tumblrbot 1.1.5__tar.gz → 1.2.1__tar.gz

{tumblrbot-1.1.5 → tumblrbot-1.2.1}/.gitignore

@@ -1,3 +1,8 @@
+# Custom
+data
+*.toml
+*.json*
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[codz]
@@ -207,9 +212,4 @@ marimo/_lsp/
 __marimo__/
 
 # Streamlit
-.streamlit/secrets.toml
-
-# Custom
-data
-*.toml
-*.jsonl
+.streamlit/secrets.toml

{tumblrbot-1.1.5 → tumblrbot-1.2.1}/PKG-INFO

@@ -1,9 +1,10 @@
 Metadata-Version: 2.4
 Name: tumblrbot
-Version: 1.1.5
+Version: 1.2.1
 Summary: An updated bot that posts to Tumblr, based on your very own blog!
 Requires-Python: >= 3.13
 Description-Content-Type: text/markdown
+Requires-Dist: keyring
 Requires-Dist: more-itertools
 Requires-Dist: openai
 Requires-Dist: pydantic
@@ -61,6 +62,7 @@ This fork is largely a rewrite of the source code with similarities in its struc
       - Added the option to [Download] the latest posts from the [specified blogs][Settings].
       - Added the option to remove posts flagged by the [Moderation API].
       - Added the option to automatically [Fine-Tune] the examples on the [specified base model][Settings].
+      - Added the ability to add custom prompts and responses to the example data.
       - Changed to now escape examples automatically.
       - Set encoding for reading post data to `UTF-8` to fix decoding errors.
       - Added newlines between paragraphs.
@@ -83,7 +85,6 @@ To-Do:
 - Add documentation.
 - Finish updating [README.md].
 - Change the differences list to instead just be a list of features.
-- Allow adding arbitrary data to examples.
 
 
 **Please submit an issue or contact us for features you want to added/reimplemented.**

{tumblrbot-1.1.5 → tumblrbot-1.2.1}/README.md

@@ -44,6 +44,7 @@ This fork is largely a rewrite of the source code with similarities in its struc
       - Added the option to [Download] the latest posts from the [specified blogs][Settings].
       - Added the option to remove posts flagged by the [Moderation API].
       - Added the option to automatically [Fine-Tune] the examples on the [specified base model][Settings].
+      - Added the ability to add custom prompts and responses to the example data.
       - Changed to now escape examples automatically.
       - Set encoding for reading post data to `UTF-8` to fix decoding errors.
       - Added newlines between paragraphs.
@@ -66,7 +67,6 @@ To-Do:
 - Add documentation.
 - Finish updating [README.md].
 - Change the differences list to instead just be a list of features.
-- Allow adding arbitrary data to examples.
 
 
 **Please submit an issue or contact us for features you want to added/reimplemented.**

{tumblrbot-1.1.5 → tumblrbot-1.2.1}/pyproject.toml

@@ -1,10 +1,11 @@
 [project]
 name = "tumblrbot"
-version = "1.1.5"
+version = "1.2.1"
 description = "An updated bot that posts to Tumblr, based on your very own blog!"
 readme = "README.md"
 requires-python = ">= 3.13"
 dependencies = [
+  "keyring",
   "more-itertools",
   "openai",
   "pydantic",

{tumblrbot-1.1.5 → tumblrbot-1.2.1}/src/tumblrbot/flow/examples.py

@@ -1,8 +1,10 @@
 from collections.abc import Generator
 from dataclasses import dataclass
+from json import loads
 from math import ceil
 from pathlib import Path
 from re import search
+from typing import IO
 
 import rich
 from more_itertools import chunked
@@ -76,17 +78,40 @@ class ExamplesWriter(UtilClass):
         else:
             yield from posts
 
