llx 0.1.1__tar.gz

llx-0.1.1/LICENSE

@@ -0,0 +1,15 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

llx-0.1.1/PKG-INFO

@@ -0,0 +1,247 @@
+Metadata-Version: 2.4
+Name: llx
+Version: 0.1.1
+Summary: Intelligent LLM model router driven by real code metrics — successor to preLLM
+Author-email: Tom Sapletta <tom@sapletta.com>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/wronai/llx
+Project-URL: Repository, https://github.com/wronai/llx
+Keywords: llm,code-analysis,model-routing,litellm,code2llm,developer-tools
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Quality Assurance
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: typer>=0.12
+Requires-Dist: rich>=13.0
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pydantic-settings>=2.0
+Requires-Dist: tomli>=2.0; python_version < "3.11"
+Requires-Dist: httpx>=0.27
+Requires-Dist: pyyaml>=6.0
+Provides-Extra: litellm
+Requires-Dist: litellm>=1.40; extra == "litellm"
+Provides-Extra: code2llm
+Requires-Dist: code2llm>=0.9; extra == "code2llm"
+Provides-Extra: redup
+Requires-Dist: redup>=0.4; extra == "redup"
+Provides-Extra: vallm
+Requires-Dist: vallm>=0.1; extra == "vallm"
+Provides-Extra: ollama
+Requires-Dist: ollama>=0.3; extra == "ollama"
+Provides-Extra: all
+Requires-Dist: litellm>=1.40; extra == "all"
+Requires-Dist: code2llm>=0.9; extra == "all"
+Requires-Dist: redup>=0.4; extra == "all"
+Requires-Dist: vallm>=0.1; extra == "all"
+Requires-Dist: ollama>=0.3; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-cov>=5.0; extra == "dev"
+Requires-Dist: ruff>=0.5; extra == "dev"
+Requires-Dist: mypy>=1.10; extra == "dev"
+Dynamic: license-file
+
+# llx
+
+**Intelligent LLM model router driven by real code metrics.**
+
+[![PyPI](https://img.shields.io/pypi/v/llx)](https://pypi.org/project/llx/)
+[![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://python.org)
+
+**Successor to [preLLM](https://github.com/wronai/prellm)** — rebuilt with modular architecture, no god modules, and metric-driven routing.
+
+llx analyzes your codebase with **code2llm**, **redup**, and **vallm**, then selects the optimal LLM model based on actual project metrics — file count, complexity, coupling, duplication — not abstract scores.
+
+**Principle**: larger + more coupled + more complex → stronger (and more expensive) model.
+
+## Why llx? (Lessons from preLLM)
+
+preLLM proved the concept but had architectural issues that llx resolves:
+
+| Problem in preLLM | llx Solution |
+|---|---|
+| `cli.py`: 999 lines, CC=30 (`main`), CC=27 (`query`) | CLI split into `app.py` + `formatters.py`, max CC ≤ 8 |
+| `core.py`: 893 lines god module | Config, analysis, routing in separate modules (≤250L each) |
+| `trace.py`: 509 lines, CC=28 (`to_stdout`) | Output formatting as dedicated functions |
+| Hardcoded model selection | Metric-driven thresholds from code2llm .toon data |
+| No duplication/validation awareness | Integrates redup + vallm for richer metrics |
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                    IDE / Agent Layer                         │
+│  Roo Code │ Cline │ Continue.dev │ Aider │ Claude Code      │
+│  (point at localhost:4000 as OpenAI-compatible API)          │
+└─────────────────┬───────────────────────────────────────────┘
+                  │
+┌─────────────────▼───────────────────────────────────────────┐
+│              LiteLLM Proxy (localhost:4000)                  │
+│  ┌──────────┐  ┌──────────────┐  ┌────────────────────┐     │
+│  │ Router   │  │ Semantic     │  │ Cost Tracking      │     │
+│  │ (metrics)│  │ Cache (Redis)│  │ + Budget Limits    │     │
+│  └────┬─────┘  └──────────────┘  └────────────────────┘     │
+└───────┼─────────────────────────────────────────────────────┘
+        │
+   ┌────┼────────────────────────────────────────┐
+   │    │           Model Tiers                   │
+   │    ├── premium:  Claude Opus 4               │
+   │    ├── balanced: Claude Sonnet 4 / GPT-5     │
+   │    ├── cheap:    Claude Haiku 4.5            │
+   │    ├── free:     Gemini 2.5 Pro              │
+   │    ├── openrouter: 300+ models (fallback)    │
+   │    └── local:    Ollama (Qwen2.5-Coder)      │
+   └──────────────────────────────────────────────┘
+        │
+┌───────▼─────────────────────────────────────────────────────┐
+│            Code Analysis Pipeline                           │
