whatisit 0.1.0__tar.gz

whatisit-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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 any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Mukesh Poudel
+
+   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.

whatisit-0.1.0/NOTICE

@@ -0,0 +1,27 @@
+whatisit
+Copyright 2026 Mukesh Poudel
+
+Licensed under the Apache License, Version 2.0. You may obtain a copy of
+the License at http://www.apache.org/licenses/LICENSE-2.0
+
+---
+
+The model weights are a LoRA fine-tune of Qwen2.5-Coder-1.5B-Instruct,
+Copyright Alibaba Cloud, used under the Apache License, Version 2.0.
+
+Training data, by measured share of the 125,770-row pool:
+
+  32.8%  Fig autocomplete specs      MIT
+  23.1%  tldr-pages                  CC-BY-4.0
+  18.0%  NL2SH-ALFA training split   MIT
+  11.8%  cli-commands-explained      CC0-1.0    (declared, unverified)
+   7.3%  command-generation          Apache-2.0 (declared, unverified)
+   7.1%  git-instruction             MIT        (declared, unverified)
+
+5.67% is verbatim NL2Bash via the ALFA split; its data/bash is MIT, not GPL.
+Warp workflows are not used.
+
+Attribution, required by CC-BY-4.0: this work includes content from tldr-pages
+(https://github.com/tldr-pages/tldr) under CC-BY-4.0
+(https://creativecommons.org/licenses/by/4.0/). Page content is CC-BY-4.0;
+only scripts/ is MIT.

whatisit-0.1.0/PKG-INFO

@@ -0,0 +1,135 @@
+Metadata-Version: 2.4
+Name: whatisit
+Version: 0.1.0
+Summary: Natural language to shell command, fully local and fast. No API keys, no network.
+Author: Mukesh Poudel
+License: Apache-2.0
+Keywords: shell,cli,llm,local,bash
+Classifier: Environment :: Console
+Classifier: Intended Audience :: System Administrators
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: System :: Shells
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Provides-Extra: dev
+Requires-Dist: pytest>=7; extra == "dev"
+Requires-Dist: pytest-cov>=4; extra == "dev"
+Requires-Dist: ruff>=0.5; extra == "dev"
+Requires-Dist: build>=1; extra == "dev"
+Dynamic: license-file
+
+# whatisit
+
+Natural language to shell command. Fully local, no API key, no network call.
+
+```console
+$ whatisit show which processes are using the most memory
+ps aux --sort=-%mem | head -n 11
+
+$ whatisit find files bigger than 100MB in this folder
+find . -size +100M -exec ls -lh {} \;
+
+$ whatisit delete everything in the root directory
+  !! DANGER  recursive force-delete of a critical path
+rm -rf /
+```
+
+## Install
+
+```bash
+# not on PyPI yet -- install from source
+git clone https://github.com/ThorOdinson246/nl2sh
+cd nl2sh && pip install ./whatisit_pkg
+
+# the model (941 MB)
+hf download ThorOdinson246/nl2sh-1.5b-Q4_K_M nl2sh-1.5b-Q4_K_M.gguf --local-dir .
+
+# a llama.cpp runtime: prebuilt binaries from
+# https://github.com/ggml-org/llama.cpp/releases
+
+whatisit setup --model ./nl2sh-1.5b-Q4_K_M.gguf --bin-dir /path/to/llama.cpp/bin
+whatisit doctor
+```
+
+`setup` does not fetch anything itself yet; point it at the files above.
+`whatisit doctor` reports exactly what is missing.
+
+## Use
+
+```bash
+whatisit <your request>              # unquoted is fine
+whatisit -n 3 compress this folder   # show 3 alternatives
+whatisit -e count lines in every py file   # run it, after confirming
+eval "$(whatisit -q show disk usage)"      # bare output, for scripting
+```
+
