llmshim 0.3.2__tar.gz → 0.3.4__tar.gz

{llmshim-0.3.2 → llmshim-0.3.4}/CLAUDE.md

@@ -14,7 +14,7 @@ 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`
+- **Gemini:** `gemini-3.7-flash`, `gemini-3.6-flash`, `gemini-3.5-flash`, `gemini-3.5-flash-lite`, `gemini-3.1-flash-lite`
 - **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-0.3.2 → llmshim-0.3.4}/Cargo.lock

@@ -958,7 +958,7 @@ checksum = "6373607a59f0be73a39b6fe456b8192fcc3585f602af20751600e974dd455e77"
 
 [[package]]
 name = "llmshim"
-version = "0.3.2"
+version = "0.3.4"
 dependencies = [
  "async-stream",
  "async-trait",

{llmshim-0.3.2 → llmshim-0.3.4}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "llmshim"
-version = "0.3.2"
+version = "0.3.4"
 edition = "2021"
 description = "Blazing fast LLM API translation layer in pure Rust"
 license = "MIT OR Apache-2.0"

{llmshim-0.3.2 → llmshim-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llmshim
-Version: 0.3.2
+Version: 0.3.4
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
@@ -37,11 +37,30 @@ llmshim.configure(
     openai="sk-...",
     gemini="AIza...",
     xai="xai-...",
+    openrouter="sk-or-...",
 )
 ```
 
 Or from the CLI: `llmshim configure`
 
+### Self-hosted servers (vLLM / SGLang)
+
+vLLM and SGLang are configured via **environment variables** (not
+`config.toml`) — the auto-spawned proxy inherits them from your Python
+process. Set them before your first call:
+
+```python
+import os
+
+os.environ["VLLM_BASE_URL"] = "http://localhost:8000/v1"
+os.environ["VLLM_API_KEY"] = "..."       # optional
+os.environ["SGLANG_BASE_URL"] = "http://localhost:30000/v1"
+os.environ["SGLANG_API_KEY"] = "..."     # optional
+```
+
+Then address them via the model string — `vllm/<served-model>` or
+`sglang/<served-model>` (see the model table below).
+
 ## Chat
 
 ```python
@@ -106,17 +125,63 @@ print(f"GPT: {r2['message']['content']}")
 
 ## Reasoning / Thinking
 
+Two provider-agnostic knobs control reasoning; both are clamped to the
+nearest tier the target model supports:
+
+- `reasoning_effort` — `"none"`, `"low"`, `"medium"`, `"high"`, `"xhigh"`, or `"max"`
+- `reasoning_mode` — `"standard"` (default) or `"pro"` (requests substantially
+  more model work; native on OpenAI gpt-5.6/-pro, emulated as an effort bump
+  elsewhere)
+
 ```python
 resp = llmshim.chat(
-    "claude-sonnet-4-6",
+    "claude-sonnet-5",
     "Solve: x^2 - 5x + 6 = 0",
     max_tokens=4000,
     reasoning_effort="high",
+    reasoning_mode="pro",
 )
 print(resp["reasoning"])        # thinking content
 print(resp["message"]["content"])  # answer
 ```
 
+For full native control, bypass the unified mapping with a namespaced
+`provider_config` (see below), e.g.
+`provider_config={"x-anthropic": {"thinking": {"type": "enabled", "budget_tokens": 4000}}}`.
+
+## Provider-Specific Controls (`provider_config`)
+
+`provider_config` merges into the request **root** and carries anything the
+unified `config` doesn't cover. Native provider controls MUST be **namespaced**
+per provider (`x-anthropic`, `x-openai`, `x-gemini`, `x-openrouter`, `x-vllm`,
+`x-sglang`); it also carries the top-level `tools`, `response_format`, and
+`reasoning_summary` keys.
+
+```python
+resp = llmshim.chat(
+    "anthropic/claude-sonnet-5",
+    "Solve this step by step: 17 * 23",
+    max_tokens=4000,
+    provider_config={
+        # native Anthropic extended-thinking control
+        "x-anthropic": {"thinking": {"type": "enabled", "budget_tokens": 4000}},
+        # structured output
+        "response_format": {"type": "json_object"},
+    },
+)
+```
+
+OpenRouter routing preferences use the `x-openrouter` namespace:
+
+```python
+resp = llmshim.chat(
+    "openrouter/anthropic/claude-sonnet-4.5",
+    "Hello",
+    max_tokens=200,
+    provider_config={"x-openrouter": {"provider": {"sort": "throughput"}}},
+)
+```
+
 ## Tool Use / Function Calling
 
 ```python
@@ -147,7 +212,7 @@ resp = llmshim.chat(
     "anthropic/claude-sonnet-4-6",
     "Hello",
     max_tokens=100,
-    fallback=["openai/gpt-5.5", "gemini/gemini-3-flash-preview"],
+    fallback=["openai/gpt-5.6-sol", "gemini/gemini-3.5-flash"],
 )
 ```
 
