infinidev 0.14.3__tar.gz

infinidev-0.14.3/.gitignore

@@ -0,0 +1,84 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+dist/
+build/
+*.egg
+*.whl
+*.spec
+
+# Logs
+*.log
+logs/
+
+# Virtual environments
+.venv/
+venv/
+.env
+.env.*
+!.env.example
+
+# Infinidev local data
+.infinidev/
+
+# Local-only working notes (kept untracked on purpose)
+TODO.md
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Testing / coverage
+.pytest_cache/
+.hypothesis/
+.mypy_cache/
+.ruff_cache/
+.tox/
+.nox/
+htmlcov/
+.coverage
+.coverage.*
+coverage.xml
+
+# Local package/build caches
+.hatch/
+.uv-cache/
+.uv-tmp/
+
+# Claude code
+.claude/
+
+# Fine-tuning data (large repos + model weights)
+finetune/repos/
+finetune/output/
+finetune/validation_report.txt
+finetune/__pycache__/
+unsloth_compiled_cache/
+
+# Benchmark and example output
+bench/runs/*
+!bench/runs/prompt-comprehension-closure/
+bench/runs/prompt-comprehension-closure/*
+!bench/runs/prompt-comprehension-closure/closure.json
+!bench/runs/prompt-comprehension-closure/terminal-tuples.jsonl
+bench/predictions*.jsonl
+examples/**/build.log
+examples/**/*.db
+
+
+# ken — local index, daemon socket, logs
+.ken/
+
+# SWE-bench evaluation output, regenerated per run
+.infinidev_eval.json
+# Downloaded embedding calibration datasets retain their upstream licenses.
+bench/data/*.json
+bench/data/*.jsonl

infinidev-0.14.3/LICENSE.md

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Infinibay LLC <andres@infinibay.net>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

infinidev-0.14.3/PKG-INFO

@@ -0,0 +1,341 @@
+Metadata-Version: 2.4
+Name: infinidev
+Version: 0.14.3
+Summary: A terminal-based AI programming tool using agent loops.
+Project-URL: Homepage, https://github.com/Infinibay/infinidev
+Project-URL: Repository, https://github.com/Infinibay/infinidev.git
+Project-URL: Issues, https://github.com/Infinibay/infinidev/issues
+Author-email: Andres Borek <andres@infinibay.net>
+License-Expression: MIT
+License-File: LICENSE.md
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development
+Requires-Python: >=3.11
+Requires-Dist: chromadb>=1.1.0
+Requires-Dist: click>=8.1.7
+Requires-Dist: duckduckgo-search>=8.1.0
+Requires-Dist: httpx>=0.28.0
+Requires-Dist: langdetect>=1.0.9
+Requires-Dist: litellm!=1.82.7,!=1.82.8,>=1.81.0
+Requires-Dist: numpy>=2.0.0
+Requires-Dist: ollama>=0.6.0
+Requires-Dist: pillow>=10.0.0
+Requires-Dist: prompt-toolkit>=3.0.43
+Requires-Dist: pydantic-settings>=2.10.0
+Requires-Dist: pydantic>=2.11.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: textual>=8.1.1
+Requires-Dist: tokenizers>=0.22.0
+Requires-Dist: trafilatura>=2.0.0
+Requires-Dist: tree-sitter-bash>=0.23.0
+Requires-Dist: tree-sitter-c-sharp>=0.23.1
+Requires-Dist: tree-sitter-c>=0.24.1
+Requires-Dist: tree-sitter-css>=0.23.0
+Requires-Dist: tree-sitter-go>=0.23.0
+Requires-Dist: tree-sitter-html>=0.23.0
+Requires-Dist: tree-sitter-java>=0.23.0
+Requires-Dist: tree-sitter-javascript>=0.23.0
+Requires-Dist: tree-sitter-json>=0.24.0
+Requires-Dist: tree-sitter-kotlin>=1.1.0
+Requires-Dist: tree-sitter-markdown>=0.3.0
+Requires-Dist: tree-sitter-php>=0.24.1
+Requires-Dist: tree-sitter-python>=0.23.0
+Requires-Dist: tree-sitter-regex>=0.24.0
+Requires-Dist: tree-sitter-ruby>=0.23.1
+Requires-Dist: tree-sitter-rust>=0.23.0
+Requires-Dist: tree-sitter-toml>=0.6.0
+Requires-Dist: tree-sitter-typescript>=0.23.2
+Requires-Dist: tree-sitter-xml>=0.7.0
+Requires-Dist: tree-sitter-yaml>=0.6.0
+Requires-Dist: tree-sitter>=0.23.0
+Requires-Dist: watchfiles>=0.24.0
+Requires-Dist: wordfreq>=3.1.1
+Requires-Dist: yappi>=1.6.0
