osa_tool 0.3.0__tar.gz → 0.3.2__tar.gz

{osa_tool-0.3.0 → osa_tool-0.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: osa_tool
-Version: 0.3.0
+Version: 0.3.2
 Summary: Tool that just makes your open source project better!
 License-Expression: BSD-3-Clause
 License-File: LICENSE
@@ -12,8 +12,10 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
 Provides-Extra: paper-claims
-Provides-Extra: repository-validation
+Provides-Extra: paper-claims-lite
+Provides-Extra: paper-claims-marker
 Requires-Dist: GitPython (>=3.1.40)
 Requires-Dist: Pygments (>=2.18.0)
 Requires-Dist: aiofiles (>=24.1.0)
@@ -23,16 +25,13 @@ Requires-Dist: docx2txt (>=0.9)
 Requires-Dist: json-repair[schema] (>=0.60.0,<0.61.0)
 Requires-Dist: libcst (>=1.8.6)
 Requires-Dist: markdown-it-py (>=3.0.0) ; extra == "paper-claims"
-Requires-Dist: marker-pdf (>=1.10.2,<2.0.0) ; (python_version < "3.15") and (extra == "paper-claims")
-Requires-Dist: matplotlib (>=3.10.9) ; extra == "repository-validation"
+Requires-Dist: marker-pdf (>=1.10.2,<2.0.0) ; (python_version < "3.15") and (extra == "paper-claims-marker")
 Requires-Dist: mkdocs (>=1.6.0)
 Requires-Dist: mkdocs-material (>=9.6.0)
 Requires-Dist: mkdocstrings-python (>=1.16.0)
 Requires-Dist: mkdocstrings[python] (>=0.29.0)
 Requires-Dist: nbconvert (>=6.0)
 Requires-Dist: nbformat (>=5.0)
-Requires-Dist: networkx (>=3.6,<3.6.1) ; (python_full_version == "3.14.1") and (extra == "repository-validation")
-Requires-Dist: networkx (>=3.6.1) ; (python_full_version != "3.14.1") and (extra == "repository-validation")
 Requires-Dist: numpy (>=1.26.0,<3.0.0) ; extra == "paper-claims"
 Requires-Dist: packaging (>=25.0)
 Requires-Dist: pandas (>=2.2.0,<3.0.0)
@@ -44,15 +43,13 @@ Requires-Dist: pydantic (>=2.9.0,<3.0.0)
 Requires-Dist: pypdf (>=5.0.0) ; extra == "paper-claims"
 Requires-Dist: qrcode (>=7.4.0)
 Requires-Dist: rapidfuzz (>=3.14.0) ; extra == "paper-claims"
+Requires-Dist: rapidfuzz (>=3.14.0) ; extra == "paper-claims-lite"
 Requires-Dist: reportlab (>=4.2.0,<5.0.0)
 Requires-Dist: scipy (>=1.13.0,<2.0.0) ; extra == "paper-claims"
 Requires-Dist: sentence-transformers (>=3.0.0,<6.0.0) ; extra == "paper-claims"
 Requires-Dist: structlog (>=24.4.0)
 Requires-Dist: tiktoken (>=0.8.0)
 Requires-Dist: tomli (>=2.0.0)
-Requires-Dist: torch (>=2.11.0) ; (python_version < "3.15") and (extra == "repository-validation")
-Requires-Dist: torch-geometric (>=2.7.0) ; extra == "repository-validation"
-Requires-Dist: transformers (>=4.45.2,<5.0.0) ; extra == "repository-validation"
 Requires-Dist: tree-sitter (>=0.23.0)
 Requires-Dist: tree-sitter-javascript (>=0.25.0)
 Requires-Dist: tree-sitter-python (>=0.23.0)
@@ -141,14 +138,14 @@ Here is a short video:
 5. **Workflow Generator**: Automatically generates customizable CI/CD workflows for Python repositories,
    including unit tests, code formatting, PEP 8 compliance checks, and PyPI publication.
 
-6. **Thesis (VKR) check**: Evaluates a repository against a set of formal criteria (
-   non-empty README, license file, etc.).  It also extracts claims (unique entities such as preprocessing type, model
-   architecture, etc.) from the thesis (VKR) text and matches them against the repository's code.
-   
-7. **Standalone paper claims pipeline**: Extracts technical claims from PDF papers through the reusable
-   `paper_claims` operation and batch utilities. This pipeline is available as a separate module and is not registered
-   in the scheduler yet.
-   
+6. **Repository-quality score**: Evaluates a repository against formal criteria such as a non-empty README and
+   license file. The score is available as part of paper analysis with `--include-repository-quality`.
+
+7. **Paper repository analysis**: The canonical `osa-tool --paper-analysis` mode extracts or resumes typed paper
+   claims and verifies them against a repository. Formal repository-quality scoring is optional through
+   `--include-repository-quality`. With `--delete-dir`, the command removes only a remote clone created by that
+   invocation, never a user-supplied local repository.
+
 ---
 
