sno-llmix 2.0.0__tar.gz

sno_llmix-2.0.0/LICENSE

@@ -0,0 +1,176 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

sno_llmix-2.0.0/PKG-INFO

@@ -0,0 +1,305 @@
+Metadata-Version: 2.4
+Name: sno-llmix
+Version: 2.0.0
+Summary: Cross-runtime LLM orchestration for Python, TypeScript, and Rust with L2 caching, retries, key rotation, and config-driven runtime control
+Requires-Python: >=3.14
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: openai>=2.0.0
+Requires-Dist: anthropic>=0.40.0
+Requires-Dist: google-genai<3,>=1.18.0
+Requires-Dist: httpx[http2]<0.29,>=0.28.1
+Requires-Dist: cachetools<8,>=5.5.0
+Requires-Dist: pydantic<3,>=2
+Requires-Dist: snoai-mda-config<2,>=1.0.0
+Requires-Dist: json-repair<1,>=0.58.0
+Requires-Dist: openrouter>=0.9.1
+Provides-Extra: redis
+Requires-Dist: redis<8,>=6.4.0; extra == "redis"
+Provides-Extra: dev
+Requires-Dist: pyright>=1.1.0; extra == "dev"
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.24; extra == "dev"
+Dynamic: license-file
+
+# LLMix
+
+[![npm version](https://img.shields.io/npm/v/@snoai/llmix.svg)](https://www.npmjs.com/package/@snoai/llmix)
+[![PyPI](https://img.shields.io/pypi/v/sno-llmix.svg)](https://pypi.org/project/sno-llmix/)
+[![Python 3.14+](https://img.shields.io/badge/python-3.14%2B-blue.svg)](https://www.python.org/downloads/)
+[![TypeScript 5.0+](https://img.shields.io/badge/TypeScript-5.0%2B-blue.svg)](https://www.typescriptlang.org/)
+[![Rust 1.83+](https://img.shields.io/badge/rust-1.83%2B-orange.svg)](https://www.rust-lang.org/)
+[![License: Apache--2.0](https://img.shields.io/badge/License-Apache--2.0-green.svg)](LICENSE)
+
+> **Config-driven harness around your LLM SDK.**
+> Swap models by editing MDA presets. Keep the SDK you already use.
+
+LLMix sits **above** your existing LLM client — `openai`, `anthropic`, AI SDK, LiteLLM, anything with a callable signature — and wraps it with the production primitives you'd otherwise rebuild from scratch: an MDA-driven config layer, a two-tier response cache, a circuit breaker, key-pool rotation, and singleflight deduplication.
+
+Provider, model, and parameters can live in a `.mda` preset. Edit the preset, publish or reload config, and get a different model at runtime. **No redeploy.**
+
+---
+
+## At a Glance
+
+![LLMix wraps your existing LLM SDK stack with MDA config, cache, resilience, and key-pool primitives.](docs/images/llmix-wraps-sdk.png)
+
+**Works with:** AI SDK v6 · `openai` (Py/JS) · `anthropic` · `google-genai` · LiteLLM · any async callable that returns your model's response.
+
+---
+
+## Three Things It Does
+
+**Config-driven model swap.** Provider, model, and params are *data*, not code. Drop in a new MDA preset, the next call can route to a different provider. Built for agent harnesses that reshape behavior via config, not redeploys.
+
+**Production resilience, no extra code.** Two-tier cache (L1 memory + L2 Redis), circuit breaker, key-pool rotation with auto-eviction of dead keys, single flight dedup, adaptive concurrency, retries that honor `Retry-After`. Composable with whatever SDK you already ship.
+
+**Runtime parity.** Python, TypeScript, and Rust share byte-identical cache keys and retry semantics. Config authoring now uses MDA Source Mode across all three runtimes. (`llmix-rs` is currently beta — see [`rust/llmix-rs/README.md`](rust/llmix-rs/README.md).)
+
+---
+
+## Quick Start
+
+### Python
+
+```bash
+pip install sno-llmix
+```
+
+```python
+from llmix import (
+    CallInput, CallPipeline, KeyPool, PipelineConfig,
+    TwoTierCache, openai_dispatch,
+)
+
+pipeline = CallPipeline(PipelineConfig(
+    dispatch=openai_dispatch(),
+    response_cache=TwoTierCache("memory"),
+))
+pipeline.set_key_pool("openai", KeyPool(["sk-..."]))