+| command | what it does |
+|---|---|
+| `whatisit setup --model <gguf>` | register a local model file |
+| `whatisit doctor` | check the install and report what's missing |
+| `whatisit stop` | unload the model from memory |
+| `whatisit config --set threads=3` | change settings |
+
+## Security notes
+
+**Never run `whatisit` through `sudo`.** Three environment variables
+(`WHATISIT_LLAMA_SERVER`, `WHATISIT_LLAMA_CLI`, `WHATISIT_RUNTIME_LIB`) point at
+the binaries and shared libraries it executes. That is harmless when it is your own
+environment running as you, but across a privilege boundary -- `sudo -E`, a cron
+or setuid wrapper -- they become a way to run an arbitrary binary as root.
+
+The model server listens on a **UNIX socket** inside a `0700` directory, not a
+TCP port, and requires a per-run bearer token. On a shared machine loopback is
+reachable by every other user, so a TCP port would let a co-tenant use your model
+or -- worse -- claim the port first and answer in place of the real server with a
+command of their choosing. Config, query log, pid, token and server log are all
+`0600`.
+
+**The safety check is a seatbelt, not a sandbox.** It is a denylist over a
+Turing-complete language: `eval`, base64 indirection and aliasing defeat any
+static check. The real protection is that nothing runs unless you ask it to.
+
+## Design notes
+
+**It never runs anything on its own.** The default prints the command and
+stops. `-e` runs it, but only after an interactive confirmation, and it
+*refuses* on anything flagged `DANGER` — you have to copy those yourself.
+Compound commands are split on `;`, `&&`, `||` and `|` and every segment is
+checked independently, because a plausible first clause followed by a
+destructive one is a real observed failure mode.
+
+**The model stays resident.** The first query starts a small local server that
+holds the model in RAM; later queries reuse it. Reloading a ~1 GB model per
+invocation costs several seconds and is most of what makes local tools feel
+slow. `whatisit stop` unloads it.
+
+**Threads default to half your cores, capped at 4.** Decoding is limited by
+memory bandwidth, not compute — measured at ~31 GB/s saturated by both a 1.5B
+and a 4B model — so throughput stops improving well before your core count,
+and spending every core only spins the fans.
+
+**Zero Python dependencies.** `pip install whatisit` cannot disturb anything else
+in your environment.
+
+## Model
+
+A 1.5B-parameter model fine-tuned for this one job and quantised to Q4_K_M
+(941 MB): [ThorOdinson246/nl2sh-1.5b-Q4_K_M](https://huggingface.co/ThorOdinson246/nl2sh-1.5b-Q4_K_M).
+
+On [InterCode-ALFA](https://github.com/westenfelder/InterCode-ALFA) — 300 tasks
+scored by *executing* each command in a container and comparing filesystem
+state, file contents and stdout against a reference — it scores **0.620**,
+against 0.540 for the untuned base it was fine-tuned from (+0.080, p = 0.004).
+That puts it level with an untuned Qwen2.5-Coder-7B at 0.613: a difference of
+0.007, p = 0.91, statistically indistinguishable at roughly a fifth the size.
+
+It is not as good as a frontier model — GPT-4o is about 11 points ahead on the
+same benchmark — and it is weakest on multi-stage pipelines. It is meant for
+the one-liner you'd otherwise go and look up.
+
+## Licence
+
+Apache-2.0, as is the Qwen2.5-Coder base model it derives from.