 ## Installation
@@ -167,12 +164,12 @@ Install optional features when needed:
 # PDF-to-claims extraction and evaluation utilities
 pip install "osa_tool[paper-claims]"
 
-# Legacy graph-based document and paper validation
-pip install "osa_tool[repository-validation]"
+# Add the optional local Marker parser
+pip install "osa_tool[paper-claims,paper-claims-marker]"
 ```
 
-The core package supports Python 3.11 and later. The `paper-claims` PDF conversion workflow currently requires
-Python 3.11--3.14 because its Marker dependency stack is not available for Python 3.15+.
+The core package and remote PDF parsers support Python 3.11 and later. The optional Marker parser requires Python
+3.11--3.14 because its dependency stack is not available for Python 3.15+.
 
 **Build from source:**
 
@@ -225,31 +222,29 @@ docker build --build-arg GIT_USER_NAME="your-user-name" --build-arg GIT_USER_EMA
 
 OSA requires Python 3.11 or higher.
 
-The .env file is required to specify the LLM API key (OPENAI_API_KEY or AUTHORIZATION_KEY) and optionally a Git token.
-The Git token (GIT_TOKEN) may be omitted if you plan to work with a public repository without creating a fork (using the
---no-fork option).
-
-Alternatively, instead of GIT_TOKEN, you can use GITHUB_TOKEN, GITLAB_TOKEN, or GITVERSE_TOKEN for GitHub, GitLab, and
-Gitverse respectively.
-
-When running `osa-tool` from CLI, you need to set the GIT_TOKEN and API key first:
+OSA can be configured in two common ways:
 
 ```sh
-# Linux / macOS (bash/zsh)
-export OPENAI_API_KEY=<your_api_key>
+# Subscription-backed Host LLM provider (api = "host")
+export HOST_LLM_COMMAND=codex
 export GIT_TOKEN=<your_git_token>
 
-# Windows (PowerShell)
-setx OPENAI_API_KEY "<your_api_key>"
-setx GIT_TOKEN "<your_git_token>"
+# OpenAI-compatible API provider (--api openai)
+export OPENAI_API_KEY=<your_api_key>
+export GIT_TOKEN=<your_git_token>
 ```
 
+The Git token (GIT_TOKEN) may be omitted if you plan to work with a public repository without creating a fork (using the
+--no-fork option). Instead of GIT_TOKEN, you can use GITHUB_TOKEN, GITLAB_TOKEN, or GITVERSE_TOKEN for GitHub, GitLab,
+and Gitverse respectively. `AUTHORIZATION_KEY` is only needed when using Gigachat.
+
 ### Tokens
 
 | Token name          | Description                                                                                                                                                                          | Mandatory |
 |---------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------|
 | `GIT_TOKEN`         | Personal GitHub/GitLab/Gitverse token used to clone private repositories, access metadata, and interact with its API.                                                                | Yes       |
-| `OPENAI_API_KEY`    | API key for accessing [OpenAI](https://platform.openai.com/docs/api-reference/introduction), [vsegpt](https://vsegpt.ru/Docs/API) and [openrouter](https://openrouter.ai/) providers | No        |
+| `HOST_LLM_COMMAND`  | Logged-in Codex CLI command used by the subscription-backed `api = "host"` provider (`codex`).                                                                        | No        |
+| `OPENAI_API_KEY`    | API key for accessing [OpenAI](https://platform.openai.com/docs/api-reference/introduction), [vsegpt](https://vsegpt.ru/Docs/API), and [openrouter](https://openrouter.ai/) providers through `--api openai`. | No        |
 | `AUTHORIZATION_KEY` | API key for [gigachat](https://developers.sber.ru/portal/products/gigachat-api) provider                                                                                             | No        |
 | `X-API-Key`         | API key for the [pepy.tech](https://pepy.tech/pepy-api) REST API, used to fetch Python package download statistics                                                                   | No        |
 
@@ -271,6 +266,8 @@ python -m osa_tool.run -r {repository} [--api {api}] [--base-url {base_url}] [--
 docker run --env-file .env {image-name} -r {repository} [--api {api}] [--base-url {base_url}] [--model {model_name}] [--attachment {article}] [--convert-notebooks {notebook_paths}]
 ```
 
+Docker runs default to the OpenAI-compatible API-key provider because the container cannot inherit a logged-in host command from the user's machine. Pass `--api host` only when the container has access to a host command or bridge.
+
 The --attachment option enables you to choose a README template for a repository based on an article. You can provide
 either a link to a PDF file of the article or a path to a local PDF file after the --attachment option. If you are using
 Docker, ensure that you upload the PDF file to the OSA folder before building the image, then, specify the path as
@@ -281,30 +278,34 @@ documentation, see the [Workflow Generator README](./osa_tool/operations/codebas
 