@@ -220,10 +285,21 @@ billed provider calls; run it only when you deliberately want to hit real APIs.
 
 | Provider | Models |
 |----------|--------|
-| OpenAI | `gpt-5.5`, `gpt-5.5-pro`, `gpt-5.4`, `gpt-5.4-pro`, `gpt-5.4-mini`, `gpt-5.4-nano` |
+| 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` |
+| Gemini | `gemini-3.7-flash`, `gemini-3.6-flash`, `gemini-3.5-flash`, `gemini-3.5-flash-lite`, `gemini-3.1-flash-lite` |
 | 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.
 
+### OpenRouter & self-hosted (vLLM / SGLang)
+
+These providers are addressed by the model string plus environment variables —
+any model the upstream serves is reachable, so they aren't in the table above.
+
+| Provider | Address as | Env vars | Native controls |
+|----------|-----------|----------|-----------------|
+| OpenRouter | `openrouter/<vendor>/<model>` (e.g. `openrouter/anthropic/claude-sonnet-4.5`) | `OPENROUTER_API_KEY` (or `llmshim.configure(openrouter=...)`) | `provider_config={"x-openrouter": {...}}` (`provider`, `models`, `transforms`) |
+| vLLM | `vllm/<served-model>` | `VLLM_BASE_URL` (+ optional `VLLM_API_KEY`) | `provider_config={"x-vllm": {...}}` |
+| SGLang | `sglang/<served-model>` | `SGLANG_BASE_URL` (+ optional `SGLANG_API_KEY`) | `provider_config={"x-sglang": {...}}` |
+

{llmshim-0.3.2 → llmshim-0.3.4}/README.md

@@ -364,7 +364,7 @@ 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) |
+| **Google Gemini** | `gemini-3.7-flash`, `gemini-3.6-flash`, `gemini-3.5-flash`, `gemini-3.5-flash-lite`, `gemini-3.1-flash-lite` | Yes (thought summaries) |
 | **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-0.3.2 → llmshim-0.3.4}/docs/src/guides/reasoning.md

@@ -117,7 +117,7 @@ token budget scaled from `max_tokens` and floored at 1024:
 Gemini uses the four-rung
 `generationConfig.thinkingConfig.thinkingLevel` enum:
 
-| unified | gemini-3.5-flash / 3-flash-preview / 3.1-flash-lite-preview | gemini-3.1-pro-preview |
+| unified | gemini-3.5-flash / 3.6-flash / 3.5-flash-lite / 3.1-flash-lite | gemini-3.7-flash (and gemini-3.1-pro) |
 |---|---|---|
 | `none` | `minimal` (zero thinking tokens) | **`low`** (this model cannot disable thinking) |
 | `low` | `low` | `low` |
@@ -126,8 +126,8 @@ Gemini uses the four-rung
 | `xhigh` | **`high`** | **`high`** |
 | `max` | **`high`** | **`high`** |
 
-Gemini 3.1 Pro rejects both `minimal` and `thinkingBudget: 0`, so `none` clamps
-to its `low` floor. The legacy integer `thinkingBudget` remains available only
+Gemini 3.7 Flash and Gemini 3.1 Pro reject both `minimal` and `thinkingBudget: 0`, so `none`
+clamps to their `low` floor (verified live). Other flash models accept `minimal` and can disable thinking. The legacy integer `thinkingBudget` remains available only
 through `x-gemini.thinkingConfig`.
 