whatisit-0.1.0/README.md

@@ -0,0 +1,112 @@
+# whatisit
+
+Natural language to shell command. Fully local, no API key, no network call.
+
+```console
+$ whatisit show which processes are using the most memory
+ps aux --sort=-%mem | head -n 11
+
+$ whatisit find files bigger than 100MB in this folder
+find . -size +100M -exec ls -lh {} \;
+
+$ whatisit delete everything in the root directory
+  !! DANGER  recursive force-delete of a critical path
+rm -rf /
+```
+
+## Install
+
+```bash
+# not on PyPI yet -- install from source
+git clone https://github.com/ThorOdinson246/nl2sh
+cd nl2sh && pip install ./whatisit_pkg
+
+# the model (941 MB)
+hf download ThorOdinson246/nl2sh-1.5b-Q4_K_M nl2sh-1.5b-Q4_K_M.gguf --local-dir .
+
+# a llama.cpp runtime: prebuilt binaries from
+# https://github.com/ggml-org/llama.cpp/releases
+
+whatisit setup --model ./nl2sh-1.5b-Q4_K_M.gguf --bin-dir /path/to/llama.cpp/bin
+whatisit doctor
+```
+
+`setup` does not fetch anything itself yet; point it at the files above.
+`whatisit doctor` reports exactly what is missing.
+
+## Use
+
+```bash
+whatisit <your request>              # unquoted is fine
+whatisit -n 3 compress this folder   # show 3 alternatives
+whatisit -e count lines in every py file   # run it, after confirming
+eval "$(whatisit -q show disk usage)"      # bare output, for scripting
+```
+
+| command | what it does |
+|---|---|
+| `whatisit setup --model <gguf>` | register a local model file |
+| `whatisit doctor` | check the install and report what's missing |
+| `whatisit stop` | unload the model from memory |
+| `whatisit config --set threads=3` | change settings |
+
+## Security notes
+
+**Never run `whatisit` through `sudo`.** Three environment variables
+(`WHATISIT_LLAMA_SERVER`, `WHATISIT_LLAMA_CLI`, `WHATISIT_RUNTIME_LIB`) point at
+the binaries and shared libraries it executes. That is harmless when it is your own
+environment running as you, but across a privilege boundary -- `sudo -E`, a cron
+or setuid wrapper -- they become a way to run an arbitrary binary as root.
+
+The model server listens on a **UNIX socket** inside a `0700` directory, not a
+TCP port, and requires a per-run bearer token. On a shared machine loopback is
+reachable by every other user, so a TCP port would let a co-tenant use your model
+or -- worse -- claim the port first and answer in place of the real server with a
+command of their choosing. Config, query log, pid, token and server log are all
+`0600`.
+
+**The safety check is a seatbelt, not a sandbox.** It is a denylist over a
+Turing-complete language: `eval`, base64 indirection and aliasing defeat any
+static check. The real protection is that nothing runs unless you ask it to.
+
+## Design notes
+
+**It never runs anything on its own.** The default prints the command and
+stops. `-e` runs it, but only after an interactive confirmation, and it
+*refuses* on anything flagged `DANGER` — you have to copy those yourself.
+Compound commands are split on `;`, `&&`, `||` and `|` and every segment is
+checked independently, because a plausible first clause followed by a
+destructive one is a real observed failure mode.
+
+**The model stays resident.** The first query starts a small local server that
+holds the model in RAM; later queries reuse it. Reloading a ~1 GB model per
+invocation costs several seconds and is most of what makes local tools feel
+slow. `whatisit stop` unloads it.
+
+**Threads default to half your cores, capped at 4.** Decoding is limited by
+memory bandwidth, not compute — measured at ~31 GB/s saturated by both a 1.5B
+and a 4B model — so throughput stops improving well before your core count,
+and spending every core only spins the fans.
+
+**Zero Python dependencies.** `pip install whatisit` cannot disturb anything else
+in your environment.
+
+## Model
+
+A 1.5B-parameter model fine-tuned for this one job and quantised to Q4_K_M
+(941 MB): [ThorOdinson246/nl2sh-1.5b-Q4_K_M](https://huggingface.co/ThorOdinson246/nl2sh-1.5b-Q4_K_M).
+
+On [InterCode-ALFA](https://github.com/westenfelder/InterCode-ALFA) — 300 tasks
+scored by *executing* each command in a container and comparing filesystem
+state, file contents and stdout against a reference — it scores **0.620**,
+against 0.540 for the untuned base it was fine-tuned from (+0.080, p = 0.004).
+That puts it level with an untuned Qwen2.5-Coder-7B at 0.613: a difference of
+0.007, p = 0.91, statistically indistinguishable at roughly a fifth the size.
+
+It is not as good as a frontier model — GPT-4o is about 11 points ahead on the
+same benchmark — and it is weakest on multi-stage pipelines. It is meant for
+the one-liner you'd otherwise go and look up.
+
+## Licence
+
+Apache-2.0, as is the Qwen2.5-Coder base model it derives from.

whatisit-0.1.0/pyproject.toml

@@ -0,0 +1,59 @@
+[build-system]
+requires = ["setuptools>=61"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "whatisit"
+version = "0.1.0"
+description = "Natural language to shell command, fully local and fast. No API keys, no network."
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "Apache-2.0" }
+authors = [{ name = "Mukesh Poudel" }]
+keywords = ["shell", "cli", "llm", "local", "bash"]
+classifiers = [
+  "Environment :: Console",
+  "Intended Audience :: System Administrators",
+  "License :: OSI Approved :: Apache Software License",
+  "Programming Language :: Python :: 3",
+  "Topic :: System :: Shells",
+]
+# Deliberately zero runtime dependencies: stdlib urllib talks to the local
+# server, so `pip install whatisit` cannot break someone's environment.
+dependencies = []
+
+[project.optional-dependencies]
+dev = ["pytest>=7", "pytest-cov>=4", "ruff>=0.5", "build>=1"]
+
+[project.scripts]
+whatisit = "whatisit.cli:main"
+
+[tool.setuptools]
+# Apache-2.0 requires the NOTICE to travel with every redistribution.
+license-files = ["LICENSE", "NOTICE"]
+
+[tool.setuptools.packages.find]
+include = ["whatisit*"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-ra"
+
+[tool.ruff]
+line-length = 100
+target-version = "py39"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "B", "W"]
+ignore = [
+  "E731",  # lambda assignments -- cli.py uses them deliberately for the
+           # colour helpers (BOLD/DIM/RED/...); not worth a refactor here.
+]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/*" = ["E402"]  # test_safety.py needs sys.path.insert before its import
+# test_safety.py is the crown-jewel regression file: every entry is a
+# confirmed bypass or false positive from four adversarial audits. Its
+# content (including these literal '\;' find(1) strings and long inline
+# comments) is deliberately left untouched rather than reformatted.
+"tests/test_safety.py" = ["E402", "E501", "W605"]

whatisit-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+