+│  code2llm → redup → vallm → llx                            │
+│  (metrics → duplication → validation → model selection)      │
+└─────────────────────────────────────────────────────────────┘
+```
+
+## Installation
+
+```bash
+pip install llx
+
+# With integrations
+pip install llx[all]        # Everything
+pip install llx[litellm]    # LiteLLM proxy
+pip install llx[code2llm]   # Code analysis
+pip install llx[redup]      # Duplication detection
+pip install llx[vallm]      # Code validation
+```
+
+## Quick Start
+
+```bash
+# Analyze project and get model recommendation
+llx analyze ./my-project
+
+# Quick model selection
+llx select .
+
+# With task hint
+llx select . --task refactor
+
+# Point to pre-existing .toon files
+llx analyze . --toon-dir ./analysis/
+
+# JSON output for CI/CD
+llx analyze . --json
+
+# Chat with auto-selected model
+llx chat . --prompt "Refactor the god modules"
+
+# Force local model
+llx select . --local
+```
+
+## Model Selection Logic
+
+| Metric | Premium (≥) | Balanced (≥) | Cheap (≥) | Free |
+|--------|-------------|--------------|-----------|------|
+| Files | 50 | 10 | 3 | <3 |
+| Lines | 20,000 | 5,000 | 500 | <500 |
+| Avg CC | 6.0 | 4.0 | 2.0 | <2.0 |
+| Max fan-out | 30 | 10 | — | — |
+| Max CC | 25 | 15 | — | — |
+| Dup groups | 15 | 5 | — | — |
+| Dep cycles | any | — | — | — |
+
+## Real-World Selection Examples
+
+| Project | Files | Lines | CC̄ | Max CC | Fan-out | Tier |
+|---------|-------|-------|-----|--------|---------|------|
+| Single script | 1 | 80 | 2.0 | 4 | 0 | **free** |
+| Small CLI | 5 | 600 | 3.0 | 8 | 3 | **cheap** |
+| **preLLM** | **31** | **8,900** | **5.0** | **28** | **30** | **premium** |
+| vallm | 56 | 8,604 | 3.5 | 42 | — | **balanced** |
+| code2llm | 113 | 21,128 | 4.6 | 65 | 45 | **premium** |
+| Monorepo | 500+ | 100K+ | 5.0+ | 30+ | 50+ | **premium** |
+
+## LiteLLM Proxy
+
+```bash
+llx proxy config     # Generate litellm_config.yaml
+llx proxy start      # Start proxy on :4000
+llx proxy status     # Check if running
+```
+
+Configure IDE tools to point at `http://localhost:4000`:
+
+| Tool | Config |
+|------|--------|
+| Roo Code / Cline | `"apiBase": "http://localhost:4000/v1"` |
+| Continue.dev | `"apiBase": "http://localhost:4000/v1"` |
+| Aider | `OPENAI_API_BASE=http://localhost:4000` |
+| Claude Code | `ANTHROPIC_BASE_URL=http://localhost:4000` |
+| Cursor / Windsurf | OpenAI-compatible endpoint |
+
+## Configuration
+
+```bash
+llx init  # Creates llx.toml with defaults
+```
+
+Environment variables: `LLX_LITELLM_URL`, `LLX_DEFAULT_TIER`, `LLX_PROXY_PORT`, `LLX_VERBOSE`.
+
+## Python API
+
+```python
+from llx import analyze_project, select_model, LlxConfig
+
+metrics = analyze_project("./my-project")
+result = select_model(metrics)
+print(result.model_id)   # "claude-opus-4-20250514"
+print(result.explain())   # Human-readable reasoning
+```
+
+## Integration with wronai Toolchain
+
+| Tool | Role | llx Uses |
+|------|------|----------|
+| [code2llm](https://github.com/wronai/code2llm) | Static analysis | CC, fan-out, cycles, hotspots |
+| [redup](https://github.com/semcod/redup) | Duplication detection | Groups, recoverable lines |
+| [vallm](https://github.com/semcod/vallm) | Code validation | Pass rate, issue count |
+| **llx** | **Model routing** | **Consumes all above** |
+
+## Package Structure
+
+```
+llx/
+├── __init__.py              # Public API (30L)
+├── config.py                # Config loader (160L)
+├── analysis/
+│   ├── collector.py         # Metrics from .toon, filesystem (280L)
+│   └── runner.py            # Tool invocation (80L)
+├── routing/
+│   ├── selector.py          # Metric → tier mapping (200L)
+│   └── client.py            # LiteLLM client wrapper (150L)
+├── integrations/
+│   ├── context_builder.py   # .toon → LLM context (130L)
+│   └── proxy.py             # LiteLLM proxy management (100L)
+└── cli/
+    ├── app.py               # Commands (230L, max CC ≤ 8)
+    └── formatters.py        # Output formatting (120L)
+```
+
+**Total**: ~1,280 lines across 10 modules. No file exceeds 300L. Max CC ≤ 8.
+
+Compare: preLLM had 8,900 lines with 3 god modules (cli.py: 999L, core.py: 893L, trace.py: 509L).
+
+## License
+
+Apache License 2.0 - see [LICENSE](LICENSE) for details.
+
+## Author
+
+Created by **Tom Sapletta** - [tom@sapletta.com](mailto:tom@sapletta.com)