 ### xAI Responses API

{llmshim-0.3.2 → llmshim-0.3.4}/docs/src/reference/models.md

@@ -14,7 +14,7 @@ the ID and display label.
 
 ## Registered catalog
 
-The current registry contains 24 entries, newest first within each provider.
+The current registry contains 27 entries, newest first within each provider.
 This page mirrors `src/models.rs`; use runtime discovery rather than parsing
 this table in applications.
 
@@ -48,9 +48,11 @@ this table in applications.
 
 | ID | Display name |
 |---|---|
+| `gemini/gemini-3.7-flash` | Gemini 3.7 Flash |
+| `gemini/gemini-3.6-flash` | Gemini 3.6 Flash |
 | `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 |
+| `gemini/gemini-3.5-flash-lite` | Gemini 3.5 Flash Lite |
+| `gemini/gemini-3.1-flash-lite` | Gemini 3.1 Flash Lite |
 
 ### xAI
 

{llmshim-0.3.2 → llmshim-0.3.4}/llmshim/__init__.py

@@ -14,6 +14,8 @@ Spec-faithful TypedDicts live in ``llmshim.types`` (also re-exported here) for
 static type-checking of requests, responses, and stream events.
 """
 
+from importlib.metadata import PackageNotFoundError, version
+
 from llmshim import types
 from llmshim._client import LlmShimError, chat, configure, health, models, stream
 from llmshim.types import (
@@ -55,4 +57,7 @@ __all__ = [
     "ToolCall",
     "Usage",
 ]
-__version__ = "0.1.22"
+try:
+    __version__ = version("llmshim")
+except PackageNotFoundError:  # not installed (e.g. running from source tree)
+    __version__ = "0.0.0"

{llmshim-0.3.2 → llmshim-0.3.4}/llmshim/_client.py

@@ -89,6 +89,7 @@ def configure(
     anthropic: Optional[str] = None,
     gemini: Optional[str] = None,
     xai: Optional[str] = None,
+    openrouter: Optional[str] = None,
 ) -> None:
     """Configure API keys. Writes to ~/.llmshim/config.toml.
 
@@ -98,6 +99,19 @@ def configure(
     Usage:
         import llmshim
         llmshim.configure(anthropic="sk-ant-...", openai="sk-...")
+
+    Self-hosted servers (vLLM, SGLang) are configured via environment
+    variables — NOT config.toml — which the auto-spawned proxy inherits from
+    the Python process. Set them before your first call, e.g.::
+
+        import os
+        os.environ["VLLM_BASE_URL"] = "http://localhost:8000/v1"
+        os.environ["VLLM_API_KEY"] = "..."      # optional
+        os.environ["SGLANG_BASE_URL"] = "http://localhost:30000/v1"
+        os.environ["SGLANG_API_KEY"] = "..."    # optional
+
+    Then address them via the model string, e.g. ``vllm/<served-model>`` or
+    ``sglang/<served-model>``.
     """
     config_dir = Path.home() / ".llmshim"
     config_path = config_dir / "config.toml"
@@ -125,6 +139,8 @@ def configure(
         keys["gemini"] = gemini
     if xai is not None:
         keys["xai"] = xai
+    if openrouter is not None:
+        keys["openrouter"] = openrouter
 
     # Write back
     config_dir.mkdir(parents=True, exist_ok=True)
@@ -152,6 +168,8 @@ def configure(
         os.environ["GEMINI_API_KEY"] = gemini
     if xai:
         os.environ["XAI_API_KEY"] = xai
+    if openrouter:
+        os.environ["OPENROUTER_API_KEY"] = openrouter
 