+Provides-Extra: cuda
+Requires-Dist: cupy-cuda12x>=13.0.0; extra == 'cuda'
+Provides-Extra: finetune
+Requires-Dist: accelerate<2,>=1.10; extra == 'finetune'
+Requires-Dist: bitsandbytes<1,>=0.46; (platform_system == 'Linux' and platform_machine == 'x86_64') and extra == 'finetune'
+Requires-Dist: ctranslate2<5,>=4.6; extra == 'finetune'
+Requires-Dist: datasets<4.4,>4.1; extra == 'finetune'
+Requires-Dist: deepspeed<1,>=0.17; (platform_system == 'Linux') and extra == 'finetune'
+Requires-Dist: peft<1,>=0.17; extra == 'finetune'
+Requires-Dist: sacremoses<1,>=0.1; extra == 'finetune'
+Requires-Dist: sentencepiece<1,>=0.2; extra == 'finetune'
+Requires-Dist: torch<3,>=2.7; extra == 'finetune'
+Requires-Dist: transformers<5,>=4.57.1; extra == 'finetune'
+Provides-Extra: finetune-unsloth
+Requires-Dist: datasets<4.4,>4.1; extra == 'finetune-unsloth'
+Requires-Dist: torch<3,>=2.7; extra == 'finetune-unsloth'
+Requires-Dist: transformers<5,>=4.57.1; extra == 'finetune-unsloth'
+Requires-Dist: trl<2,>=0.24; extra == 'finetune-unsloth'
+Requires-Dist: unsloth<2027,>=2026.3.17; (platform_system == 'Linux' and platform_machine == 'x86_64') and extra == 'finetune-unsloth'
+Provides-Extra: mnn
+Requires-Dist: mnn>=3.5.0; extra == 'mnn'
+Requires-Dist: transformers<5,>=4.40; extra == 'mnn'
+Description-Content-Type: text/markdown
+
+# Infinidev
+
+A terminal-based AI programming assistant for modern coding models. It runs an autonomous agent loop that can read, write, and edit code, execute commands, manage git, search the web, and maintain a persistent knowledge base — all from your terminal.
+
+The primary target is a single configured SOTA reasoning or coding model with a long context window, including models around 1M tokens where the provider supports them. LiteLLM keeps the backend provider-agnostic; local open-weight models through [Ollama](https://ollama.com) remain a supported compatibility path.
+
+![Infinidev TUI](https://raw.githubusercontent.com/Infinibay/infinidev/main/public/screenshot.png)
+
+## Features
+
+- **Plan-execute-summarize loop** — the agent keeps context relevant through step summaries, evidence pointers, and on-demand recall instead of filling even a large window indiscriminately.
+- **Full-featured TUI** — tabbed interface with chat, file explorer, syntax-highlighted editor, sidebar with live progress, and autocomplete for commands.
+- **Live file change diffs** — collapsible widgets showing colorized unified diffs with line numbers for every file the agent modifies, updated in real time during task execution.
+- **Context window tracking** — dual progress bars showing Chat Usage (your input + session history) and Task Usage (actual prompt tokens from the LLM), with automatic budget warnings when context runs low.
+- **Settings editor** — modal settings browser with section grouping, inline editing, and save/cancel buttons. Accessible via `/settings`.
+- **Persistent knowledge base** — the agent records what it learns about your project (classes, patterns, APIs) and recalls it across steps and future sessions.
+- **Dual tool-calling modes** — auto-detects whether the LLM supports native function calling or falls back to JSON-in-text parsing.
+- **30+ built-in tools** — file operations, git, shell, web search/fetch, knowledge management with semantic dedup.
+- **Project-local state** — settings, DB, and logs live in `.infinidev/` inside your project directory.
+- **Model management** — list, switch, and interactively pick Ollama models from the TUI.
+- **Documentation management** — browse and manage cached library documentation.