 ### Configuration
 
-| Flag                 | Description                                                                         | Default                        |
-|----------------------|-------------------------------------------------------------------------------------|--------------------------------|
-| `-r`, `--repository` | URL of the GitHub/GitLab/Gitverse repository (**Mandatory**)                        |                                |
-| `-b`, `--branch`     | Branch name of the repository                                                       | Default branch                 |
-| `-o`, `--output`     | Path to the output directory                                                        | Current working directory      |
-| `--api`              | LLM API service provider                                                            | `openai`                       |
-| `--base-url`         | URL of the provider compatible with API OpenAI                                      | `https://openrouter.ai/api/v1` |
-| `--model`            | Specific LLM model to use                                                           | `gpt-3.5-turbo`                |
-| `--top_p`            | Nucleus sampling probability                                                        | `0.95`                         |
-| `--temperature`      | Sampling temperature to use for the LLM output (0 = deterministic, 1 = creative).   | `0.05`                         |
-| `--max_tokens`       | Maximum number of output tokens the model can generate in a single response         | `4096`                         |
-| `--context_window`   | Total number of model context (Input + Output)                                      | `16385`                        |
-| `--attachment`       | Path to a local PDF or .docx file, or a URL to a PDF resource                       | `None`                         |
-| `-m`, `--mode`       | Operation mode for repository processing: `basic`, `auto` (default), or `advanced`. | `auto`                         |
-| `--delete-dir`       | Enable deleting the downloaded repository after processing                          | `disabled`                     |
-| `--no-fork`          | Avoid create fork for target repository                                             | `False`                        |
-| `--no-pull-request`  | Avoid create pull request for target repository                                     | `False`                        |
+| Flag                   | Description                                                                         | Default                        |
+|------------------------|-------------------------------------------------------------------------------------|--------------------------------|
+| `-r`, `--repository`   | URL of the GitHub/GitLab/Gitverse repository (**Mandatory**)                        |                                |
+| `-b`, `--branch`       | Branch name of the repository                                                       | Default branch                 |
+| `--based-on-date`      | Analyse the repository version closest to the given date (forces no fork / no PR)   | `None`                         |
+| `-o`, `--output`       | Path to the output directory                                                        | Current working directory      |
+| `--api`                | LLM API service provider                                                            | `openai`                       |
+| `--base-url`           | URL of the provider compatible with API OpenAI                                      | `https://openrouter.ai/api/v1` |
+| `--model`              | Specific LLM model to use                                                           | `gpt-3.5-turbo`                |
+| `--top-p`              | Nucleus sampling probability                                                        | `0.95`                         |
+| `--temperature`        | Sampling temperature to use for the LLM output (0 = deterministic, 1 = creative).   | `0.05`                         |
+| `--max-tokens`         | Maximum number of output tokens the model can generate in a single response         | `4096`                         |
+| `--context-window`     | Total number of model context (Input + Output)                                      | `16385`                        |
+| `--attachment`         | Path to a local PDF or .docx file, or a URL to a PDF resource                       | `None`                         |
+| `-m`, `--mode`         | Operation mode for repository processing: `basic`, `auto` (default), or `advanced`. | `auto`                         |
+| `--delete-dir`         | Enable deleting the downloaded repository after processing                          | `disabled`                     |
+| `--no-fork`            | Avoid create fork for target repository                                             | `False`                        |
+| `--no-pull-request`    | Avoid create pull request for target repository                                     | `False`                        |
+| `--artefacts-language` | Language for report generation                                                      | `English`                      |
 
 Also OSA supports custom configuration via TOML files. Use the `--config-file` option to specify a path to custom
 configuration file. If no custom configuration file is provided, OSA will use the default configuration.
 
-By default, OSA uses a single model for all tasks (specified via `--model`). If you want to use different models for
-different types of tasks, disable the `--use-single-model` flag and specify models for each task type (
-`--model-docstring`, `--model-readme`, `--model-validation`, `--model-general`).
+OSA uses the shared `[llm]` model settings unless a task-specific profile is configured. Task profiles fall back to the
+shared settings when they do not override a value. The `--use-single-model` flag forces all tasks to use the shared
+`[llm]` settings; omit it to allow task-specific profiles and model flags. Supported task model flags include
+`--model-docstring`, `--model-readme`, `--model-general`, `--model-repository-quality`, `--model-paper-claims`, and
+`--model-paper-verification`. There is no `--model-validation` option in the current CLI.
 