+
+response = await pipeline.call(CallInput(
+    config={
+        "provider": "openai",
+        "model": "gpt-4.1-mini",
+        "common": {"temperature": 0.7, "max_output_tokens": 1024},
+        "caching": {"strategy": "memory"},
+    },
+    messages=[{"role": "user", "content": "Summarize this article..."}],
+))
+
+print(response.content, response.cache_hit)
+```
+
+### TypeScript
+
+```typescript
+import { CallPipeline, KeyPool, TwoTierCache, openaiDispatch } from "@snoai/llmix";
+
+const pipeline = new CallPipeline({
+  dispatch: openaiDispatch(),
+  responseCache: new TwoTierCache("memory"),
+});
+pipeline.setKeyPool("openai", new KeyPool(["sk-..."]));
+
+const response = await pipeline.call({
+  config: {
+    provider: "openai",
+    model: "gpt-4.1-mini",
+    common: { temperature: 0.2, maxOutputTokens: 2048 },
+    caching: { strategy: "memory" },
+  },
+  messages: [{ role: "user", content: "Extract entities from this text." }],
+});
+
+console.log(response.content, response.usage);
+```
+
+### Rust
+
+```rust
+use llmix_rs::{
+    CallInput, CallPipeline, DispatchContext, KeyPool, LlmUsage,
+    PipelineConfig, ProviderResult,
+};
+use serde_json::json;
+
+#[tokio::main(flavor = "current_thread")]
+async fn main() -> Result<(), Box<dyn std::error::Error>> {
+    let pipeline = CallPipeline::new(PipelineConfig::new(|ctx: DispatchContext| async move {
+        Ok(ProviderResult {
+            content: format!("echo: {}", ctx.messages.last().and_then(|m| m.get("content")).and_then(|v| v.as_str()).unwrap_or("")),
+            model: ctx.model,
+            usage: LlmUsage { input_tokens: 1, output_tokens: 2, total_tokens: 3 },
+            headers: None,
+            tool_calls: None,
+        })
+    }))?;
+    pipeline.set_key_pool("openai", KeyPool::new(vec!["sk-...".into()])?);
+
+    let response = pipeline.call(CallInput {
+        config: json!({"provider": "openai", "model": "gpt-4o-mini"}),
+        messages: vec![json!({"role": "user", "content": "Extract entities."})],
+        singleflight_key: None,
+    }).await;
+
+    println!("{}", response.content);
+    pipeline.close().await;
+    Ok(())
+}
+```
+
+### MDA Presets
+
+![LLMix turns editable MDA presets into immutable registry snapshots that Python, TypeScript, and Rust runtimes can read consistently.](docs/images/llmix-mda-config.png)
+
+```mda
+---
+name: extraction
+description: Entity extraction preset.
+metadata:
+  snoai-llmix:
+    common:
+      provider: openai
+      model: gpt-4.1-mini
+      maxOutputTokens: 2048
+      temperature: 0.2
+    caching:
+      strategy: redis-or-memory
+    providerOptions:
+      openai:
+        reasoningEffort: medium
+---
+# extraction
+
+Runtime settings plus human-readable operating notes live together.
+```
+
+---
+
+## Inside Every Call
+
+![LLMix request pipeline from config and cache lookup through circuit breaker, singleflight, key-pool rotation, retry loop, dispatch, and telemetry.](docs/images/llmix-call-pipeline.png)
+
+| Concern             | What LLMix does                                                                    |
+|---------------------|------------------------------------------------------------------------------------|
+| **Cache**           | L1 memory + optional Redis L2; cross-language byte-identical keys                  |
+| **Concurrency**     | AIMD adaptive semaphore with rate-limit feedback                                   |
+| **Dedup**           | Singleflight collapses identical concurrent calls into one upstream request        |
+| **Failures**        | Retry with jittered exponential backoff; `Retry-After` honored                     |
+| **Provider health** | Circuit breaker scoped to `(provider, endpoint)`                                   |
+| **API keys**        | Round-robin pools; dead-key eviction on `401/403`; fast rotation on `429`          |
+| **Request shaping** | Provider-specific kwargs transforms and capability filtering                       |
+| **Output**          | Optional `<think>` token extraction; normalized response objects                   |
+
+---
+
+## Tested Against Real Providers
+
+Every dispatcher below has a real-HTTP integration suite under `tests/integration/` — no mocks, no recorded fixtures.
