llmshim 0.1.26__tar.gz → 0.2.1__tar.gz

llmshim-0.2.1/.github/workflows/pages.yml

@@ -0,0 +1,50 @@
+name: Deploy docs to GitHub Pages
+
+# Gated to main: this only runs after the docs branch is merged. It never
+# fires on feature branches or pull requests.
+on:
+  push:
+    branches: [main]
+    paths:
+      - 'docs/**'
+      - '.github/workflows/pages.yml'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+# Allow one concurrent deployment; let an in-progress deploy finish.
+concurrency:
+  group: pages
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install mdBook + mermaid preprocessor
+        uses: taiki-e/install-action@v2
+        with:
+          # Pin both: mdbook-mermaid must match mdbook's preprocessor protocol
+          # (an unpinned mismatch fails with "Unable to parse the input").
+          tool: mdbook@0.4.52,mdbook-mermaid@0.16.2
+      - name: Build book
+        run: mdbook build docs
+      - name: Upload Pages artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: docs/book
+
+  deploy:
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

{llmshim-0.1.26 → llmshim-0.2.1}/CLAUDE.md

@@ -8,14 +8,14 @@ A pure Rust LLM API translation layer. Takes OpenAI-format JSON requests, transl
 
 **Published on crates.io as `llmshim`** — https://crates.io/crates/llmshim
 
-This is a public crate. Do NOT make breaking changes to `pub` items in `src/lib.rs`, `src/router.rs`, `src/provider.rs`, `src/error.rs`, `src/fallback.rs`, `src/log.rs`, `src/config.rs`, `src/models.rs`, or `src/vision.rs` without a semver bump. The `ragents` crate (https://github.com/sanjay920/ragents) depends on this.
+This is a public crate on crates.io. Do NOT make breaking changes to `pub` items in `src/lib.rs`, `src/router.rs`, `src/provider.rs`, `src/error.rs`, `src/fallback.rs`, `src/log.rs`, `src/config.rs`, `src/models.rs`, or `src/vision.rs` without a semver bump.
 
 ## Supported models
 
 - **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-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-3.1-flash-lite-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`, `grok-4-1-fast-reasoning`, `grok-4-1-fast-non-reasoning`
+- **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`
 
 ## Build & Test
 
@@ -70,7 +70,7 @@ Image content blocks are translated between providers automatically. Users can s
 
 ### Multi-model conversations
 
-Each provider sanitizes messages from other providers in `transform_request`. OpenAI's `annotations`/`refusal` stripped for Anthropic/Gemini. `reasoning_content` stripped for all. Tool calls normalized to OpenAI format in responses, translated back per-provider on input.
+Each provider sanitizes messages from other providers in `transform_request`. OpenAI's `annotations`/`refusal` stripped for Anthropic/Gemini. `reasoning_content` is stripped by other providers, but **Anthropic reconstructs a native `thinking` block** from `reasoning_content` + `reasoning_signature` (and `redacted_thinking` from `redacted_reasoning_content`) as the first block of the assistant turn, so extended-thinking + tool-use round-trips losslessly (surfaced on responses incl. streaming; opaque signatures are stripped by other providers so they never leak cross-provider; no signature → still stripped). Symmetric to the tool-call `thought_signature` round-trip. Tool calls normalized to OpenAI format in responses, translated back per-provider on input.
 
 ### Provider extension namespaces (`x-anthropic`, `x-gemini`)
 
@@ -81,7 +81,7 @@ Callers pass provider-specific controls under these keys. Each provider copies w
 