 To learn how to work with the interactive CLI and view descriptions of all available keys, visit
 the [CLI usage guide](./docs/scheduler/index.md).
@@ -318,9 +319,23 @@ Examples of generated README files are available in [examples](./examples).
 URL of the GitHub/GitLab/Gitverse repository, LLM API service provider (*optional*) and Specific LLM model to use
 (*optional*) are required to use the generator.
 
-Supported LLM providers are available as part of the [ProtoLLM](https://github.com/aimclub/ProtoLLM/)
-ecosystem. See the [connectors directory](https://github.com/aimclub/ProtoLLM/tree/main/protollm/connectors) for the
-full list.
+OSA supports the subscription-backed Host LLM provider directly. `HOST_LLM_COMMAND` currently expects the Codex CLI protocol; use the bridge or an API-backed provider when custom generation controls are required. Other LLM providers are available as part of the
+[ProtoLLM](https://github.com/aimclub/ProtoLLM/) ecosystem. See the
+[connectors directory](https://github.com/aimclub/ProtoLLM/tree/main/protollm/connectors) for the full list.
+
+Subscription-backed Host LLM:
+
+```sh
+export HOST_LLM_COMMAND=codex
+python -m osa_tool.run -r https://github.com/aimclub/OSA --api host
+```
+
+OpenAI-compatible API key:
+
+```sh
+export OPENAI_API_KEY=<your_api_key>
+python -m osa_tool.run -r https://github.com/aimclub/OSA --api openai --base-url https://api.openai.com/v1 --model gpt-4o
+```
 
 Local ITMO model:
 

{osa_tool-0.3.0 → osa_tool-0.3.2}/README.md

@@ -77,14 +77,14 @@ Here is a short video:
 5. **Workflow Generator**: Automatically generates customizable CI/CD workflows for Python repositories,
    including unit tests, code formatting, PEP 8 compliance checks, and PyPI publication.
 
-6. **Thesis (VKR) check**: Evaluates a repository against a set of formal criteria (
-   non-empty README, license file, etc.).  It also extracts claims (unique entities such as preprocessing type, model
-   architecture, etc.) from the thesis (VKR) text and matches them against the repository's code.
-   
-7. **Standalone paper claims pipeline**: Extracts technical claims from PDF papers through the reusable
-   `paper_claims` operation and batch utilities. This pipeline is available as a separate module and is not registered
-   in the scheduler yet.
-   
+6. **Repository-quality score**: Evaluates a repository against formal criteria such as a non-empty README and
+   license file. The score is available as part of paper analysis with `--include-repository-quality`.
+
+7. **Paper repository analysis**: The canonical `osa-tool --paper-analysis` mode extracts or resumes typed paper
+   claims and verifies them against a repository. Formal repository-quality scoring is optional through
+   `--include-repository-quality`. With `--delete-dir`, the command removes only a remote clone created by that
+   invocation, never a user-supplied local repository.
+
 ---
 
 ## Installation
@@ -103,12 +103,12 @@ Install optional features when needed:
 # PDF-to-claims extraction and evaluation utilities
 pip install "osa_tool[paper-claims]"
 
-# Legacy graph-based document and paper validation
-pip install "osa_tool[repository-validation]"
+# Add the optional local Marker parser
+pip install "osa_tool[paper-claims,paper-claims-marker]"
 ```
 
-The core package supports Python 3.11 and later. The `paper-claims` PDF conversion workflow currently requires
-Python 3.11--3.14 because its Marker dependency stack is not available for Python 3.15+.
+The core package and remote PDF parsers support Python 3.11 and later. The optional Marker parser requires Python
+3.11--3.14 because its dependency stack is not available for Python 3.15+.
 
 **Build from source:**
 
@@ -161,31 +161,29 @@ docker build --build-arg GIT_USER_NAME="your-user-name" --build-arg GIT_USER_EMA
 
 OSA requires Python 3.11 or higher.
 
-The .env file is required to specify the LLM API key (OPENAI_API_KEY or AUTHORIZATION_KEY) and optionally a Git token.
-The Git token (GIT_TOKEN) may be omitted if you plan to work with a public repository without creating a fork (using the
---no-fork option).
-
-Alternatively, instead of GIT_TOKEN, you can use GITHUB_TOKEN, GITLAB_TOKEN, or GITVERSE_TOKEN for GitHub, GitLab, and
-Gitverse respectively.
-
-When running `osa-tool` from CLI, you need to set the GIT_TOKEN and API key first:
+OSA can be configured in two common ways:
 
 ```sh
-# Linux / macOS (bash/zsh)
-export OPENAI_API_KEY=<your_api_key>
+# Subscription-backed Host LLM provider (api = "host")
+export HOST_LLM_COMMAND=codex
 export GIT_TOKEN=<your_git_token>
 
