localagentbrowser 1.63__tar.gz → 1.64.1__tar.gz

{localagentbrowser-1.63 → localagentbrowser-1.64.1}/CHANGELOG.md

@@ -1,11 +1,76 @@
 # Changelog
 
-Every version of LocalAgentBrowser, newest first. Each released version is also a tagged commit (`v1.11` … `v1.62`); 1.54 to 1.56 and 1.58 to 1.60 were internal steps
+Every version of LocalAgentBrowser, newest first. Each released version is also a tagged commit (`v1.11` … `v1.63`); 1.54 to 1.56 and 1.58 to 1.60 were internal steps
 measured on the regression suite and released as part of 1.57 and 1.61 (see
 [docs/regression-history.md](docs/regression-history.md)).
 Timings are from live runs on the development machine (Intel i5-9500, 6 cores, no GPU, Qwen2.5-7B-Instruct
 Q4_K_M in LM Studio), where reading the prompt takes about 90% of every model call.
 
+## [1.64.1] - 2026-11-08
+Documentation only; the code is unchanged from 1.64, as measured.
+- **README revamped,** so PyPI's page shows it too: the four models tested near the top, with download size, RAM and
+  results; install steps with the virtual-environment commands; a first-run guide (load the model at 8192 context);
+  Windows shortcuts. The long technical sections moved to docs/how-it-works.md and docs/task-results.md.
+- **Fixed in the README:** the FAQ's model table showed the October results, and a link was broken on PyPI.
+- **Project site:** a "pick the model that fits your PC" section, an Install section, and its charts redrawn with
+  1.64's results.
+
+## [1.64] - 2026-11-08
+The theme is **silent omission** ([issue #11](https://github.com/SnowFXXX/LocalAgentBrowser/issues/11)): a part of
+the objective dropping out of the final answer without being marked "not found". It was measured on two PCs (PC A
+and PC B, both Intel i5-9500, no GPU) and then on four models with identical code.
+
+### Added
+- **Windows launcher and shortcuts.** `tools/windows/LocalAgentBrowser.cmd` checks that LM Studio is answering,
+  runs the agent in its own folder under `Documents\LocalAgentBrowser runs`, and opens the report when the run ends.
+  `tools/windows/make_shortcuts.ps1` adds Start-menu and desktop shortcuts with the project icon (from a clone of
+  the repository).
+- **The report opens by itself** when a launcher run ends: `research_report.md` is written next to it as a dark web
+  page, in the project site's colors, with the final result, checklist and discoveries in separate cards and
+  citations shown as tags (`tools/windows/show_report.py`, standard library only). Windows has no program for `.md`
+  files by default.
+- Regression suite: every run folder gets `run_info.json` (PC label from `LAB_PC_LABEL`, commit, and a fingerprint
+  of the uncommitted changes), so runs on several PCs can be tied to the exact code they ran.
+- Regression suite: `LAB_BLOCKED_SITES` makes NAVIGATE refuse given sites, for benchmark runs that must not read the
+  benchmark's own answer pages.
+
+### Fixed: parts of the objective dropping out of the answer
+- **The coverage check asks for the quote first.** "Does this discovery answer the item?" is now answered by first
+  copying the words that answer it, with a rule that words on the same topic but a different aspect don't count.
+  On 30 hand-labelled real cases, 25 right instead of 16 (no false "not found", 5 false "found" left).
+- **A part credited to several items only counts where the item's own words appear**, so one quote can't silently
+  cover three parts; such an item is sent back as unanswered.
+- **Missing amounts and concrete missing terms send the agent back.** When an item asks for amounts and no discovery
+  for it gives one, or the check names a concrete missing term ("O2") that no discovery contains, the agent is told
+  to find it, instead of finishing without it (an explanation once finished in 4 turns without oxygen).
+- **Each fact stays under its own part.** A discovery keeps the page heading it came from, including headings inside
+  a discovery that crosses page sections; a heading the discovery starts with isn't replaced by the one above;
+  bylines, very long "headings" (numbered sentences) and the prompt's own section names don't count as headings or
+  names.