 ### Unified reasoning controls
 
-Two knobs work across every provider: `reasoning_effort` (`none|low|medium|high|xhigh|max`) and `reasoning_mode` (`standard|pro`). Each provider transform maps them to its native dialect, **clamping to the nearest tier the target model accepts** (all boundaries verified live — e.g. `max` is native only on OpenAI gpt-5.6; Anthropic 4.6 rejects `xhigh` but has `max`; Gemini's enum tops out at `high`; xAI grok-4.20 models reject any reasoning param). `mode: "pro"` is native on OpenAI gpt-5.6/-pro models (`reasoning.mode`), emulated as a one-tier effort bump elsewhere; explicit `none` always wins. Native passthrough (`x-openai.reasoning`, `x-anthropic.thinking`, `x-gemini.thinkingConfig`) bypasses the mapping entirely and always takes precedence. **Full per-provider mapping tables: `docs/reasoning.md`** — update it and the pinning tests in `tests/unit_*.rs` together whenever a mapping changes.
+Two knobs work across every provider: `reasoning_effort` (`none|low|medium|high|xhigh|max`) and `reasoning_mode` (`standard|pro`). Each provider transform maps them to its native dialect, **clamping to the nearest tier the target model accepts** (all boundaries verified live — e.g. `max` is native only on OpenAI gpt-5.6; Anthropic 4.6 rejects `xhigh` but has `max`; Gemini's enum tops out at `high`; xAI grok-4.20 models reject any reasoning param). `mode: "pro"` is native on OpenAI gpt-5.6/-pro models (`reasoning.mode`), emulated as a one-tier effort bump elsewhere; explicit `none` always wins. Native passthrough (`x-openai.reasoning`, `x-anthropic.thinking`, `x-gemini.thinkingConfig`) bypasses the mapping entirely and always takes precedence. **Full per-provider mapping tables: `docs/src/guides/reasoning.md`** — update it and the pinning tests in `tests/unit_*.rs` together whenever a mapping changes.
 
 ### Tool format translation
 

{llmshim-0.1.26 → llmshim-0.2.1}/Cargo.lock

@@ -958,7 +958,7 @@ checksum = "6373607a59f0be73a39b6fe456b8192fcc3585f602af20751600e974dd455e77"
 
 [[package]]
 name = "llmshim"
-version = "0.1.26"
+version = "0.2.1"
 dependencies = [
  "async-stream",
  "async-trait",

{llmshim-0.1.26 → llmshim-0.2.1}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "llmshim"
-version = "0.1.26"
+version = "0.2.1"
 edition = "2021"
 description = "Blazing fast LLM API translation layer in pure Rust"
 license = "MIT"

{llmshim-0.1.26 → llmshim-0.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llmshim
-Version: 0.1.26
+Version: 0.2.1
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
@@ -222,8 +222,8 @@ 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-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-3.1-flash-lite-preview`, `gemini-3-flash-preview` |
-| xAI | `grok-4.3`, `grok-4.20-multi-agent-beta-0309`, `grok-4.20-beta-0309-reasoning`, `grok-4.20-beta-0309-non-reasoning`, `grok-4-1-fast-reasoning`, `grok-4-1-fast-non-reasoning` |
+| 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` |
 
 Call `llmshim.models()` for the live list filtered to your configured providers.
 

{llmshim-0.1.26 → llmshim-0.2.1}/README.md

@@ -72,7 +72,7 @@ async fn main() {
     let router = llmshim::router::Router::from_env();
 
     let request = json!({
-        "model": "claude-sonnet-4-6",
+        "model": "claude-sonnet-5",
         "messages": [{"role": "user", "content": "What is Rust?"}],
         "max_tokens": 500,
     });
@@ -93,7 +93,7 @@ use serde_json::json;
 
 let router = llmshim::router::Router::from_env();
 let request = json!({
-    "model": "gpt-5.5",
+    "model": "gpt-5.6-sol",
     "messages": [{"role": "user", "content": "Write a haiku about Rust."}],
     "max_tokens": 128,
 });
@@ -142,7 +142,7 @@ llmshim proxy
 ```bash
 curl http://localhost:3000/v1/chat \
   -H "Content-Type: application/json" \
-  -d '{"model":"claude-sonnet-4-6","messages":[{"role":"user","content":"Hi"}],"config":{"max_tokens":100}}'
+  -d '{"model":"claude-sonnet-5","messages":[{"role":"user","content":"Hi"}],"config":{"max_tokens":100}}'
 ```
 
 | Method | Path | Description |
@@ -206,14 +206,14 @@ import llmshim
 # Keys can also come from env vars or `llmshim configure`.
 llmshim.configure(anthropic="sk-ant-...", openai="sk-...")
 