-# Windows (PowerShell)
-setx OPENAI_API_KEY "<your_api_key>"
-setx GIT_TOKEN "<your_git_token>"
+# OpenAI-compatible API provider (--api openai)
+export OPENAI_API_KEY=<your_api_key>
+export GIT_TOKEN=<your_git_token>
 ```
 
+The Git token (GIT_TOKEN) may be omitted if you plan to work with a public repository without creating a fork (using the
+--no-fork option). Instead of GIT_TOKEN, you can use GITHUB_TOKEN, GITLAB_TOKEN, or GITVERSE_TOKEN for GitHub, GitLab,
+and Gitverse respectively. `AUTHORIZATION_KEY` is only needed when using Gigachat.
+
 ### Tokens
 
 | Token name          | Description                                                                                                                                                                          | Mandatory |
 |---------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------|
 | `GIT_TOKEN`         | Personal GitHub/GitLab/Gitverse token used to clone private repositories, access metadata, and interact with its API.                                                                | Yes       |
-| `OPENAI_API_KEY`    | API key for accessing [OpenAI](https://platform.openai.com/docs/api-reference/introduction), [vsegpt](https://vsegpt.ru/Docs/API) and [openrouter](https://openrouter.ai/) providers | No        |
+| `HOST_LLM_COMMAND`  | Logged-in Codex CLI command used by the subscription-backed `api = "host"` provider (`codex`).                                                                        | No        |
+| `OPENAI_API_KEY`    | API key for accessing [OpenAI](https://platform.openai.com/docs/api-reference/introduction), [vsegpt](https://vsegpt.ru/Docs/API), and [openrouter](https://openrouter.ai/) providers through `--api openai`. | No        |
 | `AUTHORIZATION_KEY` | API key for [gigachat](https://developers.sber.ru/portal/products/gigachat-api) provider                                                                                             | No        |
 | `X-API-Key`         | API key for the [pepy.tech](https://pepy.tech/pepy-api) REST API, used to fetch Python package download statistics                                                                   | No        |
 
@@ -207,6 +205,8 @@ python -m osa_tool.run -r {repository} [--api {api}] [--base-url {base_url}] [--
 docker run --env-file .env {image-name} -r {repository} [--api {api}] [--base-url {base_url}] [--model {model_name}] [--attachment {article}] [--convert-notebooks {notebook_paths}]
 ```
 
+Docker runs default to the OpenAI-compatible API-key provider because the container cannot inherit a logged-in host command from the user's machine. Pass `--api host` only when the container has access to a host command or bridge.
+
 The --attachment option enables you to choose a README template for a repository based on an article. You can provide
 either a link to a PDF file of the article or a path to a local PDF file after the --attachment option. If you are using
 Docker, ensure that you upload the PDF file to the OSA folder before building the image, then, specify the path as
@@ -217,30 +217,34 @@ documentation, see the [Workflow Generator README](./osa_tool/operations/codebas
 
 ### Configuration
 
-| Flag                 | Description                                                                         | Default                        |
-|----------------------|-------------------------------------------------------------------------------------|--------------------------------|
-| `-r`, `--repository` | URL of the GitHub/GitLab/Gitverse repository (**Mandatory**)                        |                                |
-| `-b`, `--branch`     | Branch name of the repository                                                       | Default branch                 |
-| `-o`, `--output`     | Path to the output directory                                                        | Current working directory      |
-| `--api`              | LLM API service provider                                                            | `openai`                       |
-| `--base-url`         | URL of the provider compatible with API OpenAI                                      | `https://openrouter.ai/api/v1` |
-| `--model`            | Specific LLM model to use                                                           | `gpt-3.5-turbo`                |
-| `--top_p`            | Nucleus sampling probability                                                        | `0.95`                         |
-| `--temperature`      | Sampling temperature to use for the LLM output (0 = deterministic, 1 = creative).   | `0.05`                         |
-| `--max_tokens`       | Maximum number of output tokens the model can generate in a single response         | `4096`                         |
-| `--context_window`   | Total number of model context (Input + Output)                                      | `16385`                        |
-| `--attachment`       | Path to a local PDF or .docx file, or a URL to a PDF resource                       | `None`                         |
-| `-m`, `--mode`       | Operation mode for repository processing: `basic`, `auto` (default), or `advanced`. | `auto`                         |
-| `--delete-dir`       | Enable deleting the downloaded repository after processing                          | `disabled`                     |
-| `--no-fork`          | Avoid create fork for target repository                                             | `False`                        |
-| `--no-pull-request`  | Avoid create pull request for target repository                                     | `False`                        |
+| Flag                   | Description                                                                         | Default                        |
+|------------------------|-------------------------------------------------------------------------------------|--------------------------------|
+| `-r`, `--repository`   | URL of the GitHub/GitLab/Gitverse repository (**Mandatory**)                        |                                |
+| `-b`, `--branch`       | Branch name of the repository                                                       | Default branch                 |
+| `--based-on-date`      | Analyse the repository version closest to the given date (forces no fork / no PR)   | `None`                         |
+| `-o`, `--output`       | Path to the output directory                                                        | Current working directory      |
+| `--api`                | LLM API service provider                                                            | `openai`                       |
+| `--base-url`           | URL of the provider compatible with API OpenAI                                      | `https://openrouter.ai/api/v1` |
+| `--model`              | Specific LLM model to use                                                           | `gpt-3.5-turbo`                |
+| `--top-p`              | Nucleus sampling probability                                                        | `0.95`                         |
+| `--temperature`        | Sampling temperature to use for the LLM output (0 = deterministic, 1 = creative).   | `0.05`                         |
+| `--max-tokens`         | Maximum number of output tokens the model can generate in a single response         | `4096`                         |
+| `--context-window`     | Total number of model context (Input + Output)                                      | `16385`                        |
+| `--attachment`         | Path to a local PDF or .docx file, or a URL to a PDF resource                       | `None`                         |
+| `-m`, `--mode`         | Operation mode for repository processing: `basic`, `auto` (default), or `advanced`. | `auto`                         |
+| `--delete-dir`         | Enable deleting the downloaded repository after processing                          | `disabled`                     |
+| `--no-fork`            | Avoid create fork for target repository                                             | `False`                        |
+| `--no-pull-request`    | Avoid create pull request for target repository                                     | `False`                        |
+| `--artefacts-language` | Language for report generation                                                      | `English`                      |
 