+
+
+## Requirements
+
+- Python 3.11+
+- A LiteLLM-compatible model provider
+- [Ollama](https://ollama.com) when using a local open-weight model
+- [uv](https://docs.astral.sh/uv/) (recommended) or pip
+
+## Quickstart
+
+```bash
+# Clone and install
+git clone https://github.com/Infinibay/infinidev.git
+cd infinidev
+uv sync
+
+# Local-model option: make sure Ollama is running with a model
+ollama pull qwen3-coder:30b
+
+# Launch
+uv run infinidev
+```
+
+Or install system-wide:
+
+```bash
+./install.sh
+infinidev
+```
+
+## Usage
+
+### TUI Mode (default)
+
+```bash
+uv run infinidev
+```
+
+The TUI has three panels:
+- **Left** — File explorer (toggle with `Ctrl+E`)
+- **Center** — Tabbed area with Chat + file editor tabs
+- **Right** — Sidebar showing plan progress, active tools, and logs
+
+### Classic Mode
+
+```bash
+uv run infinidev --classic
+```
+
+Text-only mode for minimal terminals or piping.
+
+### Commands
+
+| Command | Description |
+|---------|-------------|
+| `/help` | Show all commands and keybindings |
+| `/models` | Show current model configuration |
+| `/models list` | List available Ollama models |
+| `/models set <name>` | Change the active model |
+| `/models manage` | Interactive model picker |
+| `/settings` | Show or edit settings configuration |
+| `/settings browse` | Open settings editor modal |
+| `/findings` | Browse all knowledge base findings |
+| `/knowledge` | Browse project context knowledge |
+| `/documentation` | Browse cached library documentation |
+| `/docs` | Browse cached library documentation (alias) |
+| `/clear` | Clear chat history and panels |
+| `/exit` | Quit |
+
+### Keybindings
+
+| Key | Action |
+|-----|--------|
+| `Ctrl+S` | Save current file |
+| `Ctrl+F` | Find in current file |
+| `Ctrl+Shift+F` | Search across project |
+| `Ctrl+E` | Toggle file explorer |
+| `Ctrl+W` | Close active file tab |
+| `F2` / `F3` / `F4` | Focus: Chat / Explorer / Sidebar |
+
+### File Editor
+
+The built-in editor tracks unsaved changes with a visual indicator (`●`) on the tab and in the file explorer (highlighted in yellow). Closing a modified file prompts a Save/Discard/Cancel dialog.
+
+### Image Viewer
+
+Opening an image file (PNG, JPG, GIF, BMP, WebP, etc.) from the explorer renders it directly in the terminal using Unicode half-block characters (`▀`). Each character cell represents 2 vertical pixels with 24-bit color.
+
+Controls when viewing an image:
+
+| Key | Action |
+|-----|--------|
+| `+` / `-` | Zoom in / out |
+| `0` | Reset zoom to 100% |
+| `F` | Fit image to viewport |
+
+The info bar shows filename, dimensions, format, file size, current zoom level, and the active rendering backend (`numpy` or `cuda`).
+
+#### GPU-accelerated rendering
+
+By default, images are processed with NumPy on CPU. If you have an NVIDIA GPU, you can enable CUDA acceleration for faster rendering of large images:
+
+```bash
+# Install with CUDA support
+uv sync --extra cuda
+
+# Or add cupy manually
+uv pip install cupy-cuda12x
+```
+
+The backend is auto-detected at startup — no configuration needed. The info bar in the image viewer shows `[cuda]` or `[numpy]` so you know which one is active.
+
+### Project Search
+
+`Ctrl+Shift+F` opens a project-wide search modal with:
+- Real-time results with highlighted matches
+- Preview pane with context (2 lines before/after)
+- **Skip junk** toggle (on by default) — excludes `node_modules`, `.git`, `__pycache__`, `.venv`, binary files, lock files, and other common non-source files
+- Click a result to open the file at the matching line
+
+## Configuration
+
+Settings are stored in `.infinidev/settings.json` in your project directory. They can also be set via environment variables with the `INFINIDEV_` prefix.
+
+| Setting | Default | Description |
+|--|---------|--|
+| `LLM_MODEL` | `ollama_chat/qwen3-coder:30b` | LiteLLM model identifier |
+| `LLM_BASE_URL` | `http://localhost:11434` | Ollama / LLM API base URL |
+| `LOOP_MAX_ITERATIONS` | `50` | Max planning iterations per task |
+| `LOOP_MAX_TOTAL_TOOL_CALLS` | `200` | Global tool call limit per task |
+| `LOOP_HISTORY_WINDOW` | `0` | Summaries to keep (0 = all) |
+| `COMMAND_OUTPUT_CAPTURE_ENABLED` | `false` | Opt in to private, bounded capture of command streams that exceed the normal truncation limit. See [`docs/COMMAND_OUTPUT_CAPTURE.md`](docs/COMMAND_OUTPUT_CAPTURE.md). |
+| `COMMAND_OUTPUT_AUTO_NOTES_ENABLED` | `false` | Independently create traceable closure notes for captured-output handles. |
+| `COMMAND_OUTPUT_NOTE_COMPACTION_ENABLED` | `false` | Independently compact newly created closure notes without replacing their sources. |
+| `FORGEJO_API_URL` | `""` | Forgejo API URL |
+| `FORGEJO_OWNER` | `""` | Forgejo owner |
+| `INFINIDEV_MNN_MODEL_PATH` | unset | Override for the MNN model path. Only needed to point at a custom location; leave unset to use the auto-managed default under `~/.infinidev/models/`. |
+
+## Optional: MNN-accelerated embeddings
+
+ContextRank, finding dedup, and symbol search all rely on the same
+`all-MiniLM-L6-v2` embedding model. By default this runs through
+ChromaDB's bundled ONNX Runtime on CPU, which costs ~115 ms per query
+on consumer hardware. For sessions backed by a remote LLM provider, that
+latency is visible on every pivot of the loop.