-resp = llmshim.chat("claude-sonnet-4-6", "Hello!", max_tokens=500)
+resp = llmshim.chat("claude-sonnet-5", "Hello!", max_tokens=500)
 print(resp["message"]["content"])
 ```
 
 **Streaming:**
 
 ```python
-for event in llmshim.stream("claude-sonnet-4-6", "Write a poem"):
+for event in llmshim.stream("claude-sonnet-5", "Write a poem"):
     if event["type"] == "content":
         print(event["text"], end="", flush=True)
     elif event["type"] == "usage":
@@ -225,13 +225,13 @@ for event in llmshim.stream("claude-sonnet-4-6", "Write a poem"):
 ```python
 messages = [{"role": "user", "content": "What is a closure?"}]
 
-r1 = llmshim.chat("claude-sonnet-4-6", messages, max_tokens=500)
+r1 = llmshim.chat("claude-sonnet-5", messages, max_tokens=500)
 print(f"Claude: {r1['message']['content']}")
 
 messages.append({"role": "assistant", "content": r1["message"]["content"]})
 messages.append({"role": "user", "content": "Now explain it differently."})
 
-r2 = llmshim.chat("gpt-5.5", messages, max_tokens=500)
+r2 = llmshim.chat("gpt-5.6-sol", messages, max_tokens=500)
 print(f"GPT: {r2['message']['content']}")
 ```
 
@@ -251,7 +251,7 @@ tools = [{
     },
 }]
 
-resp = llmshim.chat("claude-sonnet-4-6", "Weather in Tokyo?", max_tokens=500, tools=tools)
+resp = llmshim.chat("claude-sonnet-5", "Weather in Tokyo?", max_tokens=500, tools=tools)
 for tc in resp["message"].get("tool_calls", []):
     print(f"{tc['function']['name']}({tc['function']['arguments']})")
 ```
@@ -260,7 +260,7 @@ for tc in resp["message"].get("tool_calls", []):
 
 ```python
 resp = llmshim.chat(
-    "claude-sonnet-4-6",
+    "claude-sonnet-5",
     "Solve: x^2 - 5x + 6 = 0",
     max_tokens=4000,
     reasoning_effort="high",   # none | low | medium | high | xhigh | max
@@ -270,16 +270,16 @@ print(resp["reasoning"])          # thinking content
 print(resp["message"]["content"]) # answer
 ```
 
-llmshim maps these to each provider's native control (OpenAI `reasoning.effort`/`mode`, Anthropic adaptive thinking, Gemini `thinkingLevel`, xAI `reasoning.effort`), clamping to the nearest tier the target model actually supports — so `reasoning_effort="max"` works everywhere even though only some models have a native `max`. Full verified mapping tables: [`docs/reasoning.md`](docs/reasoning.md). Prefer a provider's exact native dialect? Pass it via `provider_config` (`x-openai.reasoning`, `x-anthropic.thinking`, `x-gemini.thinkingConfig`) and llmshim won't touch it.
+llmshim maps these to each provider's native control (OpenAI `reasoning.effort`/`mode`, Anthropic adaptive thinking, Gemini `thinkingLevel`, xAI `reasoning.effort`), clamping to the nearest tier the target model actually supports — so `reasoning_effort="max"` works everywhere even though only some models have a native `max`. Full verified mapping tables: [the reasoning guide](https://sanjay920.github.io/llmshim/guides/reasoning.html). Prefer a provider's exact native dialect? Pass it via `provider_config` (`x-openai.reasoning`, `x-anthropic.thinking`, `x-gemini.thinkingConfig`) and llmshim won't touch it.
 
 **Fallback chains** — automatic failover across providers:
 