 Also OSA supports custom configuration via TOML files. Use the `--config-file` option to specify a path to custom
 configuration file. If no custom configuration file is provided, OSA will use the default configuration.
 
-By default, OSA uses a single model for all tasks (specified via `--model`). If you want to use different models for
-different types of tasks, disable the `--use-single-model` flag and specify models for each task type (
-`--model-docstring`, `--model-readme`, `--model-validation`, `--model-general`).
+OSA uses the shared `[llm]` model settings unless a task-specific profile is configured. Task profiles fall back to the
+shared settings when they do not override a value. The `--use-single-model` flag forces all tasks to use the shared
+`[llm]` settings; omit it to allow task-specific profiles and model flags. Supported task model flags include
+`--model-docstring`, `--model-readme`, `--model-general`, `--model-repository-quality`, `--model-paper-claims`, and
+`--model-paper-verification`. There is no `--model-validation` option in the current CLI.
 
 To learn how to work with the interactive CLI and view descriptions of all available keys, visit
 the [CLI usage guide](./docs/scheduler/index.md).
@@ -254,9 +258,23 @@ Examples of generated README files are available in [examples](./examples).
 URL of the GitHub/GitLab/Gitverse repository, LLM API service provider (*optional*) and Specific LLM model to use
 (*optional*) are required to use the generator.
 
-Supported LLM providers are available as part of the [ProtoLLM](https://github.com/aimclub/ProtoLLM/)
-ecosystem. See the [connectors directory](https://github.com/aimclub/ProtoLLM/tree/main/protollm/connectors) for the
-full list.
+OSA supports the subscription-backed Host LLM provider directly. `HOST_LLM_COMMAND` currently expects the Codex CLI protocol; use the bridge or an API-backed provider when custom generation controls are required. Other LLM providers are available as part of the
+[ProtoLLM](https://github.com/aimclub/ProtoLLM/) ecosystem. See the
+[connectors directory](https://github.com/aimclub/ProtoLLM/tree/main/protollm/connectors) for the full list.
+
+Subscription-backed Host LLM:
+
+```sh
+export HOST_LLM_COMMAND=codex
+python -m osa_tool.run -r https://github.com/aimclub/OSA --api host
+```
+
+OpenAI-compatible API key:
+
+```sh
+export OPENAI_API_KEY=<your_api_key>
+python -m osa_tool.run -r https://github.com/aimclub/OSA --api openai --base-url https://api.openai.com/v1 --model gpt-4o
+```
 
 Local ITMO model:
 