llx-0.1.1/README.md

@@ -0,0 +1,198 @@
+# llx
+
+**Intelligent LLM model router driven by real code metrics.**
+
+[![PyPI](https://img.shields.io/pypi/v/llx)](https://pypi.org/project/llx/)
+[![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://python.org)
+
+**Successor to [preLLM](https://github.com/wronai/prellm)** — rebuilt with modular architecture, no god modules, and metric-driven routing.
+
+llx analyzes your codebase with **code2llm**, **redup**, and **vallm**, then selects the optimal LLM model based on actual project metrics — file count, complexity, coupling, duplication — not abstract scores.
+
+**Principle**: larger + more coupled + more complex → stronger (and more expensive) model.
+
+## Why llx? (Lessons from preLLM)
+
+preLLM proved the concept but had architectural issues that llx resolves:
+
+| Problem in preLLM | llx Solution |
+|---|---|
+| `cli.py`: 999 lines, CC=30 (`main`), CC=27 (`query`) | CLI split into `app.py` + `formatters.py`, max CC ≤ 8 |
+| `core.py`: 893 lines god module | Config, analysis, routing in separate modules (≤250L each) |
+| `trace.py`: 509 lines, CC=28 (`to_stdout`) | Output formatting as dedicated functions |
+| Hardcoded model selection | Metric-driven thresholds from code2llm .toon data |
+| No duplication/validation awareness | Integrates redup + vallm for richer metrics |
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                    IDE / Agent Layer                         │
+│  Roo Code │ Cline │ Continue.dev │ Aider │ Claude Code      │
+│  (point at localhost:4000 as OpenAI-compatible API)          │
+└─────────────────┬───────────────────────────────────────────┘
+                  │
+┌─────────────────▼───────────────────────────────────────────┐
+│              LiteLLM Proxy (localhost:4000)                  │
+│  ┌──────────┐  ┌──────────────┐  ┌────────────────────┐     │
+│  │ Router   │  │ Semantic     │  │ Cost Tracking      │     │
+│  │ (metrics)│  │ Cache (Redis)│  │ + Budget Limits    │     │
+│  └────┬─────┘  └──────────────┘  └────────────────────┘     │
+└───────┼─────────────────────────────────────────────────────┘
+        │
+   ┌────┼────────────────────────────────────────┐
+   │    │           Model Tiers                   │
+   │    ├── premium:  Claude Opus 4               │
+   │    ├── balanced: Claude Sonnet 4 / GPT-5     │
+   │    ├── cheap:    Claude Haiku 4.5            │
+   │    ├── free:     Gemini 2.5 Pro              │
+   │    ├── openrouter: 300+ models (fallback)    │
+   │    └── local:    Ollama (Qwen2.5-Coder)      │
+   └──────────────────────────────────────────────┘
+        │
+┌───────▼─────────────────────────────────────────────────────┐
+│            Code Analysis Pipeline                           │
+│  code2llm → redup → vallm → llx                            │
+│  (metrics → duplication → validation → model selection)      │
+└─────────────────────────────────────────────────────────────┘
+```
+
+## Installation
+
+```bash
+pip install llx
+
+# With integrations
+pip install llx[all]        # Everything
+pip install llx[litellm]    # LiteLLM proxy
+pip install llx[code2llm]   # Code analysis
+pip install llx[redup]      # Duplication detection
+pip install llx[vallm]      # Code validation
+```
+
+## Quick Start
+
+```bash
+# Analyze project and get model recommendation
+llx analyze ./my-project
+
+# Quick model selection
+llx select .
+
+# With task hint
+llx select . --task refactor
+
+# Point to pre-existing .toon files
+llx analyze . --toon-dir ./analysis/
+
+# JSON output for CI/CD