 ```python
 resp = llmshim.chat(
-    "anthropic/claude-sonnet-4-6",
+    "anthropic/claude-sonnet-5",
     "Hello",
     max_tokens=100,
-    fallback=["openai/gpt-5.5", "gemini/gemini-3.5-flash"],
+    fallback=["openai/gpt-5.6-sol", "gemini/gemini-3.5-flash"],
 )
 ```
 
@@ -298,7 +298,7 @@ import { Client } from "llmshim";
 
 const client = new Client(); // no baseUrl -> auto-starts the bundled proxy
 const res = await client.chat({
-  model: "anthropic/claude-sonnet-4-6",
+  model: "anthropic/claude-sonnet-5",
   messages: [{ role: "user", content: "Hello!" }],
 });
 console.log(res.message.content);
@@ -315,7 +315,7 @@ go get github.com/sanjay920/llmshim/clients/go
 ```go
 client := llmshim.New() // defaults to http://localhost:3000
 resp, err := client.Chat(ctx, llmshim.ChatRequest{
-    Model:    "anthropic/claude-sonnet-4-6",
+    Model:    "anthropic/claude-sonnet-5",
     Messages: []llmshim.Message{{Role: "user", Content: "Hello!"}},
 })
 ```
@@ -331,7 +331,7 @@ gem install llmshim
 ```ruby
 require "llmshim"
 
-resp = Llmshim.chat(model: "anthropic/claude-sonnet-4-6", messages: [{role: "user", content: "Hello!"}])
+resp = Llmshim.chat(model: "anthropic/claude-sonnet-5", messages: [{role: "user", content: "Hello!"}])
 puts resp.message.content
 ```
 
@@ -345,8 +345,8 @@ 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-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-3.1-flash-lite-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`, `grok-4-1-fast-reasoning`, `grok-4-1-fast-non-reasoning` | No (hidden) |
+| **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) |
 
 Use a bare model name (auto-detected by prefix) or an explicit `provider/model` string.
 
@@ -366,7 +366,7 @@ No canonical struct. Requests flow as `serde_json::Value` — each provider maps
 
 ```
 llmshim::completion(router, request)
-  → router.resolve("anthropic/claude-sonnet-4-6")
+  → router.resolve("anthropic/claude-sonnet-5")
   → provider.transform_request(model, &value)
   → HTTP
   → provider.transform_response(model, body)

llmshim-0.2.1/docs/.gitignore

@@ -0,0 +1 @@
+book/

llmshim-0.2.1/docs/book.toml

@@ -0,0 +1,22 @@
+[book]
+title = "llmshim"
+authors = ["llmshim contributors"]
+language = "en"
+multilingual = false
+src = "src"
+
+[build]
+build-dir = "book"
+create-missing = false
+
+[preprocessor.mermaid]
+command = "mdbook-mermaid"
+
+[output.html]
+default-theme = "light"
+preferred-dark-theme = "navy"
+git-repository-url = "https://github.com/sanjay920/llmshim"
+edit-url-template = "https://github.com/sanjay920/llmshim/edit/docs/concepts-site/docs/{path}"
+site-url = "/llmshim/"
+additional-js = ["mermaid.min.js", "mermaid-init.js"]
+

llmshim-0.2.1/docs/mermaid-init.js

@@ -0,0 +1,39 @@
+// This Source Code Form is subject to the terms of the Mozilla Public
+// License, v. 2.0. If a copy of the MPL was not distributed with this
+// file, You can obtain one at https://mozilla.org/MPL/2.0/.
+
+(() => {
+    const darkThemes = ['ayu', 'navy', 'coal'];
+    const lightThemes = ['light', 'rust'];
+
+    const classList = document.getElementsByTagName('html')[0].classList;
+
+    let lastThemeWasLight = true;
+    for (const cssClass of classList) {
+        if (darkThemes.includes(cssClass)) {
+            lastThemeWasLight = false;
+            break;
+        }
+    }
+
+    const theme = lastThemeWasLight ? 'default' : 'dark';
+    mermaid.initialize({ startOnLoad: true, theme });
+
+    // Simplest way to make mermaid re-render the diagrams in the new theme is via refreshing the page
+
+    for (const darkTheme of darkThemes) {
+        document.getElementById(darkTheme).addEventListener('click', () => {
+            if (lastThemeWasLight) {
+                window.location.reload();
+            }
+        });
+    }
+
+    for (const lightTheme of lightThemes) {
+        document.getElementById(lightTheme).addEventListener('click', () => {
+            if (!lastThemeWasLight) {
+                window.location.reload();
+            }
+        });
+    }
+})();