chore(models): sync Command Code catalog

CHANGELOG.md

@@ -2,6 +2,8 @@
 
 ## Unreleased
 
+- Refresh the Command Code CLI catalog to `1.56.0`, adding image input, reasoning effort levels, a 131,072-token output limit, and reviewed display pricing for `Qwen/Qwen3.8-Omni-Flash`.
+
 - Normalize nullable type arrays for `google/gemini-*` tools on the generate transport to avoid the gateway's `any_of` validation error (#99), preserving required fields, literal data, and schemas for unrelated models.
 
 ## 0.7.0 - 2026-09-15

README.md

@@ -139,7 +139,7 @@ The following environment variables are intended for tests, local mocks, and com
 
 ## Image input
 
-The provider advertises image input only for models marked with the `image` input modality in the official Command Code CLI model catalog. The capability snapshot currently follows `command-code@1.54.0`; unknown models default to text-only until their upstream metadata is reviewed. A daily GitHub Actions job synchronizes the CLI version, image capabilities, reasoning flags, reasoning efforts, and model-specific output limits with the latest published CLI package, also dropping manual effort overrides that upstream has published itself, and opens or updates a reviewable pull request when they change. Pricing remains manually reviewed because temporary promotions and long-context tiers require explicit review.
+The provider advertises image input only for models marked with the `image` input modality in the official Command Code CLI model catalog. The capability snapshot currently follows `command-code@1.56.0`; unknown models default to text-only until their upstream metadata is reviewed. A daily GitHub Actions job synchronizes the CLI version, image capabilities, reasoning flags, reasoning efforts, and model-specific output limits with the latest published CLI package, also dropping manual effort overrides that upstream has published itself, and opens or updates a reviewable pull request when they change. Pricing remains manually reviewed because temporary promotions and long-context tiers require explicit review.
 
 For vision-capable models, Pi's native provider adapters forward image blocks from user messages and tool results using the documented OpenAI or Anthropic message schema. Unknown and text-only models remain marked text-only in Pi.
 

src/commandcode-catalog.ts

@@ -1,10 +1,10 @@
-export const COMMAND_CODE_CLI_VERSION = "1.54.0"
+export const COMMAND_CODE_CLI_VERSION = "1.56.0"
 
 export type CommandCodeInputType = "text" | "image"
 export type CommandCodeReasoningEffort = "minimal" | "low" | "medium" | "high" | "xhigh" | "max"
 
 /**
- * Generated from command-code@1.54.0 by `npm run sync:commandcode-catalog`.
+ * Generated from command-code@1.56.0 by `npm run sync:commandcode-catalog`.
  * Do not edit manually.
  */
 export const MODEL_INPUT_MODALITIES: Readonly<Record<string, readonly CommandCodeInputType[]>> = {
@@ -50,6 +50,7 @@ export const MODEL_INPUT_MODALITIES: Readonly<Record<string, readonly CommandCod
   "Qwen/Qwen3.8-Flash": ["text", "image"],
   "Qwen/Qwen3.8-Max": ["text", "image"],
   "Qwen/Qwen3.8-Max-0902": ["text", "image"],
+  "Qwen/Qwen3.8-Omni-Flash": ["text", "image"],
   "sakana/fugu-ultra": ["text", "image"],
   "stepfun/Step-3.7-Flash": ["text", "image"],
   "thinkingmachines/inkling": ["text", "image"],
@@ -109,6 +110,7 @@ export const MODEL_REASONING: Readonly<Record<string, true>> = {
   "Qwen/Qwen3.8-Flash": true,
   "Qwen/Qwen3.8-Max": true,
   "Qwen/Qwen3.8-Max-0902": true,
+  "Qwen/Qwen3.8-Omni-Flash": true,
   "sakana/fugu-ultra": true,
   "stepfun/Step-3.5-Flash": true,
   "stepfun/Step-3.7-Flash": true,
@@ -161,6 +163,7 @@ export const MODEL_EFFORTS: Readonly<Record<string, readonly CommandCodeReasonin
   "Qwen/Qwen3.8-Flash": ["low", "medium", "xhigh"],
   "Qwen/Qwen3.8-Max": ["low", "medium", "xhigh"],
   "Qwen/Qwen3.8-Max-0902": ["low", "medium", "xhigh"],
+  "Qwen/Qwen3.8-Omni-Flash": ["low", "medium", "xhigh"],
   "sakana/fugu-ultra": ["high", "xhigh"],
   "tencent/hy4-preview": ["low", "medium", "high"],
   "xai/grok-4.5": ["low", "medium", "high"],
@@ -174,5 +177,6 @@ export const MODEL_MAX_OUTPUT_TOKENS: Readonly<Record<string, number>> = {
   "inclusionai/ling-3.0-flash-sante:free": 32_768,
   "poolside/laguna-s-2.1-free": 32_768,
   "Qwen/Qwen3.8-27B": 32_768,
+  "Qwen/Qwen3.8-Omni-Flash": 131_072,
   "z-ai/glm-5.3-flash": 131_072,
 }

src/pricing.ts

@@ -20,7 +20,7 @@ export interface TemporaryPricing {
 }
 
 export const PRICING_SOURCE_URL = "https://commandcode.ai/docs/resources/pricing-limits"
-export const PRICING_LAST_VERIFIED = "2026-09-15"
+export const PRICING_LAST_VERIFIED = "2026-09-18"
 