     # If server is already running, it won't pick up new keys until restart.
     # Force restart on next call.

{llmshim-0.3.2 → llmshim-0.3.4}/src/main.rs

@@ -22,9 +22,11 @@ const MODELS: &[(&str, &str)] = &[
     ("anthropic/claude-opus-4-6", "Claude Opus 4.6"),
     ("anthropic/claude-sonnet-4-6", "Claude Sonnet 4.6"),
     ("anthropic/claude-haiku-4-5-20251001", "Claude Haiku 4.5"),
+    ("gemini/gemini-3.7-flash", "Gemini 3.7 Flash"),
+    ("gemini/gemini-3.6-flash", "Gemini 3.6 Flash"),
     ("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"),
+    ("gemini/gemini-3.5-flash-lite", "Gemini 3.5 Flash Lite"),
+    ("gemini/gemini-3.1-flash-lite", "Gemini 3.1 Flash Lite"),
     ("xai/grok-4.6", "Grok 4.6"),
     ("xai/grok-4.5", "Grok 4.5"),
     ("xai/grok-4.3", "Grok 4.3"),

{llmshim-0.3.2 → llmshim-0.3.4}/src/models.rs

@@ -325,6 +325,24 @@ pub const MODELS: &[ModelInfo] = &[
         max_output_tokens: Some(64_000),
         capabilities: CAPS_FULL,
     },
+    ModelInfo {
+        id: "gemini/gemini-3.7-flash",
+        provider: "gemini",
+        name: "gemini-3.7-flash",
+        label: "Gemini 3.7 Flash",
+        context_window_tokens: Some(1_048_576),
+        max_output_tokens: Some(65_536),
+        capabilities: CAPS_STD,
+    },
+    ModelInfo {
+        id: "gemini/gemini-3.6-flash",
+        provider: "gemini",
+        name: "gemini-3.6-flash",
+        label: "Gemini 3.6 Flash",
+        context_window_tokens: Some(1_048_576),
+        max_output_tokens: Some(65_536),
+        capabilities: CAPS_STD,
+    },
     ModelInfo {
         id: "gemini/gemini-3.5-flash",
         provider: "gemini",
@@ -335,19 +353,19 @@ pub const MODELS: &[ModelInfo] = &[
         capabilities: CAPS_FULL,
     },
     ModelInfo {
-        id: "gemini/gemini-3.1-pro-preview",
+        id: "gemini/gemini-3.5-flash-lite",
         provider: "gemini",
-        name: "gemini-3.1-pro-preview",
-        label: "Gemini 3.1 Pro",
+        name: "gemini-3.5-flash-lite",
+        label: "Gemini 3.5 Flash Lite",
         context_window_tokens: Some(1_048_576),
         max_output_tokens: Some(65_536),
         capabilities: CAPS_STD,
     },
     ModelInfo {
-        id: "gemini/gemini-3-flash-preview",
+        id: "gemini/gemini-3.1-flash-lite",
         provider: "gemini",
-        name: "gemini-3-flash-preview",
-        label: "Gemini 3 Flash",
+        name: "gemini-3.1-flash-lite",
+        label: "Gemini 3.1 Flash Lite",
         context_window_tokens: Some(1_048_576),
         max_output_tokens: Some(65_536),
         capabilities: CAPS_STD,

{llmshim-0.3.2 → llmshim-0.3.4}/src/providers/gemini.rs

@@ -581,11 +581,15 @@ fn transform_response_to_openai(model: &str, resp: &Value) -> Result<Value> {
     }))
 }
 
-/// Models that cannot turn thinking off: gemini-3.1-pro rejects both
-/// thinkingLevel "minimal" and thinkingBudget 0 ("This model only works in
-/// thinking mode", verified live). Unified effort "none" clamps to "low".
+/// Models that cannot turn thinking off: gemini-3.1-pro and gemini-3.7-flash
+/// reject thinkingLevel "minimal" (and thinkingBudget 0) — verified live.
+/// Unified effort "none" clamps to "low" for them.
 fn cannot_disable_thinking(model: &str) -> bool {
-    model.to_lowercase().contains("3.1-pro")
+    let m = model.to_lowercase();
+    // gemini-3.1-pro and gemini-3.7-flash reject thinkingLevel "minimal" (and
+    // thinkingBudget 0), verified live — unified "none" clamps to "low". Other
+    // flash models (3.5/3.6/3.5-lite) accept "minimal" and can disable thinking.
+    m.contains("3.1-pro") || m.contains("3.7-flash")
 }
 
