unique_toolkit 1.45.0__tar.gz → 1.45.2__tar.gz

{unique_toolkit-1.45.0 → unique_toolkit-1.45.2}/CHANGELOG.md

@@ -5,6 +5,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), 
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.45.2] - 2026-01-26
+- Make FileMimeType backwards compatible with legacy extensions
+
+## [1.45.1] - 2026-01-26
+- Add FileMimeType utility helpers
+
 ## [1.45.0] - 2026-01-23
 - Remove unused code execution options from config
 

{unique_toolkit-1.45.0 → unique_toolkit-1.45.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unique_toolkit
-Version: 1.45.0
+Version: 1.45.2
 Summary: 
 License: Proprietary
 Author: Cedric Klinkert
@@ -125,6 +125,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), 
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.45.2] - 2026-01-26
+- Make FileMimeType backwards compatible with legacy extensions
+
+## [1.45.1] - 2026-01-26
+- Add FileMimeType utility helpers
+
 ## [1.45.0] - 2026-01-23
 - Remove unused code execution options from config
 

{unique_toolkit-1.45.0 → unique_toolkit-1.45.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "unique_toolkit"
-version = "1.45.0"
+version = "1.45.2"
 description = ""
 authors = [
     "Cedric Klinkert <cedric.klinkert@unique.ch>",

unique_toolkit-1.45.2/unique_toolkit/_common/utils/files.py

@@ -0,0 +1,126 @@
+from __future__ import annotations
+
+import mimetypes
+from enum import StrEnum
+from pathlib import Path
+
+
+class FileMimeType(StrEnum):
+    PDF = "application/pdf"
+    DOCX = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+    DOC = "application/msword"
+    # TODO: clean up duplicates and make the monolith compatible with this.
+    XLSX = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+    MSEXCEL = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+    XLS = "application/vnd.ms-excel"
+    EXCEL = "application/vnd.ms-excel"
+    PPT = "application/vnd.ms-powerpoint"
+    PPTX = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
+    MSPPT = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
+    CSV = "text/csv"
+    HTML = "text/html"
+    MD = "text/markdown"
+    TXT = "text/plain"
+    JSON = "application/json"
+
+    @classmethod
+    def get_mime_from_file_path(cls, filepath: Path) -> "FileMimeType | None":
+        mime_type, _ = mimetypes.guess_type(filepath)
+        if mime_type is None:
+            return None
+        try:
+            return cls(mime_type)
+        except ValueError:
+            return None
+
+    @classmethod
+    def is_docx_mime(cls, filepath: Path) -> bool:
+        mime_type = cls.get_mime_from_file_path(filepath)
+        return mime_type in {cls.DOCX, cls.DOC}
+
+    @classmethod
+    def is_pdf_mime(cls, filepath: Path) -> bool:
+        mime_type = cls.get_mime_from_file_path(filepath)
+        return mime_type == cls.PDF
+
+    @classmethod
+    def is_xlsx_mime(cls, filepath: Path) -> bool:
+        mime_type = cls.get_mime_from_file_path(filepath)
+        return mime_type in {cls.XLSX, cls.XLS, cls.MSEXCEL, cls.EXCEL}
+
+    @classmethod
+    def is_pptx_mime(cls, filepath: Path) -> bool:
+        mime_type = cls.get_mime_from_file_path(filepath)
+        return mime_type in {cls.PPTX, cls.PPT, cls.MSPPT}
+
+    @classmethod
+    def is_json_mime(cls, filepath: Path) -> bool:
+        mime_type = cls.get_mime_from_file_path(filepath)
+        return mime_type == cls.JSON
+
+    @classmethod
+    def is_valid_mime(cls, filepath: Path, valid_mimes: list[FileMimeType]) -> bool:
+        mime_type = cls.get_mime_from_file_path(filepath)
+        return mime_type in valid_mimes
+
+
+def get_common_name(extension: FileMimeType) -> str:
+    match extension:
+        case FileMimeType.DOCX | FileMimeType.DOC:
+            return "docx"
+        case (
+            FileMimeType.XLSX
+            | FileMimeType.XLS
+            | FileMimeType.MSEXCEL
+            | FileMimeType.EXCEL
+        ):
+            return "excel"
+        case FileMimeType.PPT | FileMimeType.PPTX | FileMimeType.MSPPT:
+            return "powerpoint"
+        case FileMimeType.PDF:
+            return "pdf"
+        case FileMimeType.JSON:
+            return "json"
+        case FileMimeType.CSV:
+            return "csv"
+        case FileMimeType.TXT:
+            return "text"
+        case FileMimeType.MD:
+            return "markdown"
+        case FileMimeType.HTML:
+            return "html"
+        case _:
+            return "unknown"
+
+
+def get_file_extensions(mimes: list[FileMimeType]) -> list[str]:
+    types = [mimetypes.guess_extension(mime) for mime in mimes]
+    return [t for t in types if t]
+
+
+class ImageMimeType(StrEnum):
+    JPEG = "image/jpeg"
+    PNG = "image/png"
+    GIF = "image/gif"
+    BMP = "image/bmp"
+    WEBP = "image/webp"
+    TIFF = "image/tiff"
+    SVG = "image/svg+xml"
+
+
+def is_file_content(filename: str) -> bool:
+    mimetype, _ = mimetypes.guess_type(filename)
+
+    if not mimetype:
+        return False
+
+    return mimetype in FileMimeType.__members__.values()
+
+
+def is_image_content(filename: str) -> bool:
+    mimetype, _ = mimetypes.guess_type(filename)
+
+    if not mimetype:
+        return False
+
+    return mimetype in ImageMimeType.__members__.values()