+- **Names no discovery gives are cut,** with a note: a short cited heading's name is checked too, word forms need
+  an 80% shared start ("PhotoScape" over a PhotoSplice source), and words in a source's web address count as given.
+- **A sentence under one label copied from another subject's sentence is cut** (SQLite's sentence under
+  PostgreSQL).
+- **Numbers in words are checked like digits** ("two weeks" needs a 2 in a source, "one cup" equals "1 cup"), unit
+  abbreviations count as their words ("5,895 m (19,341 ft)" answers "in meters" and "in feet"), and a time needs
+  the same number as a time in a source ("2 weeks" was taken from a "2L jar").
+- **Citations:** citation lines on their own are joined to the line they cite; citations are moved out of code, and
+  unclosed code blocks closed, so correct commands aren't cut as invented.
+- A **"Recommendation" section is labelled as the model's view**, like "My view:".
+- **NAVIGATE refuses text that isn't a web address** (a run lost 5 turns on it).
+
+### Fixed: the regression suite's scoring
+- The code's own "Left out, because…" notes are no longer read as the result's claims (commands and uncited lines).
+  4 of 78 earlier run folders were over-counted.
+- A bold label ("**1. Creating a virtual environment:**") is a heading, not an uncited claim.
+
+### Measured
+- 7B on two PCs: 7 of 7 on both PCs with v11 (297.8 and 269.6 model minutes), with no outside knowledge, invented
+  numbers or invented commands in any finished result.
+- Four models, same code (v12, 90 minutes per task): Qwen2.5-7B 6 of 7, Llama 3.1 8B 7 of 7, Qwen2.5-14B 5 of 7,
+  Qwen2.5-3B 3 of 7. On 1.63 they were 6, 2, 2 and 0 of 7. No finished result used outside knowledge. Details in
+  docs/regression-history.md.
+
 ## [1.63] - 2026-11-01
 ### Added
 - A model call the server fails is tried again after a wait (5, 15, 30, 60 and 120 seconds, about 4 minutes in all),

localagentbrowser-1.64.1/PKG-INFO

@@ -0,0 +1,337 @@
+Metadata-Version: 2.4
+Name: localagentbrowser
+Version: 1.64.1
+Summary: An autonomous web agent driven by a local LLM (LM Studio) and Playwright. Runs entirely on your own machine.
+Author: SnowFX
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/SnowFXXX/LocalAgentBrowser
+Project-URL: Changelog, https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/CHANGELOG.md
+Project-URL: Issues, https://github.com/SnowFXXX/LocalAgentBrowser/issues
+Keywords: ai-agent,autonomous-agent,llm,local-llm,lm-studio,playwright,browser-automation,web-agent,web-research,qwen,offline-ai
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Internet :: WWW/HTTP :: Browsers
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: openai>=2.0
+Requires-Dist: playwright>=1.50
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Requires-Dist: ruff>=0.15; extra == "dev"
+Dynamic: license-file
+
+# LocalAgentBrowser
+
+**An autonomous web agent powered by a local LLM. Give it an objective; it searches, reads, takes notes and
+decides when it's done, on your own computer. It gives an answer you can check, or says honestly what it couldn't
+find.**
+
+[![Tests](https://github.com/SnowFXXX/LocalAgentBrowser/actions/workflows/tests.yml/badge.svg)](https://github.com/SnowFXXX/LocalAgentBrowser/actions/workflows/tests.yml)
+[![PyPI](https://img.shields.io/pypi/v/localagentbrowser.svg)](https://pypi.org/project/localagentbrowser/)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/LICENSE)
+![Python 3.10–3.13](https://img.shields.io/badge/python-3.10%E2%80%933.13-blue.svg)
+![Runs locally](https://img.shields.io/badge/LLM-local%20(LM%20Studio)-green.svg)
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/SnowFXXX/LocalAgentBrowser/main/docs/social-preview.png" alt="LocalAgentBrowser: SEARCH, NAVIGATE, READ_MORE, DISCOVER, FINISH. No cloud AI, 7B model on a CPU, LM Studio and Playwright." width="820">
+</p>
+
+A local language model served by [LM Studio](https://lmstudio.ai) decides what to do next, and
+[Playwright](https://playwright.dev/python/) carries it out in a Chromium window you can watch. It is built for a
+**small model on an ordinary CPU, no GPU required**, and every claim in its answer points to the page it came from.