+
+Routing the same model through [MNN](https://github.com/alibaba/MNN)
+(Alibaba's inference runtime) cuts this to ~11 ms per query — roughly
+10× faster — while producing bit-compatible vectors (cosine 1.0000
+against the ONNX baseline), so embeddings already stored in the DB
+remain valid without re-indexing.
+
+### Enable
+
+```bash
+uv sync --extra mnn     # or: pip install 'infinidev[mnn]'
+uv run infinidev
+```
+
+That's it. On the first session after installing the extra, infinidev
+detects the MNN runtime, converts ChromaDB's cached ONNX model to MNN
+format (one-time, ~30 s, logged on stderr), caches it under
+`~/.infinidev/models/minilm.mnn`, and switches to the faster path for
+every subsequent session. If the extra isn't installed, nothing changes
+— infinidev keeps using the ChromaDB default embedder.
+
+The `scripts/convert_minilm_to_mnn.py` script is still available for
+pre-warming (useful in CI images or read-only deployments where the
+first-run conversion is inconvenient), but it's not required.
+
+### Notes
+
+- **CPU only today.** The MNN pip wheel does not ship with the Vulkan
+  backend compiled in, so inference runs on CPU regardless of the
+  requested backend. CPU alone is already the ~10× speedup documented
+  above; GPU would be additional.
+- **Hardened kernels.** MNN's wheel ships with an executable-stack ELF
+  flag that Arch/CachyOS/Ubuntu hardened kernels reject. The embedder
+  auto-patches the affected `.so` files on first use; no manual step
+  needed.
+- **Same model, same vectors.** The embedder produces the same 384-dim
+  output as before. Stored finding, symbol, and context embeddings
+  remain correct — no migration required.
+
+## Architecture
+
+```
+src/infinidev/
+  cli/          # TUI (Textual) and classic CLI entry points
+  engine/       # Plan-execute-summarize loop engine
+  agents/       # Agent role definitions and tool binding
+  tools/        # 30+ tools: file, git, shell, web, knowledge, documentation
+  config/       # Settings, LLM params, model capability probing
+  db/           # SQLite with FTS5, findings, artifacts, conversations
+  prompts/      # System prompts, tech-specific guidelines
+```
+
+The core loop:
+1. **Plan** — LLM produces 2-3 initial steps
+2. **Execute** — one step at a time, calling tools as needed
+3. **Summarize and archive** — the step conclusion stays on the plan while raw tool evidence moves into searchable working memory
+4. **Repeat** — the next prompt is rebuilt from the plan, durable summaries, and recalled evidence when needed
+
+This keeps context focused, attributable, and recoverable. A long context window provides headroom; it does not make every old tool result equally relevant.
+
+## Knowledge Base
+
+The agent maintains a persistent knowledge base of findings across sessions. It automatically records:
+- Project structure, key classes, and public APIs
+- Patterns, conventions, and dependencies
+- Research results and bug findings
+- Things you ask it to remember
+
+Findings are auto-injected into the prompt at the start of each task, so the agent starts every session already knowing your project.
+
+Browse the knowledge base anytime with `/findings` or `/knowledge`.
+
+## Development
+
+```bash
+# Run tests
+uv run pytest tests/
+
+# Run a specific test
+uv run pytest tests/test_tui.py::test_space_inserts_space_character -v
+```
+
+Prompt changes must follow [`docs/PROMPTING.md`](docs/PROMPTING.md). The current
+specification-elaboration design is documented in
+[`docs/SPEC_ELABORATION.md`](docs/SPEC_ELABORATION.md).
+
+## License
+
+Infinidev is distributed under the MIT License. Copyright (c) 2026 Infinibay LLC
+<andres@infinibay.net>. See [`LICENSE.md`](LICENSE.md).