osa_tool-0.3.2/osa_tool/config/locales/english.toml

@@ -0,0 +1,168 @@
+language = "English"
+
+[translations]
+report_header = "Repository Analysis Report"
+statistics = "Statistics"
+values = "Values"
+stars_count = "Stars Count"
+forks_count = "Forks Count"
+issues_count = "Issues Count"
+metric = "Metric"
+readme_presence = "README Presence"
+license_presence = "License Presence"
+documentation_presence = "Documentation Presence"
+examples_presence = "Examples Presence"
+requirements_presence = "Requirements Presence"
+tests_presence = "Tests Presence"
+description_presence = "Description Presence"
+repository_name = "Repository Name"
+owner = "Owner"
+created_at = "Created at"
+repository_structure = "Repository Structure"
+compliance = "Compliance"
+missing_files = "Missing Files"
+organization = "Organization"
+readme_analysis = "README Analysis"
+quality = "Quality"
+documentation = "Documentation"
+test_present = "Test present"
+documentation_quality = "Document quality"
+outdated_content = "Outdated content"
+key_shortcomings = "Key Shortcomings"
+recommendations = "Recommendations"
+readme_quality = "text"
+project_description = "Project description"
+installation = "Installation"
+usage_examples = "Usage examples"
+contribution_guidelines = "Contribution guidelines"
+license_specified = "License specified"
+badges_present = "Badges present"
+summary_header = "OSA Work Summary"
+what_have_been_done = "What have been done"
+report_by_tasks = "Report by tasks"
+yes = "Yes"
+no = "No"
+partial = "Partial"
+report = "Report"
+translate_dirs = "Translate dirs"
+convert_notebooks = "Convert notebooks"
+translate_readme = "Translate readme"
+ensure_license = "Ensure license"
+community_docs = "Community docs"
+docstring = "Docstring"
+ignore_list = "Ignore list"
+incremental = "Incremental"
+target_files = "Target files"
+readme = "Readme"
+refine_readme = "Refine readme"
+requirements = "Requirements"
+organize = "Organize"
+about = "About"
+validate_paper = "Validate paper"
+validate_doc = "Validate doc"
+author = "Author"
+generate_workflows = "Generate workflows"
+include_tests = "Include tests"
+include_black = "Include black"
+include_pep8 = "Include pep8"
+include_autopep8 = "Include autopep8"
+include_fix_pep8 = "Include fix pep8"
+include_pypi = "Include pypi"
+python_versions = "Python versions"
+pep8_tool = "Pep8 tool"
+use_poetry = "Use poetry"
+include_codecov = "Include codecov"
+unknown = "Unknown"
+for = "for"
+
+# Notebook Analysis Report
+notebook_report_header = "Notebook Analysis Report"
+notebook_summary = "Notebook Summary"
+value = "Value"
+quality_signals = "Quality Signals"
+total_notebooks_scanned = "Total notebooks scanned"
+total_findings = "Total findings"
+successfully_analyzed = "Successfully analyzed"
+invalid_syntax_notebooks = "Invalid syntax notebooks"
+read_or_parse_failures = "Read or parse failures"
+fully_non_executed_notebooks = "Fully non-executed notebooks"
+notebooks_with_findings = "Notebooks with findings"
+analysis_scope = "Analysis scope"
+repository_wide = "Repository-wide"
+overview = "Overview"
+notebook_overview_text = "This report reviewed <b>{total_notebooks}</b> notebook(s) and recorded <b>{total_issues}</b> finding(s) across structure, execution, and readability."
+notebook_explicit_targets = "Selected targets were provided explicitly: <b>{count}</b> path(s)."
+notebook_full_scan = "Scope: full repository notebook scan."
+most_frequent_findings = "Most Frequent Findings"
+notebook_details = "Notebook Details"
+status_label = "Status"
+analysis_errors_present = "analysis errors present"
+finding_count = "{count} finding(s)"
+no_findings_detected = "no findings detected"
+cells_line = "Cells: total <b>{total}</b>, code {code}, markdown {markdown}, raw {raw}"
+markdown_line = "Markdown lines {lines}, titles {titles}, functions {functions}, classes {classes}"
+analysis_error_line = "Analysis error: {error}"
+no_notebook_issues = "No notebook issues detected."
+recommendation_label = "Recommendation"
+
+# Notebook issue catalog (keyed by NotebookReportAnalyzer's slug).
+# NOTE: the "notebook-too-long" text below bakes in the current _MAX_CELLS_IN_NOTEBOOK
+# threshold (50); update both locales together if that constant ever changes.
+"notebook_issue_non-linear-execution_description" = "Notebook cells were executed in a non-linear order."
+"notebook_issue_non-linear-execution_recommendation" = "Re-run your notebook top to bottom to ensure it is reproducible."
+"notebook_issue_notebook-too-long_description" = "Notebook contains more than 50 cells."
+"notebook_issue_notebook-too-long_recommendation" = "Split this notebook into two or more notebooks."
+"notebook_issue_imports-beyond-first-cell_description" = "Import statements were found beyond the first code cell."
+"notebook_issue_imports-beyond-first-cell_recommendation" = "Move import statements to the first code cell to make your notebook dependencies more explicit."
+"notebook_issue_missing-h1-heading_description" = "Initial cells do not contain an H1 markdown heading."