+    def get_custom_prompts(self) -> Generator[tuple[str, str]]:
+        if self.config.custom_prompts_file.exists():
+            text = self.config.custom_prompts_file.read_text(encoding="utf_8")
+            yield from loads(text).items()
+
     def write_examples(self) -> None:
         self.config.examples_file.parent.mkdir(parents=True, exist_ok=True)
+
         with self.config.examples_file.open("w", encoding="utf_8") as fp:
             for post in self.get_filtered_posts():
-                example = Example(
-                    messages=[
-                        Example.Message(role="developer", content=self.config.developer_message),
-                        Example.Message(role="user", content=self.config.user_input),
-                        Example.Message(role="assistant", content=post.get_text_content()),
-                    ],
+                self.write_example(
+                    None,
+                    post.get_text_content(),
+                    fp,
+                )
+
+            for user_message, assistant_response in self.get_custom_prompts():
+                self.write_example(
+                    user_message,
+                    assistant_response,
+                    fp,
                 )
-                fp.write(f"{example.model_dump_json()}\n")
 
         rich.print(f"[bold]The examples file can be found at: '{self.config.examples_file}'\n")
+
+    def write_example(self, user_input: str | None, assistant_message: str, fp: IO[str]) -> None:
+        example = Example(
+            messages=[
+                Example.Message(role="developer", content=self.config.developer_message),
+                Example.Message(role="assistant", content=assistant_message),
+            ],
+        )
+
+        if user_input:
+            example.messages.insert(1, Example.Message(role="user", content=user_input))
+
+        fp.write(f"{example.model_dump_json()}\n")

{tumblrbot-1.1.5 → tumblrbot-1.2.1}/src/tumblrbot/flow/generate.py

@@ -21,7 +21,7 @@ class DraftGenerator(UtilClass):
 
     def generate_content(self) -> Post.Block:
         content = self.openai.responses.create(
-            input=self.config.user_input,
+            input=self.config.user_message,
             instructions=self.config.developer_message,
             model=self.config.fine_tuned_model,
         ).output_text

{tumblrbot-1.1.5 → tumblrbot-1.2.1}/src/tumblrbot/utils/models.py

@@ -23,7 +23,7 @@ class Post(FullyValidatedModel):
         blocks: list[int] = []  # noqa: RUF012
 
     timestamp: SkipJsonSchema[int] = 0
-    tags: Annotated[SkipJsonSchema[list[str]], PlainSerializer(",".join)] = []  # noqa: RUF012
+    tags: Annotated[list[str], PlainSerializer(",".join)] = []  # noqa: RUF012
     state: SkipJsonSchema[Literal["published", "queued", "draft", "private", "unapproved"]] = "published"
 
     content: SkipJsonSchema[list[Block]] = []  # noqa: RUF012

{tumblrbot-1.1.5 → tumblrbot-1.2.1}/src/tumblrbot/utils/settings.py

@@ -1,63 +1,28 @@
+import json
 from collections.abc import Generator, Sequence
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Self, override
+from typing import TYPE_CHECKING, Any, ClassVar, Self, override
 
 import rich
+import tomlkit
+from keyring import get_password, set_password
 from openai.types import ChatModel
 from pydantic import Field, PositiveFloat, PositiveInt, Secret, model_validator
 from pydantic_settings import BaseSettings, PydanticBaseSettingsSource, SettingsConfigDict, TomlConfigSettingsSource
-from rich.prompt import Prompt
-from tomlkit import comment, document, dumps  # pyright: ignore[reportUnknownVariableType]
+from requests_oauthlib import OAuth2Session
+from rich.prompt import Confirm, Prompt
+from tomlkit import comment, document
 