+llx analyze . --json
+
+# Chat with auto-selected model
+llx chat . --prompt "Refactor the god modules"
+
+# Force local model
+llx select . --local
+```
+
+## Model Selection Logic
+
+| Metric | Premium (≥) | Balanced (≥) | Cheap (≥) | Free |
+|--------|-------------|--------------|-----------|------|
+| Files | 50 | 10 | 3 | <3 |
+| Lines | 20,000 | 5,000 | 500 | <500 |
+| Avg CC | 6.0 | 4.0 | 2.0 | <2.0 |
+| Max fan-out | 30 | 10 | — | — |
+| Max CC | 25 | 15 | — | — |
+| Dup groups | 15 | 5 | — | — |
+| Dep cycles | any | — | — | — |
+
+## Real-World Selection Examples
+
+| Project | Files | Lines | CC̄ | Max CC | Fan-out | Tier |
+|---------|-------|-------|-----|--------|---------|------|
+| Single script | 1 | 80 | 2.0 | 4 | 0 | **free** |
+| Small CLI | 5 | 600 | 3.0 | 8 | 3 | **cheap** |
+| **preLLM** | **31** | **8,900** | **5.0** | **28** | **30** | **premium** |
+| vallm | 56 | 8,604 | 3.5 | 42 | — | **balanced** |
+| code2llm | 113 | 21,128 | 4.6 | 65 | 45 | **premium** |
+| Monorepo | 500+ | 100K+ | 5.0+ | 30+ | 50+ | **premium** |
+
+## LiteLLM Proxy
+
+```bash
+llx proxy config     # Generate litellm_config.yaml
+llx proxy start      # Start proxy on :4000
+llx proxy status     # Check if running
+```
+
+Configure IDE tools to point at `http://localhost:4000`:
+
+| Tool | Config |
+|------|--------|
+| Roo Code / Cline | `"apiBase": "http://localhost:4000/v1"` |
+| Continue.dev | `"apiBase": "http://localhost:4000/v1"` |
+| Aider | `OPENAI_API_BASE=http://localhost:4000` |
+| Claude Code | `ANTHROPIC_BASE_URL=http://localhost:4000` |
+| Cursor / Windsurf | OpenAI-compatible endpoint |
+
+## Configuration
+
+```bash
+llx init  # Creates llx.toml with defaults
+```
+
+Environment variables: `LLX_LITELLM_URL`, `LLX_DEFAULT_TIER`, `LLX_PROXY_PORT`, `LLX_VERBOSE`.
+
+## Python API
+
+```python
+from llx import analyze_project, select_model, LlxConfig
+
+metrics = analyze_project("./my-project")
+result = select_model(metrics)
+print(result.model_id)   # "claude-opus-4-20250514"
+print(result.explain())   # Human-readable reasoning
+```
+
+## Integration with wronai Toolchain
+
+| Tool | Role | llx Uses |
+|------|------|----------|
+| [code2llm](https://github.com/wronai/code2llm) | Static analysis | CC, fan-out, cycles, hotspots |
+| [redup](https://github.com/semcod/redup) | Duplication detection | Groups, recoverable lines |
+| [vallm](https://github.com/semcod/vallm) | Code validation | Pass rate, issue count |
+| **llx** | **Model routing** | **Consumes all above** |
+
+## Package Structure
+
+```
+llx/
+├── __init__.py              # Public API (30L)
+├── config.py                # Config loader (160L)
+├── analysis/
+│   ├── collector.py         # Metrics from .toon, filesystem (280L)
+│   └── runner.py            # Tool invocation (80L)
+├── routing/
+│   ├── selector.py          # Metric → tier mapping (200L)
+│   └── client.py            # LiteLLM client wrapper (150L)
+├── integrations/
+│   ├── context_builder.py   # .toon → LLM context (130L)
+│   └── proxy.py             # LiteLLM proxy management (100L)
+└── cli/
+    ├── app.py               # Commands (230L, max CC ≤ 8)
+    └── formatters.py        # Output formatting (120L)
+```
+
+**Total**: ~1,280 lines across 10 modules. No file exceeds 300L. Max CC ≤ 8.
+
+Compare: preLLM had 8,900 lines with 3 god modules (cli.py: 999L, core.py: 893L, trace.py: 509L).
+
+## License
+
+Apache License 2.0 - see [LICENSE](LICENSE) for details.
+
+## Author
+
+Created by **Tom Sapletta** - [tom@sapletta.com](mailto:tom@sapletta.com)

