@staticeng/opencode-litellm 0.3.0 → 0.3.2

package/README.md

@@ -182,3 +182,9 @@ The GitHub release workflow supports npm trusted publishing from the `npm-produc
 requires this GitHub repository to remain public. Before a release, configure npm's trusted
 publisher for package `@staticeng/opencode-litellm` with this repository, workflow
 `publish.yml`, and environment `npm-production`; no npm token is used by the workflow.
+
+### Local RTX 5090 Strata aliases
+
+The exact discovered aliases `5090-local-model` and `5090-local-model-codex` use the Qwen3.8 Flash Next Strata contract: text/image input, text output, reasoning, tools, and 262144 tokens of shared context. The output ceiling is 262144 within that shared window; it is not an additional output budget. Pricing continues to come from LiteLLM metadata.
+
+Both aliases preserve their routable IDs and use Chat Completions in OpenCode. Their public variants are `off`, `low`, `medium`, and `xhigh` (default `xhigh`): `off` sends `reasoning_effort: "none"`; the other variants send their named effort. Strata accepts `high` and `max` as aliases of native `xhigh`; they are not distinct variants. This differs from the cloud Qwen contract and does not alter it. The `-codex` alias remains available to Codex via LiteLLM's separate Responses adapter. No alias is fabricated when discovery omits it; explicit model/provider overrides still win.

package/dist/model-contracts.js

@@ -54,6 +54,15 @@ const QWEN_FLASH_NEXT_METADATA = Object.freeze({
     tool_call: true,
     limit: Object.freeze({ context: 262144, output: 0 }),
 });
+// Expose native Qwen efforts; Strata also accepts high/max as xhigh aliases.
+const STRATA_QWEN_MODES = Object.freeze([
+    Object.freeze({ id: "off", legacy: freezeJson({ reasoningEffort: "none" }), v2Body: freezeJson({ reasoning_effort: "none" }) }),
+    ...effortModes(["low", "medium", "xhigh"]),
+]);
+const STRATA_QWEN_METADATA = Object.freeze({
+    ...QWEN_FLASH_NEXT_METADATA,
+    limit: Object.freeze({ context: 262144, output: 262144 }),
+});
 const chatGptAliases = (model) => Object.freeze([
     model,
     `chatgpt/${model}`,
@@ -73,6 +82,7 @@ export const MODEL_CONTRACTS = Object.freeze([
     contract("DeepSeek V4 Flash", ["deepseek-v4-flash-fp8-mtp", "deepseek-v4-flash-fp8-mtp-norefusal"], DEEPSEEK_MODES, "max"),
     contract("Qwen3.8", ["qwen3.8-27b-refusal-dial"], QWEN_MODES, "xhigh"),
     contract("Qwen3.8", ["qwen3.8-flash-next"], QWEN_MODES, "xhigh", QWEN_FLASH_NEXT_METADATA, true),
+    contract("Qwen3.8 Strata", ["5090-local-model", "5090-local-model-codex"], STRATA_QWEN_MODES, "xhigh", STRATA_QWEN_METADATA, true),
 ]);
 export const RETIRED_MODEL_ALIASES = Object.freeze([
     ...chatGptAliases("gpt-5.3-codex"),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@staticeng/opencode-litellm",
-  "version": "0.3.0",
+  "version": "0.3.2",
   "description": "OpenCode plugin that discovers LiteLLM models at runtime.",
   "type": "module",
   "license": "MIT",