llmshim 0.3.1__tar.gz → 0.3.2__tar.gz

{llmshim-0.3.1 → llmshim-0.3.2}/CLAUDE.md

@@ -15,7 +15,7 @@ This is a public crate on crates.io. Do NOT make breaking changes to `pub` items
 - **OpenAI:** `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5`, `gpt-5.5-pro`, `gpt-5.4`, `gpt-5.4-pro`, `gpt-5.4-mini`, `gpt-5.4-nano`
 - **Anthropic:** `claude-opus-5`, `claude-opus-4-8`, `claude-sonnet-5`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-4-6`, `claude-haiku-4-5-20251001`
 - **Gemini:** `gemini-3.5-flash`, `gemini-3.1-pro-preview`, `gemini-3-flash-preview`
-- **xAI:** `grok-4.5`, `grok-4.3`, `grok-4.20-multi-agent-beta-0309`, `grok-4.20-beta-0309-reasoning`, `grok-4.20-beta-0309-non-reasoning`
+- **xAI:** `grok-4.6`, `grok-4.5`, `grok-4.3`, `grok-4.20-multi-agent-beta-0309`, `grok-4.20-beta-0309-reasoning`, `grok-4.20-beta-0309-non-reasoning`
 - **OpenRouter:** not enumerated (huge/dynamic catalog) — any `openrouter/<vendor>/<model>` slug routes through, e.g. `openrouter/anthropic/claude-sonnet-4.5`.
 - **vLLM / SGLang:** not enumerated (self-hosted) — any `vllm/<served-model>` or `sglang/<served-model>` routes through to the configured server, e.g. `sglang/Qwen/Qwen3.6-35B-A3B-FP8`.
 

{llmshim-0.3.1 → llmshim-0.3.2}/Cargo.lock

@@ -958,7 +958,7 @@ checksum = "6373607a59f0be73a39b6fe456b8192fcc3585f602af20751600e974dd455e77"
 
 [[package]]
 name = "llmshim"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
  "async-stream",
  "async-trait",

{llmshim-0.3.1 → llmshim-0.3.2}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "llmshim"
-version = "0.3.1"
+version = "0.3.2"
 edition = "2021"
 description = "Blazing fast LLM API translation layer in pure Rust"
 license = "MIT OR Apache-2.0"

{llmshim-0.3.1 → llmshim-0.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llmshim
-Version: 0.3.1
+Version: 0.3.2
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
@@ -223,7 +223,7 @@ billed provider calls; run it only when you deliberately want to hit real APIs.
 | OpenAI | `gpt-5.5`, `gpt-5.5-pro`, `gpt-5.4`, `gpt-5.4-pro`, `gpt-5.4-mini`, `gpt-5.4-nano` |
 | Anthropic | `claude-opus-5`, `claude-opus-4-8`, `claude-sonnet-5`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-4-6`, `claude-haiku-4-5-20251001` |
 | Gemini | `gemini-3.5-flash`, `gemini-3.1-pro-preview`, `gemini-3-flash-preview` |
-| xAI | `grok-4.5`, `grok-4.3`, `grok-4.20-multi-agent-beta-0309`, `grok-4.20-beta-0309-reasoning`, `grok-4.20-beta-0309-non-reasoning` |
+| xAI | `grok-4.6`, `grok-4.5`, `grok-4.3`, `grok-4.20-multi-agent-beta-0309`, `grok-4.20-beta-0309-reasoning`, `grok-4.20-beta-0309-non-reasoning` |
 
 Call `llmshim.models()` for the live list filtered to your configured providers.
 

{llmshim-0.3.1 → llmshim-0.3.2}/README.md

@@ -365,7 +365,7 @@ Standard library only. Full docs: [`clients/ruby/README.md`](clients/ruby/README
 | **OpenAI** | `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5`, `gpt-5.5-pro`, `gpt-5.4`, `gpt-5.4-pro`, `gpt-5.4-mini`, `gpt-5.4-nano` | Yes (summaries) |
 | **Anthropic** | `claude-opus-5`, `claude-opus-4-8`, `claude-sonnet-5`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-4-6`, `claude-haiku-4-5-20251001` | Yes (full thinking) |
 | **Google Gemini** | `gemini-3.5-flash`, `gemini-3.1-pro-preview`, `gemini-3-flash-preview` | Yes (thought summaries) |
-| **xAI** | `grok-4.5`, `grok-4.3`, `grok-4.20-multi-agent-beta-0309`, `grok-4.20-beta-0309-reasoning`, `grok-4.20-beta-0309-non-reasoning` | No (hidden) |
+| **xAI** | `grok-4.6`, `grok-4.5`, `grok-4.3`, `grok-4.20-multi-agent-beta-0309`, `grok-4.20-beta-0309-reasoning`, `grok-4.20-beta-0309-non-reasoning` | No (hidden) |
 
 Use a bare model name (auto-detected by prefix) or an explicit `provider/model` string.
 