+
+- 🔒 **No cloud AI and no API keys.** The model runs in your own LM Studio; your objective, the model and the
+  report stay on your computer. (Searches go to DuckDuckGo and pages load like in any browser.)
+- ✅ **Checks instead of trust.** Findings must be copied from the page shown, commands must appear on the page
+  exactly, and numbers no finding gives are cut. What it can't find is listed as not found, not filled in.
+- 🧭 **Unattended.** It searches, opens pages, reads long pages part by part, records what's relevant and finishes
+  when every part of the objective is covered.
+- 📝 **A report every time.** The final result with numbered citations and every finding with its source, written
+  however the run ends.
+- 🪟 **Windows shortcuts.** A launcher with Start-menu and desktop shortcuts opens the report by itself when a run
+  ends. A Windows installer is coming in the next release.
+
+📖 [Project site](https://snowfxxx.github.io/LocalAgentBrowser/) ·
+[Article: We Can Do Better: A Small AI That Can't Cover Up](https://snowfxxx.github.io/LocalAgentBrowser/article.html) ·
+[Paper: Verification over Trust](https://snowfxxx.github.io/LocalAgentBrowser/paper.html) ·
+[Example reports](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/docs/examples/README.md)
+
+## Contents
+
+[Tested on four models](#tested-on-four-models) · [Install](#install) · [First run](#first-run) ·
+[What a run looks like](#what-a-run-looks-like) · [How it works](#how-it-works) · [Settings](#settings) ·
+[FAQ](#faq) · [Limitations](#limitations) · [Roadmap](#roadmap) · [Testing](#testing) · [Contributing](#contributing)
+
+## Tested on four models
+
+Every release is measured on the same seven tasks, one of each kind it's built for: a fact, a list with conditions,
+a comparison with a recommendation, a how-to, an explanation, views from several sources, and a lookup in official
+documentation. In 1.64, four models ran them with identical code, 90 minutes per task, on an ordinary 6-core PC with
+no GPU (Intel i5-9500):
+
+| Model (Q4_K_M) | Download | RAM | Tasks finished | Model time | Gaps filled from its own knowledge |
+|---|---|---|---|---|---|
+| **Qwen2.5-7B-Instruct** (default) | 4.7 GB | 8 GB | 6 of 7 | 361 min | 0 |
+| **Llama-3.1-8B-Instruct** | 4.9 GB | 8 GB | **7 of 7** | 303 min | 0 |
+| **Qwen2.5-14B-Instruct** | 9.0 GB | 16 GB | 5 of 7 | 565 min | 0 |
+| **Qwen2.5-3B-Instruct** | 1.9 GB | 4 GB | 3 of 7 | 490 min | 0 |
+
+- **No finished result filled a gap from the model's own knowledge**, on any model.
+- **Llama finished every task.** Read by hand, its results contain no invented facts; its mistakes lean cautious
+  (a "not found" for something its findings do give).
+- **The 14B** is about 2.5 times slower on a CPU; its two time-outs came while a correct answer was being checked.
+- **The 3B** fits small PCs. It finished 3 tasks (none on 1.63), and one of them has a claim the checks missed.
+- On 1.63 the same models finished 6, 2, 2 and 0 of 7. Every step and run is in the
+  [regression history](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/docs/regression-history.md).
+
+**Which to pick:** the 7B for most PCs, Llama if you have the same 8 GB and want it to finish more often, the 3B for
+a PC with little memory. Any instruction-tuned model LM Studio serves should work.