+"notebook_issue_missing-h1-heading_recommendation" = "Clarify the notebook subject by writing an H1 Markdown heading in one of the initial cells of your notebook."
+"notebook_issue_missing-opening-markdown_description" = "Initial notebook cells do not contain descriptive markdown text."
+"notebook_issue_missing-opening-markdown_recommendation" = "Begin your notebook by describing what you intend to do in one or more introductory Markdown cells."
+"notebook_issue_missing-closing-markdown_description" = "Final notebook cells do not contain descriptive markdown text."
+"notebook_issue_missing-closing-markdown_recommendation" = "Conclude your notebook by describing what you have accomplished in one or more concluding Markdown cells."
+"notebook_issue_too-few-markdown-cells_description" = "Notebook contains too few markdown cells relative to code cells."
+"notebook_issue_too-few-markdown-cells_recommendation" = "Describe the steps of your computation by adding a few more Markdown cells."
+"notebook_issue_invalid-python-syntax_description" = "Notebook contains invalid Python syntax in exported code."
+"notebook_issue_invalid-python-syntax_recommendation" = "Fix syntax errors in the notebook code cells."
+"notebook_issue_non-executed-notebook_description" = "All code cells appear to be non-executed."
+"notebook_issue_non-executed-notebook_recommendation" = "Before committing, run your notebook top to bottom to ensure that all cells are executed."
+"notebook_issue_non-executed-cells_description" = "Notebook contains non-executed code cells."
+"notebook_issue_non-executed-cells_recommendation" = "Re-run your notebook top to bottom to ensure that all cells are executed."
+"notebook_issue_empty-cells_description" = "Notebook contains empty code cells."
+"notebook_issue_empty-cells_recommendation" = "Keep your notebook clean by deleting unused cells."
+"notebook_issue_long-multiline-python-comment_description" = "Notebook contains long multiline Python comments inside code cells."
+"notebook_issue_long-multiline-python-comment_recommendation" = "For improved notebook readability, prefer using Markdown formatted text to long multiline Python comments."
+"notebook_issue_cell-too-long_description" = "Notebook contains long code cells."
+"notebook_issue_cell-too-long_recommendation" = "Consider consolidating your code outside the notebook by moving utility functions to a structured and tested codebase.\nUse notebooks to display results, not to compute them."
+"notebook_issue_untitled-notebook_description" = "Notebook still uses a default Untitled name."
+"notebook_issue_untitled-notebook_recommendation" = "Give it a meaningful title to make it easy to recognize."
+"notebook_issue_non-portable-chars-in-name_description" = "Notebook filename contains non-portable characters."
+"notebook_issue_non-portable-chars-in-name_recommendation" = "Rename your notebook by using characters contained in the following portable charset: [A-Za-z0-9_.-]."
+"notebook_issue_duplicate-notebook-not-renamed_description" = "Notebook looks like a duplicate copy that was not renamed."
+"notebook_issue_duplicate-notebook-not-renamed_recommendation" = "Give it a meaningful title to make it easy to recognize."
+
+# Notebook issue short labels (used in the "Most Frequent Findings" list).
+"notebook_issue_non-linear-execution_label" = "Non-linear execution"
+"notebook_issue_notebook-too-long_label" = "Notebook too long"
+"notebook_issue_imports-beyond-first-cell_label" = "Imports beyond first cell"
+"notebook_issue_missing-h1-heading_label" = "Missing H1 heading"
+"notebook_issue_missing-opening-markdown_label" = "Missing opening markdown"
+"notebook_issue_missing-closing-markdown_label" = "Missing closing markdown"
+"notebook_issue_too-few-markdown-cells_label" = "Too few markdown cells"
+"notebook_issue_invalid-python-syntax_label" = "Invalid Python syntax"
+"notebook_issue_non-executed-notebook_label" = "Non-executed notebook"
+"notebook_issue_non-executed-cells_label" = "Non-executed cells"
+"notebook_issue_empty-cells_label" = "Empty cells"
+"notebook_issue_long-multiline-python-comment_label" = "Long multiline Python comment"
+"notebook_issue_cell-too-long_label" = "Cell too long"
+"notebook_issue_untitled-notebook_label" = "Untitled notebook"
+"notebook_issue_non-portable-chars-in-name_label" = "Non-portable characters in name"
+"notebook_issue_duplicate-notebook-not-renamed_label" = "Duplicate notebook not renamed"
+
+# Notebook issue "details" fragments (only slugs that carry dynamic details_kwargs).
+"notebook_issue_notebook-too-long_details" = "Detected {count} cells."
+"notebook_issue_too-few-markdown-cells_details" = "Markdown/code ratio is {ratio:.2f}."
+"notebook_issue_non-executed-cells_details" = "{count} code cell(s) are non-executed."
+"notebook_issue_empty-cells_details" = "{count} empty code cell(s) detected."
+"notebook_issue_long-multiline-python-comment_details" = "{count} code cell(s) contain long comment blocks."
+"notebook_issue_cell-too-long_details" = "{count} code cell(s) exceed {limit} lines."