{unique_toolkit-1.45.0 → unique_toolkit-1.45.2}/unique_toolkit/agentic/history_manager/history_construction_with_contents.py

@@ -10,6 +10,7 @@ from pydantic import RootModel
 from unique_toolkit._common.token.token_counting import (
     num_tokens_per_language_model_message,
 )
+from unique_toolkit._common.utils import files as FileUtils
 from unique_toolkit.app import ChatEventUserMessage
 from unique_toolkit.chat.schemas import ChatMessage
 from unique_toolkit.chat.schemas import ChatMessageRole as ChatRole
@@ -29,29 +30,6 @@ map_chat_llm_message_role = {
 }
 
 
-class ImageMimeType(StrEnum):
-    JPEG = "image/jpeg"
-    PNG = "image/png"
-    GIF = "image/gif"
-    BMP = "image/bmp"
-    WEBP = "image/webp"
-    TIFF = "image/tiff"
-    SVG = "image/svg+xml"
-
-
-class FileMimeType(StrEnum):
-    PDF = "application/pdf"
-    DOCX = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    DOC = "application/msword"
-    XLSX = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
-    XLS = "application/vnd.ms-excel"
-    PPTX = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
-    CSV = "text/csv"
-    HTML = "text/html"
-    MD = "text/markdown"
-    TXT = "text/plain"
-
-
 class ChatMessageWithContents(ChatMessage):
     contents: list[Content] = []
 
@@ -93,24 +71,6 @@ class ChatHistoryWithContent(RootModel):
         return self.root[item]
 
 
-def is_image_content(filename: str) -> bool:
-    mimetype, _ = mimetypes.guess_type(filename)
-
-    if not mimetype:
-        return False
-
-    return mimetype in ImageMimeType.__members__.values()
-
-
-def is_file_content(filename: str) -> bool:
-    mimetype, _ = mimetypes.guess_type(filename)
-
-    if not mimetype:
-        return False
-
-    return mimetype in FileMimeType.__members__.values()
-
-
 def get_chat_history_with_contents(
     user_message: ChatEventUserMessage,
     chat_id: str,
@@ -152,7 +112,7 @@ def download_encoded_images(
 ) -> list[str]:
     base64_encoded_images = []
     for im in contents:
-        if is_image_content(im.key):
+        if FileUtils.is_image_content(im.key):
             try:
                 file_bytes = content_service.download_content_to_bytes(
                     content_id=im.id,
@@ -224,8 +184,12 @@ def get_full_history_with_contents(
             text = ""
 
         if len(c.contents) > 0:
-            file_contents = [co for co in c.contents if is_file_content(co.key)]
-            image_contents = [co for co in c.contents if is_image_content(co.key)]
+            file_contents = [
+                co for co in c.contents if FileUtils.is_file_content(co.key)
+            ]
+            image_contents = [
+                co for co in c.contents if FileUtils.is_image_content(co.key)
+            ]
 
             content = (
                 text

unique_toolkit-1.45.0/unique_toolkit/_common/utils/files.py

@@ -1,43 +0,0 @@
-import mimetypes
-from enum import StrEnum
-
-
-class FileMimeType(StrEnum):
-    PDF = "application/pdf"
-    DOCX = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    DOC = "application/msword"
-    XLSX = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
-    XLS = "application/vnd.ms-excel"
-    PPTX = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
-    CSV = "text/csv"
-    HTML = "text/html"
-    MD = "text/markdown"
-    TXT = "text/plain"
-
-
-class ImageMimeType(StrEnum):
-    JPEG = "image/jpeg"
-    PNG = "image/png"
-    GIF = "image/gif"
-    BMP = "image/bmp"
-    WEBP = "image/webp"
-    TIFF = "image/tiff"
-    SVG = "image/svg+xml"
-
-
-def is_file_content(filename: str) -> bool:
-    mimetype, _ = mimetypes.guess_type(filename)
-
-    if not mimetype:
-        return False
-
-    return mimetype in FileMimeType.__members__.values()
-
-
-def is_image_content(filename: str) -> bool:
-    mimetype, _ = mimetypes.guess_type(filename)
-
-    if not mimetype:
-        return False
-
-    return mimetype in ImageMimeType.__members__.values()