 export const ZERO_MODEL_COST: CommandCodeModelCost = {
   input: 0,
@@ -101,6 +101,7 @@ export const MODEL_COSTS: Readonly<Record<string, CommandCodeModelCost>> = {
   "Qwen/Qwen3.8-Max-0902": { input: 2, output: 6, cacheRead: 0.25, cacheWrite: 0 },
   "Qwen/Qwen3.8-27B": { input: 0.4, output: 3, cacheRead: 0.04, cacheWrite: 0 },
   "Qwen/Qwen3.8-Flash": { input: 0.16, output: 0.47, cacheRead: 0.016, cacheWrite: 0 },
+  "Qwen/Qwen3.8-Omni-Flash": { input: 0.15, output: 0.47, cacheRead: 0.016, cacheWrite: 0 },
   "Qwen/Qwen3.7-Max": { input: 2.5, output: 7.5, cacheRead: 0.5, cacheWrite: 3.13 },
   "Qwen/Qwen3.7-Plus": {
     input: 0.4,

tests/fixtures/commandcode-model-ids.json

@@ -1,5 +1,5 @@
 {
-  "fetchedAt": "2026-09-15T00:04:32.535Z",
+  "fetchedAt": "2026-09-18T08:21:28.827Z",
   "source": "https://api.commandcode.ai/provider/v1/models",
   "modelIds": [
     "claude-sonnet-5",
@@ -38,6 +38,7 @@
     "MiniMaxAI/MiniMax-M2.5",
     "xiaomi/mimo-v2.5-pro",
     "xiaomi/mimo-v2.5",
+    "Qwen/Qwen3.8-Omni-Flash",
     "Qwen/Qwen3.8-Max-0902",
     "Qwen/Qwen3.8-Max",
     "Qwen/Qwen3.8-27B",

tests/fixtures/commandcode-pricing.json

@@ -1,5 +1,5 @@
 {
-  "verifiedAt": "2026-09-15",
+  "verifiedAt": "2026-09-18",
   "source": "https://commandcode.ai/docs/resources/pricing-limits",
   "tierPolicy": "Use request-wide input tiers; the highest threshold exceeded by input plus cache tokens applies to the full request.",
   "tiers": {
@@ -39,6 +39,7 @@
     "Qwen/Qwen3.8-Max-0902": [2, 6, 0.25, 0],
     "Qwen/Qwen3.8-27B": [0.4, 3, 0.04, 0],
     "Qwen/Qwen3.8-Flash": [0.16, 0.47, 0.016, 0],
+    "Qwen/Qwen3.8-Omni-Flash": [0.15, 0.47, 0.016, 0],
     "Qwen/Qwen3.7-Max": [2.5, 7.5, 0.5, 3.13],
     "Qwen/Qwen3.7-Plus": [0.4, 1.6, 0.08, 0.5],
     "Qwen/Qwen3.7-Flash": [0.03, 0.13, 0.006, 0.038],

tests/test-models.ts

@@ -126,6 +126,19 @@ describe("commandCodeModelsFromApiResponse()", () => {
     assert.equal(modelSupportsImageInput("unknown-new-model"), false)
   })
 
+  it("advertises Qwen 3.8 Omni Flash capabilities from the CLI catalog", () => {
+    const id = "Qwen/Qwen3.8-Omni-Flash"
+    assert.deepEqual(inputModalitiesForModel(id), ["text", "image"])
+    assert.equal(MODEL_REASONING[id], true)
+    assert.deepEqual(thinkingMetadataForModel(id)?.thinking?.efforts, ["low", "medium", "xhigh"])
+    const models = commandCodeModelsFromApiResponse({
+      object: "list",
+      data: [{ ...API_RESPONSE.data[0], id }],
+    })
+    assert.equal(models[0]?.reasoning, true)
+    assert.equal(models[0]?.maxTokens, 131_072)
+  })
+
   it("prefers host-resolved input modalities over the catalog snapshot", () => {
     // A model published upstream after the pinned CLI release is absent from the
     // generated catalog, so the host's resolved modalities must win.

tests/test-pricing.ts

@@ -54,7 +54,7 @@ function assertCost(
 describe("MODEL_COSTS pricing overlay", () => {
   it("covers the current Command Code model catalog snapshot", () => {
     assert.equal(fixture.source, "https://api.commandcode.ai/provider/v1/models")
-    assert.match(fixture.fetchedAt, /^2026-09-15T/)
+    assert.match(fixture.fetchedAt, /^2026-09-18T/)
 
     const catalogIds = [...fixture.modelIds].sort()
     const pricedIds = Object.keys(MODEL_COSTS).sort()
@@ -235,6 +235,12 @@ describe("MODEL_COSTS pricing overlay", () => {
   })
 
   it("uses reviewed rates for the September catalog additions", () => {
+    assertCost("Qwen/Qwen3.8-Omni-Flash", {
+      input: 0.15,
+      output: 0.47,
+      cacheRead: 0.016,
+      cacheWrite: 0,
+    })
     assertCost("Qwen/Qwen3.8-Max-0902", { input: 2, output: 6, cacheRead: 0.25, cacheWrite: 0 })
     assertCost("google/gemini-3.8-flash", {
       input: 1.5,
@@ -259,7 +265,7 @@ describe("MODEL_COSTS pricing overlay", () => {
 
   it("tracks pricing provenance", () => {
     assert.equal(PRICING_SOURCE_URL, "https://commandcode.ai/docs/resources/pricing-limits")
-    assert.equal(PRICING_LAST_VERIFIED, "2026-09-15")
+    assert.equal(PRICING_LAST_VERIFIED, "2026-09-18")
   })
 
   it("fails once temporary pricing needs review", () => {