+
+| Provider    | Dispatcher                                  | Primary model under test         |
+|-------------|---------------------------------------------|----------------------------------|
+| OpenAI      | `openai_dispatch` / `openaiDispatch`        | `gpt-4o-mini`, `o4-mini`         |
+| Anthropic   | `anthropic_dispatch` / `anthropicDispatch`  | `claude-haiku-4-5-20251001`      |
+| Gemini      | `gemini_dispatch` / `geminiDispatch`        | `gemini-2.5-flash`               |
+| OpenRouter  | `openrouter_dispatch` / `openrouterDispatch`| `deepseek/deepseek-v4-flash`     |
+| DeepInfra   | `deepinfra_dispatch` / `deepinfraDispatch`  | `Qwen/Qwen3-32B`                 |
+| Novita      | `novita_dispatch` / `novitaDispatch`        | `qwen/qwen3.5-27b`               |
+| Together    | `together_dispatch` / `togetherDispatch`    | `Qwen/Qwen2.5-7B-Instruct-Turbo` |
+| Sno GPU     | `sno_gpu_dispatch` / `snoGpuDispatch`       | `qwen3.6-27b-extract`            |
+
+OpenRouter, DeepInfra, Novita, and Together are OpenAI-compatible — their dispatchers reuse the OpenAI client / `@ai-sdk/openai` with a provider-specific `base_url`. TypeScript dispatchers use AI SDK v6 where the provider supports it.
+
+Cross-cutting suites (`test_e2e_cache.py`, `_concurrency`, `_parity`, `_redis`, `_resilience`, `_security`, `_thinking`) exercise the pipeline itself across every provider.
+
+---
+
+## Production Config: the Registry
+
+Services that need atomic config updates use the **LLMix Config Registry** — a publishing layer that turns editable `.mda` presets into immutable, content-addressed snapshots.
+
+```text
+config/llm/
+  authoring/         ← editable .mda presets
+  snapshots/<rev>/   ← immutable, content-addressed
+  current.json       ← the only live switch
+```
+
+Runtime services open the manager once at startup; reads come from resolved JSON snapshot files, not mutable authoring MDA.
+
+```python
+from llmix import ConfigRegistryManager, ConfigRegistryPublisher, resolve_config_dir
+
+root = resolve_config_dir().config_dir
+ConfigRegistryPublisher(root).publish()
+
+manager = ConfigRegistryManager.open(root)
+config = manager.get_preset("search", "summary")
+```
+
+```typescript
+import { ConfigRegistryManager, ConfigRegistryPublisher, resolveConfigDir } from "@snoai/llmix";
+
+const { configDir } = resolveConfigDir();
+await new ConfigRegistryPublisher(configDir).publish();
+
+const manager = await ConfigRegistryManager.open(configDir);
+const config = await manager.getPreset("search", "summary");
+```
+
+Managers expose the active revision and reload-health metadata so service code can surface which revision is live.
+
+TypeScript authoring tools can use `loadMdaConfig` / `loadMdaConfigPreset`; Python authoring tools can use `load_mda_config` / `load_mda_config_preset`; Rust authoring tools can use `load_config` / `load_config_preset`, which now hard-require `.mda` files. None of these direct loaders are the production hot path.
+
+---
+
+## What This Is *Not*
+
+- **Not a streaming library.** Streaming is your SDK's job. LLMix handles calls, not chunks.
+- **Not a provider replacement.** It wraps your client, it doesn't replace it.
+- **Not a cross-provider router** in the LiteLLM sense. One call, one provider — the one your config names.
+
+---
+
+## Environment Variables
+
+| Variable                          | Purpose                                              |
+|-----------------------------------|------------------------------------------------------|
+| `OPENAI_API_KEY` / `OPENAI_KEYS`  | Single key or comma-separated OpenAI key pool        |
+| `ANTHROPIC_API_KEY`               | Anthropic auth                                       |
+| `GEMINI_API_KEY`                  | Google / Gemini auth                                 |
+| `OPENROUTER_API_KEY`              | OpenRouter auth                                      |
+| `SNO_LLM_API_KEY`                 | Sno GPU auth                                         |
+| `GPU_BASE_URL`                    | Sno GPU base URL                                     |
+| `REDIS_URL`                       | Redis L2 cache                                       |
+| `LLMIX_STATE_DIR`                 | Lock files, batch metadata, kill switch state        |
+
+---
+
+## Development
+
+```bash
+# TypeScript
+bun install && bun test
+bunx tsc -p tsconfig.check.json
+
+# Python
+uv sync && uv run pytest tests/python/
+uv run pyright
+
+# Rust
+cargo test --manifest-path rust/llmix-rs/Cargo.toml
+cargo clippy --manifest-path rust/llmix-rs/Cargo.toml -- -D warnings
+```
+
+---
+
+## License
+
+[Apache-2.0](LICENSE)
+
+## Related
+
+- [AI SDK](https://ai-sdk.dev/)
+- [Promptix](https://github.com/sno-ai/promptix)