@staticeng/opencode-litellm 0.3.1 → 0.3.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +1 -1
- package/dist/model-contracts.js +3 -3
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -187,4 +187,4 @@ publisher for package `@staticeng/opencode-litellm` with this repository, workfl
|
|
|
187
187
|
|
|
188
188
|
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.
|
|
189
189
|
|
|
190
|
-
Both aliases preserve their routable IDs and use Chat Completions in OpenCode. Their public variants are `off`, `low`, `medium`, and `
|
|
190
|
+
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
CHANGED
|
@@ -54,10 +54,10 @@ const QWEN_FLASH_NEXT_METADATA = Object.freeze({
|
|
|
54
54
|
tool_call: true,
|
|
55
55
|
limit: Object.freeze({ context: 262144, output: 0 }),
|
|
56
56
|
});
|
|
57
|
-
//
|
|
57
|
+
// Expose native Qwen efforts; Strata also accepts high/max as xhigh aliases.
|
|
58
58
|
const STRATA_QWEN_MODES = Object.freeze([
|
|
59
59
|
Object.freeze({ id: "off", legacy: freezeJson({ reasoningEffort: "none" }), v2Body: freezeJson({ reasoning_effort: "none" }) }),
|
|
60
|
-
...effortModes(["low", "medium", "
|
|
60
|
+
...effortModes(["low", "medium", "xhigh"]),
|
|
61
61
|
]);
|
|
62
62
|
const STRATA_QWEN_METADATA = Object.freeze({
|
|
63
63
|
...QWEN_FLASH_NEXT_METADATA,
|
|
@@ -82,7 +82,7 @@ export const MODEL_CONTRACTS = Object.freeze([
|
|
|
82
82
|
contract("DeepSeek V4 Flash", ["deepseek-v4-flash-fp8-mtp", "deepseek-v4-flash-fp8-mtp-norefusal"], DEEPSEEK_MODES, "max"),
|
|
83
83
|
contract("Qwen3.8", ["qwen3.8-27b-refusal-dial"], QWEN_MODES, "xhigh"),
|
|
84
84
|
contract("Qwen3.8", ["qwen3.8-flash-next"], QWEN_MODES, "xhigh", QWEN_FLASH_NEXT_METADATA, true),
|
|
85
|
-
contract("Qwen3.8 Strata", ["5090-local-model", "5090-local-model-codex"], STRATA_QWEN_MODES, "
|
|
85
|
+
contract("Qwen3.8 Strata", ["5090-local-model", "5090-local-model-codex"], STRATA_QWEN_MODES, "xhigh", STRATA_QWEN_METADATA, true),
|
|
86
86
|
]);
|
|
87
87
|
export const RETIRED_MODEL_ALIASES = Object.freeze([
|
|
88
88
|
...chatGptAliases("gpt-5.3-codex"),
|