 impl Provider for Gemini {

{llmshim-0.3.2 → llmshim-0.3.4}/tests/integration_gemini.rs

@@ -436,3 +436,65 @@ async fn all_three_providers_same_shape() {
         );
     }
 }
+
+#[tokio::test]
+#[ignore]
+async fn gemini_3_7_flash_completion() {
+    if std::env::var("GEMINI_API_KEY").is_err() {
+        return;
+    }
+    let router = router();
+    let req = json!({
+        "model": "gemini/gemini-3.7-flash",
+        "messages": [{"role": "user", "content": "In one short sentence, what is Rust?"}],
+        "max_tokens": 2000,
+    });
+    let resp = llmshim::completion(&router, &req).await.unwrap();
+    let content = resp["choices"][0]["message"]["content"]
+        .as_str()
+        .unwrap_or("");
+    assert!(!content.is_empty(), "expected a response, got: {resp}");
+    println!("gemini-3.7-flash said: {content}");
+}
+
+#[tokio::test]
+#[ignore]
+async fn gemini_3_7_flash_none_clamps_to_low() {
+    // gemini-3.7-flash 400s on thinkingLevel "minimal"; llmshim must clamp
+    // reasoning_effort "none" to "low". Asserts success, not a 400.
+    if std::env::var("GEMINI_API_KEY").is_err() {
+        return;
+    }
+    let router = router();
+    let req = json!({
+        "model": "gemini/gemini-3.7-flash",
+        "messages": [{"role": "user", "content": "Say hi."}],
+        "max_tokens": 2000,
+        "reasoning_effort": "none",
+    });
+    let resp = llmshim::completion(&router, &req)
+        .await
+        .expect("none must clamp to low for gemini-3.7-flash, not 400");
+    assert_eq!(resp["object"], "chat.completion");
+    println!("gemini-3.7-flash none->low clamp OK");
+}
+
+#[tokio::test]
+#[ignore]
+async fn gemini_3_1_flash_lite_completion() {
+    if std::env::var("GEMINI_API_KEY").is_err() {
+        return;
+    }
+    let router = router();
+    let req = json!({
+        "model": "gemini/gemini-3.1-flash-lite",
+        "messages": [{"role": "user", "content": "In one short sentence, what is Rust?"}],
+        "max_tokens": 2000,
+    });
+    let resp = llmshim::completion(&router, &req).await.unwrap();
+    let content = resp["choices"][0]["message"]["content"]
+        .as_str()
+        .unwrap_or("");
+    assert!(!content.is_empty(), "expected a response, got: {resp}");
+    println!("gemini-3.1-flash-lite said: {content}");
+}

{llmshim-0.3.2 → llmshim-0.3.4}/tests/unit_gemini.rs

@@ -1529,3 +1529,32 @@ fn request_strips_foreign_reasoning_signature() {
     assert!(!body.contains("redacted-should-not-leak"));
     assert!(!body.contains("reasoning_signature"));
 }
+
+#[test]
+fn reasoning_none_clamps_per_model_disable_capability() {
+    // gemini-3.7-flash rejects thinkingLevel "minimal" (verified live) -> "none"
+    // clamps to "low". Other flash models accept "minimal" -> "none" stays "minimal".
+    let p = provider();
+    let req = json!({
+        "model": "x",
+        "messages": [{"role": "user", "content": "hi"}],
+        "reasoning_effort": "none",
+    });
+    let r = p.transform_request("gemini-3.7-flash", &req).unwrap();
+    assert_eq!(
+        r.body["generationConfig"]["thinkingConfig"]["thinkingLevel"], "low",
+        "gemini-3.7-flash cannot disable thinking -> none clamps to low"
+    );
+    for m in [
+        "gemini-3.6-flash",
+        "gemini-3.5-flash",
+        "gemini-3.5-flash-lite",
+        "gemini-3.1-flash-lite",
+    ] {
+        let r = p.transform_request(m, &req).unwrap();
+        assert_eq!(
+            r.body["generationConfig"]["thinkingConfig"]["thinkingLevel"], "minimal",
+            "{m} can disable thinking -> none maps to minimal"
+        );
+    }
+}

{llmshim-0.3.2 → llmshim-0.3.4}/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(), 25);
+    assert_eq!(MODELS.len(), 27);
 }
 
 #[test]