+
+## Install
+
+You need [LM Studio](https://lmstudio.ai) (free), which runs the model, and Python 3.10 or later.
+
+### Any system: pip
+
+```bash
+python -m venv venv
+venv\Scripts\activate
+pip install localagentbrowser
+python -m playwright install chromium
+```
+
+On macOS or Linux, activate with `source venv/bin/activate` instead.
+
+### From source
+
+```bash
+git clone https://github.com/SnowFXXX/LocalAgentBrowser.git
+cd LocalAgentBrowser
+python -m venv venv
+venv\Scriptsctivate
+pip install -r requirements.txt
+python -m playwright install chromium
+```
+
+Run it with `python agent_browser.py`.
+
+### Windows: Start-menu and desktop shortcuts
+
+From a clone (above), with its packages installed in a `venv` folder inside it:
+
+```bash
+powershell -ExecutionPolicy Bypass -File tools\windows\make_shortcuts.ps1
+```
+
+This adds **LocalAgentBrowser** to the Start menu and the desktop. The launcher checks that LM Studio is answering,
+runs each objective in its own folder under **Documents\LocalAgentBrowser runs**, and opens the report as a page in
+your browser when the run ends.
+
+**Coming in the next release:** a Windows installer that brings its own Python, lets you pick one of the four tested
+models during setup, and adds the shortcuts for you.
+
+## First run
+
+1. In LM Studio, load your model with a **context length of 8192** (the agent's default; LM Studio's own default may
+   differ) and start the local server (Developer tab → Start Server).
+2. Start LocalAgentBrowser: the Start-menu shortcut on Windows, or `localagentbrowser` in a terminal.
+3. Type your objective, for example *What is the tallest mountain in Africa, and how tall is it in meters and in
+   feet?* A Chromium window opens and the agent starts working. The first step takes a minute or two on a CPU.
+4. When it finishes, the report opens in your browser (Windows launcher), or read `research_report.md` in the folder
+   you ran it from. Runs from the shortcut each get their own folder under **Documents\LocalAgentBrowser runs**.
+
+A run takes about 10 to 60 minutes on a CPU. Press Ctrl+C at any time to stop; the report is still written with
+everything found so far.
+
+**Good objectives** are questions you'd research by reading pages: a fact, a list with conditions ("three free,
+open-source alternatives to Photoshop"), a comparison, a how-to, an explanation, or what several sources say.
+**Not yet:** anything behind a login, a form or a button (it reads pages; it doesn't click or type into them).
+
+## What a run looks like
+
+A real run (1.40, with the timing lines the [test runner](#testing) adds; repetitive lines left out). Objective:
+*"What is the tallest mountain in Africa, and how tall is it in meters and in feet?"*
+
+```text
+🧠 [TURN 1/100] Active reasoning cycle executing...
+   (model call 38.6s, prompt=676 tok, completion=54 tok)
+🎬 Chosen Action: [SEARCH] -> Parameter: tallest mountain in Africa
+
+🧠 [TURN 2/100] Active reasoning cycle executing...
+💡 Agent Thoughts: From the search results, I can see that Mount Kilimanjaro is mentioned as the tallest
+   mountain in Africa ... I will navigate to one of these pages to find the exact height in meters and feet.
+🎬 Chosen Action: [NAVIGATE] -> Parameter: https://en.wikipedia.org/wiki/Mount_Kilimanjaro
+
+🧠 [TURN 3/100] Active reasoning cycle executing...
+🎬 Chosen Action: [DISCOVER] -> Parameter: Mount Kilimanjaro is the highest mountain in Africa, with an
+   elevation of 5,895 m (19,341 ft) above sea level.
+
+🧠 [TURN 4/100] Active reasoning cycle executing...
+♻️ Cheap retry 1/2: [FINISH] refused. Your only discovery comes from
+   https://en.wikipedia.org/wiki/Mount_Kilimanjaro. Consider whether the objective needs more. ...