{llmshim-0.3.1 → llmshim-0.3.2}/docs/src/guides/reasoning.md

@@ -134,7 +134,7 @@ through `x-gemini.thinkingConfig`.
 
 xAI receives the nested native shape `reasoning: {effort}`:
 
-| unified | grok-4.3 | grok-4.5 | grok-4.20-\*-reasoning / -non-reasoning |
+| unified | grok-4.3 | grok-4.5 / grok-4.6 | grok-4.20-\*-reasoning / -non-reasoning |
 |---|---|---|---|
 | `none` | `none` | **`low`** | omitted |
 | `low` | `low` | `low` | omitted |
@@ -143,7 +143,7 @@ xAI receives the nested native shape `reasoning: {effort}`:
 | `xhigh` | `xhigh` | `xhigh` | omitted |
 | `max` | **`xhigh`** | **`xhigh`** | omitted |
 
-grok-4.5 cannot disable reasoning, so `none` clamps to `low`. grok-4.20 models
+grok-4.5 and grok-4.6 cannot disable reasoning, so `none` clamps to `low`. grok-4.20 models
 are name-locked: reasoning on or off is encoded in the model name, and the API
 rejects any reasoning parameter. llmshim therefore omits it for that family.
 

{llmshim-0.3.1 → llmshim-0.3.2}/docs/src/reference/models.md

@@ -56,6 +56,7 @@ this table in applications.
 
 | ID | Display name |
 |---|---|
+| `xai/grok-4.6` | Grok 4.6 |
 | `xai/grok-4.5` | Grok 4.5 |
 | `xai/grok-4.3` | Grok 4.3 |
 | `xai/grok-4.20-multi-agent-beta-0309` | Grok 4.20 Multi-Agent |

{llmshim-0.3.1 → llmshim-0.3.2}/src/main.rs

@@ -25,6 +25,7 @@ const MODELS: &[(&str, &str)] = &[
     ("gemini/gemini-3.5-flash", "Gemini 3.5 Flash"),
     ("gemini/gemini-3.1-pro-preview", "Gemini 3.1 Pro"),
     ("gemini/gemini-3-flash-preview", "Gemini 3 Flash"),
+    ("xai/grok-4.6", "Grok 4.6"),
     ("xai/grok-4.5", "Grok 4.5"),
     ("xai/grok-4.3", "Grok 4.3"),
     (

{llmshim-0.3.1 → llmshim-0.3.2}/src/models.rs

@@ -352,6 +352,15 @@ pub const MODELS: &[ModelInfo] = &[
         max_output_tokens: Some(65_536),
         capabilities: CAPS_STD,
     },
+    ModelInfo {
+        id: "xai/grok-4.6",
+        provider: "xai",
+        name: "grok-4.6",
+        label: "Grok 4.6",
+        context_window_tokens: Some(500_000),
+        max_output_tokens: None,
+        capabilities: CAPS_XAI,
+    },
     ModelInfo {
         id: "xai/grok-4.5",
         provider: "xai",

{llmshim-0.3.1 → llmshim-0.3.2}/src/providers/xai.rs

@@ -189,11 +189,14 @@ fn is_reasoning_name_locked(model: &str) -> bool {
     model.to_lowercase().contains("4.20")
 }
 
-/// grok-4.5 cannot disable reasoning: `effort: "none"` -> 400 ("does not
-/// support `reasoning_effort` value `none`", verified live). Unified effort
-/// "none" clamps to "low". grok-4.3 and the fast pair DO accept "none".
+/// grok-4.5 / grok-4.6 cannot disable reasoning: `effort: "none"` -> 400 ("does
+/// not support `reasoning_effort` value `none`", verified live). Unified effort
+/// "none" clamps to "low". grok-4.3 DOES accept "none".
 fn reasoning_cannot_disable(model: &str) -> bool {
-    model.to_lowercase().contains("4.5")
+    let m = model.to_lowercase();
+    // grok-4.5 and grok-4.6 both 400 on `reasoning_effort: "none"` (verified
+    // live); unified "none" clamps to "low" for them. grok-4.3 accepts "none".
+    m.contains("4.5") || m.contains("4.6")
 }
 