 if TYPE_CHECKING:
     from _typeshed import StrPath
 
 
-class TOMLSettings(BaseSettings):
+class Config(BaseSettings):
     model_config = SettingsConfigDict(
         extra="ignore",
         validate_assignment=True,
         validate_return=True,
         validate_by_name=True,
-    )
-
-    @override
-    @classmethod
-    def settings_customise_sources(cls, settings_cls: type[BaseSettings], *args: PydanticBaseSettingsSource, **kwargs: PydanticBaseSettingsSource) -> tuple[PydanticBaseSettingsSource, ...]:
-        return (TomlConfigSettingsSource(settings_cls),)
-
-    @model_validator(mode="after")
-    def write_to_file(self) -> Self:
-        # Make sure to call this if updating values in nested models.
-        toml_files = self.model_config.get("toml_file")
-        if isinstance(toml_files, (Path, str)):
-            self.dump_toml(toml_files)
-        elif isinstance(toml_files, Sequence):
-            for toml_file in toml_files:
-                self.dump_toml(toml_file)
-
-        return self
-
-    def dump_toml(self, toml_file: "StrPath") -> None:
-        toml_table = document()
-
-        dumped_model = self.model_dump(mode="json")
-        for name, field in self.__class__.model_fields.items():
-            if field.description:
-                for line in field.description.split(". "):
-                    toml_table.add(comment(f"{line.removesuffix('.')}."))
-
-            value = getattr(self, name)
-            toml_table[name] = value.get_secret_value() if isinstance(value, Secret) else dumped_model[name]
-
-        Path(toml_file).write_text(
-            dumps(toml_table),
-            encoding="utf_8",
-        )
-
-
-class Config(TOMLSettings):
-    model_config = SettingsConfigDict(
         cli_parse_args=True,
         cli_avoid_json=True,
         cli_kebab_case=True,
@@ -77,6 +42,7 @@ class Config(TOMLSettings):
         description="The identifiers of the blogs which post data will be downloaded from. These must be blogs associated with the same account as the configured Tumblr secret tokens.",
     )
     data_directory: Path = Field(Path("data"), description="Where to store downloaded post data.")
+    custom_prompts_file: Path = Field(Path("custom_prompts.json"), description="Where to read in custom prompts from.")
     examples_file: Path = Field(Path("examples.jsonl"), description="Where to output the examples that will be used to fine-tune the model.")
     job_id: str = Field("", description="The fine-tuning job ID that will be polled on next run.")
     expected_epochs: PositiveInt = Field(3, description="The expected number of epochs fine-tuning will be run for. This will be updated during fine-tuning.")
@@ -84,12 +50,15 @@ class Config(TOMLSettings):
 
     base_model: ChatModel = Field("gpt-4.1-nano-2025-04-14", description="The name of the model that will be fine-tuned by the generated training data.")
     developer_message: str = Field("You are a Tumblr post bot. Please generate a Tumblr post in accordance with the user's request.", description="The developer message used by the OpenAI API to generate drafts.")
-    user_input: str = Field("Please write a comical Tumblr post.", description="The user input used by the OpenAI API to generate drafts.")
+    user_message: str = Field("Please write a comical Tumblr post.", description="The user input used by the OpenAI API to generate drafts.")
 
     @override
-    def model_post_init(self, context: object) -> None:
-        super().model_post_init(context)
+    @classmethod
+    def settings_customise_sources(cls, settings_cls: type[BaseSettings], *args: PydanticBaseSettingsSource, **kwargs: PydanticBaseSettingsSource) -> tuple[PydanticBaseSettingsSource, ...]:
+        return (TomlConfigSettingsSource(settings_cls),)
 
+    @model_validator(mode="after")
+    def write_to_file(self) -> Self:
         if not self.download_blog_identifiers:
             rich.print("Enter the [cyan]identifiers of your blogs[/] that data should be [bold purple]downloaded[/] from, separated by commas.")
             self.download_blog_identifiers = list(map(str.strip, Prompt.ask("[bold]Example: staff.tumblr.com,changes").split(",")))
@@ -98,12 +67,38 @@ class Config(TOMLSettings):
             rich.print("Enter the [cyan]identifier of your blog[/] that drafts should be [bold purple]uploaded[/] to.")
             self.upload_blog_identifier = Prompt.ask("[bold]Examples: staff.tumblr.com or changes").strip()
 
+        toml_files = self.model_config.get("toml_file")
+        if isinstance(toml_files, (Path, str)):
+            self.dump_toml(toml_files)
+        elif isinstance(toml_files, Sequence):
+            for toml_file in toml_files:
+                self.dump_toml(toml_file)
 
-class Tokens(TOMLSettings):
+        return self
+
+    def dump_toml(self, toml_file: "StrPath") -> None:
+        toml_table = document()
+
+        dumped_model = self.model_dump(mode="json")
+        for name, field in self.__class__.model_fields.items():
+            if field.description:
+                for line in field.description.split(". "):
+                    toml_table.add(comment(f"{line.removesuffix('.')}."))
+
+            value = getattr(self, name)
+            toml_table[name] = value.get_secret_value() if isinstance(value, Secret) else dumped_model[name]
+
+        Path(toml_file).write_text(
+            tomlkit.dumps(toml_table),  # pyright: ignore[reportUnknownMemberType]
+            encoding="utf_8",
+        )
+
+
+class Tokens(BaseSettings):
+    service_name: ClassVar = "tumblrbot"
     model_config = SettingsConfigDict(toml_file="env.toml")
 
     openai_api_key: Secret[str] = Secret("")
-
     tumblr_client_id: Secret[str] = Secret("")
     tumblr_client_secret: Secret[str] = Secret("")
     tumblr_token: Secret[Any] = Secret({})
@@ -124,8 +119,43 @@ class Tokens(TOMLSettings):
     def model_post_init(self, context: object) -> None:
         super().model_post_init(context)
 