+   Before finishing, split the OBJECTIVE into its separate parts and, in thought_process, write each
+   part followed by the discovery that covers it, or 'not covered'. ...
+💡 Agent Thoughts: The objective has two parts: the name of the tallest mountain in Africa and its height
+   in meters and feet. Both are covered by the discovery from Mount Kilimanjaro's Wikipedia page.
+🎬 Chosen Action: [FINISH] -> Parameter: The tallest mountain in Africa is Mount Kilimanjaro ...
+🎯 Agent has signaled mission complete. Writing the final result...
+```
+
+Four turns and 11.8 minutes of model time. The report it wrote:
+
+> **Final result:** The tallest mountain in Africa is Mount Kilimanjaro [1], and its elevation is 5,895 meters
+> (19,341 feet) above sea level [1].
+>
+> **Discoveries (1)**
+> 1. Turn 3, from https://en.wikipedia.org/wiki/Mount_Kilimanjaro: *Mount Kilimanjaro is the highest mountain
+>    in Africa, with an elevation of 5,895 m (19,341 ft) above sea level.*
+
+## How it works
+
+Each turn, the model sees the objective, what it has found so far, its recent actions and the current page, and
+answers with one JSON action:
+
+| Action | What it does |
+|---|---|
+| `SEARCH` | Searches DuckDuckGo and shows the results with their real addresses |
+| `NAVIGATE` | Opens an address from the results or the current page's links |
+| `READ_MORE` | Shows the next part of a long page, or the part whose outline names what's still missing |
+| `DISCOVER` | Records something from the current page as a finding |
+| `FINISH` | Ends the run, after each part of the objective is checked; the answer is then written in a separate step |
+
+```mermaid
+flowchart LR
+    O[Objective] --> P[Build prompt]
+    P --> M[Local model<br/>LM Studio]
+    M -->|JSON action| C{Checks in code}
+    C -->|refused: cheap retry| M
+    C -->|accepted| B[Playwright<br/>Chromium]
+    B -->|page text, links| P
+    C -->|FINISH| R[Report]
+```
+
+The model proposes; code checks before anything is accepted:
+- **A fixed checklist** of the objective's parts, made once at the start, that every later check uses.
+- **Findings must come from the page:** they're compared with the page text shown, and commands must appear on the
+  page exactly.
+- **Finishing is checked part by part,** and the agent is sent back only for gaps the code can confirm: a part
+  nothing answers, fewer things than asked for, missing amounts, a concrete missing term such as "O2".
+- **The answer is written separately,** from the findings only. Names, numbers and commands no finding gives are cut
+  and named, and parts nothing answers are listed as "Not found in the pages read".
+- **Built for a CPU:** it reuses LM Studio's prompt cache, so most turns only process what changed.
+
+The full details, code layout, timings and known limits:
+[docs/how-it-works.md](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/docs/how-it-works.md).
+
+## Settings
+
+| Environment variable | Default | Meaning |
+|---|---|---|
+| `LMSTUDIO_BASE_URL` | `http://localhost:1234/v1` | Address of the OpenAI-compatible server |
+| `LMSTUDIO_MODEL` | `qwen2.5-7b-instruct` | Model identifier as the server lists it |
+| `LMSTUDIO_API_KEY` | `lm-studio` | API key, if your server requires one |
+| `LMSTUDIO_CONTEXT_LENGTH` | `8192` | Context length the model is loaded with; the conversation budget follows it |
+
+Behaviour limits are named constants in `localagentbrowser/config.py`, each with a comment.
+
+## FAQ
+
+**Does it need a GPU?** No. It was developed entirely on a CPU; a GPU just makes each turn faster.
+
+**Why does a turn take minutes?** On a CPU the model reads the prompt slowly (about 8 tokens a second on the
+development PC), so a turn that brings in a new page takes a few minutes. Most other turns reuse LM Studio's cache.
+
+**Is anything sent to the internet?** No AI service is involved, and nothing about your run is uploaded. The agent
+does browse the real web: searches, written from your objective, go to DuckDuckGo, and pages load normally.
+
+**Can I use another OpenAI-compatible server?** Probably: point `LMSTUDIO_BASE_URL` at it. The speed tricks rely
+on the server reusing cached prompt prefixes (llama.cpp-based servers do).
+
+**Where are the results?** `research_report.md` (the answer and every finding with its source) and
+`research_log.txt` (every action and reason), in the run's folder.
+
+## Limitations
+
+- **Judging whether a finding really answers a part is the weakest area.** The model can credit a finding about the
+  right topic to the wrong part (a "create" command for "activate"), or put the wrong number on a citation. Check
+  claims against the listed findings.
+- **Reading only:** it doesn't click, fill in forms or sign in, and some sites refuse automated browsers.
+- **Web pages go into the prompt,** so a page could try to manipulate the model (prompt injection); treat findings as
+  unverified. See [SECURITY.md](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/SECURITY.md).
+- **Seven kinds of task so far.** Others may expose new problems; reports are welcome.
+
+More in [docs/how-it-works.md](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/docs/how-it-works.md#limitations).
+
+## Roadmap
+
+- [x] A fixed checklist, a coverage check verified in code, and every change measured on a regression suite (1.53–1.61)
+- [x] Exact-text command checks, and four models measured on identical code (1.63)
+- [x] Parts of the objective no longer dropped silently as often; the Windows launcher (1.64)
+- [ ] A Windows installer with its own Python and a choice of tested models (next release)
+- [ ] Count silent omissions in the regression suite, so [issue #11](https://github.com/SnowFXXX/LocalAgentBrowser/issues/11) can close on a number
+- [ ] Decide in code, not by asking the model, whether a finding answers the part it's credited to
+- [ ] A tray app on Windows: new research, progress, a notification when done
+- [ ] Rewind dead ends: return to a saved point instead of carrying an unused page in every later prompt
+- [ ] Interacting with pages (clicking, forms) for tasks beyond reading
+
+Ideas and requests are welcome in [issues](https://github.com/SnowFXXX/LocalAgentBrowser/issues).
+
+## Testing
+
+The test suite runs in a few seconds with no model or browser: both are replaced by scripted fakes.
+
+```bash
+pip install -r requirements-dev.txt
+python -m pytest
+python -m ruff check .
+```
+
+To try the real agent with a fixed objective and a time limit, logging every model call:
+
+```bash
+python tools/live_test.py "Your objective here" --minutes 25
+```
+
+To measure a change on all seven kinds of task (several hours on a CPU), on any model LM Studio has:
+
+```bash
+python tools/regression.py --model qwen2.5-7b-instruct --baseline regression_runs/<earlier run>/summary.json
+```
+
+Each run gets a folder in `regression_runs/` with every task's report, journal and prompt trace, a `summary.md`
+with honesty measures for each result, and `run_info.json` naming the PC and the exact code it ran. Results by kind
+of task are in [docs/task-results.md](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/docs/task-results.md),
+and every step since 1.53 in
+[docs/regression-history.md](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/docs/regression-history.md).
+
+## Contributing
+
+Contributions are welcome! See [CONTRIBUTING.md](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/CONTRIBUTING.md)
+and the [Code of Conduct](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/CODE_OF_CONDUCT.md). Security issues:
+[SECURITY.md](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/SECURITY.md).
+
+## Project history
+
+Every released version is a tagged commit, and
+[CHANGELOG.md](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/CHANGELOG.md) says what changed and why, with
+the measurements behind each decision.
+
+## Acknowledgements
+
+Versions 1.13 onwards were developed together with [Claude](https://www.anthropic.com/claude) (Anthropic), working
+in Claude Code; those commits list Claude as co-author. Built on [LM Studio](https://lmstudio.ai),
+[Playwright](https://playwright.dev/python/) and the [OpenAI Python library](https://github.com/openai/openai-python).
+
+## License
+
+[MIT](https://github.com/SnowFXXX/LocalAgentBrowser/blob/main/LICENSE) © 2026 SnowFX