 impl Provider for Xai {

llmshim-0.3.2/tests/integration_xai.rs

@@ -0,0 +1,72 @@
+/// Integration tests for xAI (Grok) hitting the real API.
+/// Run with: XAI_API_KEY=... cargo test --test integration_xai -- --ignored --nocapture
+use serde_json::json;
+
+fn router() -> llmshim::router::Router {
+    llmshim::router::Router::from_env()
+}
+
+#[tokio::test]
+#[ignore]
+async fn grok_4_6_completion() {
+    if std::env::var("XAI_API_KEY").is_err() {
+        return;
+    }
+    let router = router();
+    let req = json!({
+        "model": "xai/grok-4.6",
+        "messages": [{"role": "user", "content": "In one short sentence, what is Rust?"}],
+        "max_tokens": 2000,
+    });
+    let resp = llmshim::completion(&router, &req).await.unwrap();
+    assert_eq!(resp["object"], "chat.completion");
+    let content = resp["choices"][0]["message"]["content"]
+        .as_str()
+        .unwrap_or("");
+    assert!(!content.is_empty(), "expected a response, got: {resp}");
+    println!("grok-4.6 said: {content}");
+}
+
+#[tokio::test]
+#[ignore]
+async fn grok_4_6_reasoning_none_clamps_to_low() {
+    // grok-4.6 400s on reasoning_effort "none"; llmshim must clamp it to "low".
+    // This asserts the request SUCCEEDS (not a 400), proving the clamp.
+    if std::env::var("XAI_API_KEY").is_err() {
+        return;
+    }
+    let router = router();
+    let req = json!({
+        "model": "xai/grok-4.6",
+        "messages": [{"role": "user", "content": "Say hi."}],
+        "max_tokens": 2000,
+        "reasoning_effort": "none",
+    });
+    let resp = llmshim::completion(&router, &req)
+        .await
+        .expect("reasoning_effort=none must be clamped to low, not 400");
+    assert_eq!(resp["object"], "chat.completion");
+    println!("grok-4.6 none->low clamp OK");
+}
+
+#[tokio::test]
+#[ignore]
+async fn grok_4_6_reasoning_high() {
+    if std::env::var("XAI_API_KEY").is_err() {
+        return;
+    }
+    let router = router();
+    let req = json!({
+        "model": "xai/grok-4.6",
+        "messages": [{"role": "user", "content": "What is 17 * 24? Reason it through."}],
+        "max_tokens": 3000,
+        "reasoning_effort": "high",
+    });
+    let resp = llmshim::completion(&router, &req).await.unwrap();
+    let content = resp["choices"][0]["message"]["content"]
+        .as_str()
+        .unwrap_or("");
+    assert!(!content.is_empty(), "expected an answer, got: {resp}");
+    assert!(content.contains("408"), "expected 408 in answer: {content}");
+    println!("grok-4.6 reasoning OK: {content}");
+}

{llmshim-0.3.1 → llmshim-0.3.2}/tests/unit_models.rs

@@ -11,7 +11,7 @@ fn models_registry_has_all_providers() {
 
 #[test]
 fn models_registry_has_expected_count() {
-    assert_eq!(MODELS.len(), 24);
+    assert_eq!(MODELS.len(), 25);
 }
 
 #[test]
@@ -160,6 +160,7 @@ fn reasoning_support_matches_provider_behavior() {
         "openai/gpt-5.6-sol",
         "anthropic/claude-opus-5",
         "anthropic/claude-opus-4-8",
+        "xai/grok-4.6",
         "xai/grok-4.5",
     ] {
         assert_eq!(

{llmshim-0.3.1 → llmshim-0.3.2}/tests/unit_xai.rs

@@ -666,6 +666,29 @@ fn name_locked_grok_4_20_omits_reasoning_entirely() {
     }
 }
 
+#[test]
+fn reasoning_none_clamps_to_low_for_grok_4_5_and_4_6() {
+    // grok-4.5 and grok-4.6 400 on effort "none" (verified live) — clamp to "low".
+    let p = provider();
+    for model in ["grok-4.5", "grok-4.6"] {
+        let req = json!({
+            "model": "x",
+            "messages": [{"role": "user", "content": "hi"}],
+            "reasoning_effort": "none",
+        });
+        let r = p.transform_request(model, &req).unwrap();
+        assert_eq!(r.body["reasoning"]["effort"], "low", "{model} none->low");
+    }
+    // grok-4.3 CAN disable — "none" stays "none".
+    let req = json!({
+        "model": "x",
+        "messages": [{"role": "user", "content": "hi"}],
+        "reasoning_effort": "none",
+    });
+    let r = p.transform_request("grok-4.3", &req).unwrap();
+    assert_eq!(r.body["reasoning"]["effort"], "none");
+}
+
 #[test]
 fn mode_pro_bumps_effort() {
     let p = provider();