-        if not self.openai_api_key.get_secret_value():
+        for name, _ in self:
+            if value := get_password(self.service_name, name):
+                setattr(self, name, Secret(json.loads(value)))
+
+    @model_validator(mode="after")
+    def write_to_keyring(self) -> Self:
+        if not self.openai_api_key.get_secret_value() or Confirm.ask("Reset OpenAI API key?", default=False):
             (self.openai_api_key,) = self.online_token_prompt("https://platform.openai.com/api-keys", "API key")
 
-        if not (self.tumblr_client_id.get_secret_value() and self.tumblr_client_secret.get_secret_value()):
+        if not all(
+            map(
+                Secret[Any].get_secret_value,
+                [
+                    self.tumblr_client_id,
+                    self.tumblr_client_secret,
+                    self.tumblr_token,
+                ],
+            ),
+        ) or Confirm.ask("Reset Tumblr API tokens?", default=False):
             self.tumblr_client_id, self.tumblr_client_secret = self.online_token_prompt("https://tumblr.com/oauth/apps", "consumer key", "consumer secret")
+
+            oauth = OAuth2Session(
+                self.tumblr_client_id.get_secret_value(),
+                scope=["basic", "write", "offline_access"],
+            )
+            authorization_url, _ = oauth.authorization_url("https://tumblr.com/oauth2/authorize")  # pyright: ignore[reportUnknownMemberType]
+            rich.print(f"Please go to {authorization_url} and authorize access.")
+            self.tumblr_token = Secret(
+                oauth.fetch_token(  # pyright: ignore[reportUnknownMemberType]
+                    "https://api.tumblr.com/v2/oauth2/token",
+                    authorization_response=Prompt.ask("Enter the full callback URL"),
+                    client_secret=self.tumblr_client_secret.get_secret_value(),
+                ),
+            )
+
+        for name, value in self:
+            if isinstance(value, Secret):
+                set_password(self.service_name, name, json.dumps(value.get_secret_value()))
+
+        return self

{tumblrbot-1.1.5 → tumblrbot-1.2.1}/src/tumblrbot/utils/tumblr.py

@@ -1,11 +1,8 @@
 from dataclasses import dataclass
-from typing import Self
 
-import rich
 from pydantic import Secret
 from requests import HTTPError, Response
 from requests_oauthlib import OAuth2Session
-from rich.prompt import Prompt
 
 from tumblrbot.utils.models import Post
 from tumblrbot.utils.settings import Tokens
@@ -22,35 +19,14 @@ class TumblrClient(OAuth2Session):
             auto_refresh_kwargs={
                 "client_id": self.tokens.tumblr_client_id.get_secret_value(),
                 "client_secret": self.tokens.tumblr_client_secret.get_secret_value(),
-                "token": self.tokens.tumblr_token.get_secret_value(),
             },
-            scope=["basic", "write", "offline_access"],
             token=self.tokens.tumblr_token.get_secret_value(),
-            token_updater=self.token_saver,
+            token_updater=self.token_updater,
         )
 
         self.hooks["response"].append(self.response_hook)
 
-    def __enter__(self) -> Self:
-        super().__enter__()
-
-        if not self.tokens.tumblr_token.get_secret_value():
-            authorization_url, _ = self.authorization_url("https://tumblr.com/oauth2/authorize")  # pyright: ignore[reportUnknownMemberType]
-
-            rich.print(f"Please go to {authorization_url} and authorize access.")
-            authorization_response = Prompt.ask("Enter the full callback URL")
-
-            self.token_saver(
-                self.fetch_token(  # pyright: ignore[reportUnknownMemberType]
-                    "https://api.tumblr.com/v2/oauth2/token",
-                    authorization_response=authorization_response,
-                    client_secret=self.tokens.tumblr_client_secret.get_secret_value(),
-                ),
-            )
-
-        return self
-
-    def token_saver(self, token: object) -> None:
+    def token_updater(self, token: object) -> None:
         self.tokens.tumblr_token = Secret(token)
 
     def response_hook(self, response: Response, **_: object) -> None: