      reasoning: 9.0,
+      cache_creation: 1.5,
+    },
   },
 
   // Qoder AI (if)

tests/unit/catalog-updates-v3x.test.ts

@@ -149,3 +149,33 @@ test("Every Codex registry model resolves a non-zero pricing row (alias: cx)", a
     );
   }
 });
+
+test("Every Qwen registry model resolves a non-zero pricing row (alias: qw)", async () => {
+  const { getPricingForModel } = await import("../../src/shared/constants/pricing.ts");
+  const models = getModelsByProviderId("qwen");
+  assert.ok(models.length > 0, "qwen must expose models");
+
+  for (const model of models) {
+    // Qwen pricing lives under the "qw" alias (its DEFAULT_PRICING key).
+    const pricing = getPricingForModel("qw", model.id) as {
+      input?: number;
+      output?: number;
+    } | null;
+    assert.ok(pricing, `qw pricing must include qwen model "${model.id}"`);
+    assert.equal(
+      typeof pricing?.input === "number" && typeof pricing?.output === "number",
+      true,
+      `qw pricing for "${model.id}" must have numeric input/output`
+    );
+  }
+
+  // Regression guard: the "coder-model" id (Qwen3.5/3.6 Coder Model, ported from
+  // upstream 9router PR #156) must be priced like the other Qwen coder tier.
+  const coderModel = getPricingForModel("qw", "coder-model") as {
+    input: number;
+    output: number;
+  } | null;
+  assert.ok(coderModel, "qw pricing must include coder-model");
+  assert.equal(typeof coderModel?.input, "number");
+  assert.equal(typeof coderModel?.output, "number");
+});