llx-0.1.1/llx/__init__.py

@@ -0,0 +1,29 @@
+"""llx — Intelligent LLM model router driven by real code metrics.
+
+Successor to preLLM. Integrates code2llm (analysis), redup (duplication),
+vallm (validation) with LiteLLM for metric-aware model selection.
+
+Key difference from preLLM: modular architecture (no god modules),
+metric-driven routing instead of hardcoded model selection,
+and clean separation of analysis/routing/client layers.
+
+Usage:
+    from llx import analyze_project, select_model, LlxConfig
+
+    metrics = analyze_project("./my-repo")
+    model = select_model(metrics)
+"""
+
+__version__ = "0.1.1"
+
+from llx.analysis.collector import ProjectMetrics, analyze_project
+from llx.routing.selector import ModelTier, select_model
+from llx.config import LlxConfig
+
+__all__ = [
+    "analyze_project",
+    "select_model",
+    "ProjectMetrics",
+    "ModelTier",
+    "LlxConfig",
+]

llx-0.1.1/llx/__main__.py

@@ -0,0 +1,4 @@
+"""Allow running llx as: python -m llx."""
+from llx.cli.app import main
+
+main()

llx-0.1.1/llx/analysis/__init__.py

@@ -0,0 +1 @@
+"""Analysis layer — collects project metrics from code2llm, redup, vallm, and filesystem."""