- Added new request models for datasource actions including validation, website crawling, and content retrieval.
- Enhanced `PluginExecutor` with methods to validate datasource credentials, crawl websites, and retrieve pages and content.
- Updated `PluginRegistration` to include methods for fetching datasource provider classes and handling website and online document datasources.
- Refined the `DatasourceProvider` interface to use `Mapping` for credentials, improving type safety.
- Introduced `OnlineDocumentDatasource` and `WebsiteCrawlDatasource` abstract classes for handling online document and website crawl functionalities.
- Added corresponding methods for retrieving pages and content, enhancing the datasource capabilities.
- Created new models for online document and website information to support the new interfaces.
* feat(oauth): implement OAuth authorization URL and credentials retrieval
- Added OAuthGetAuthorizationUrlRequest and OAuthGetCredentialsRequest models for handling OAuth requests.
- Introduced methods in PluginExecutor for generating OAuth authorization URLs and retrieving OAuth credentials.
- Updated ToolProvider interface to include OAuth methods for authorization URL and credentials handling.
- Refactored PluginInvokeType and related action enums to support OAuth actions.
- Added `@final` decorator to the constructors of `AgentStrategy`, `Endpoint`, `AIModel`, and `Tool` classes to prevent overriding.
- Included documentation notes in each constructor to indicate that they should not be overridden.
* feat: support var-selector params & surpport retriever_resources messsage
* opt: rename var-select to any
* fix: line too long
* opt: Add RetrieverResource Type
* refactor: replace json.loads with TypeAdapter for JSON validation in request readers and model
- Updated JSON parsing in BackwardsInvocation, StdioRequestReader, and TCPReaderWriter to use TypeAdapter for improved validation.
- Enhanced error handling in OAICompatLargeLanguageModel by replacing json.loads with TypeAdapter, ensuring better compliance with expected JSON schema.
* fix: linter
* feat(invocation): add FetchAppInvocation and update type hints for improved clarity
- Introduced FetchAppInvocation class to handle fetching app data.
- Updated type hints in ToolInvokeMessage and related classes to use Mapping for better type safety.
- Added FetchApp enum value to InvokeType for consistency in invocation types.
* apply ruff
* chore(python): temporarily disable `UP007` rule in Ruff
Disable the `UP007` rule temporarily due to numerous existing
violations in the current codebase.
* ci(python): add lint and test for Python SDK
* ci: Add mega-linter
* chore(python): Add final newline to markdown files
* fix(python): Fix linter issues by using ruff's auto fix
* fix(python): Fix TRY400 linter violations
Ruff suggests using `logger.exception` to log when
logging an exception, instead of using `logging.error`.
The former logs the exception and the traceback
automatically.
ref: https://docs.astral.sh/ruff/rules/error-instead-of-exception/
* fix(python): fix ruff linter violations
* test(python): Add Test cases for LLM entities
Test the initialization of `LLMResult` and `LLMResultChunk`.
* test(python): Add test for `AgentModelConfig`
Ensures that the `history_prompt_messages` attribute is
not shared between instances of `AgentModelConfig`.
* chore(python): output diffs in Ruff's format check
* style(python): format code with Ruff
* chore(python): Add a bash script for fix and format python code
* chore: add `persist-credentials: false` to checkout action
Enhances security by preventing subsequent
steps from accessing GitHub credentials, reducing
potential attack surfaces.
Ref: https://github.com/actions/checkout#checkout-v4
* refactor: remove prompt_messages from LLMResult and LLMResultChunk
* fix: add backward compatibility for deprecated prompt_messages field in LLMResult and LLMResultChunk
* fix: set default value for prompt_messages field to an empty list in LLMResult and LLMResultChunk for backward compatibility
* feat: add test for LLMResult to validate prompt_messages field and ensure backward compatibility
* apply ruff
* feat(python): Enable Ruff ruleset (RUF)
Refactor the codebase to address and resolve pre-existing style
violations flagged by the Ruff ruleset.
* feat(python): disable preview mode in Ruff
Preview rules in Ruff are unstable and subject to frequent changes.
Disabling them helps prevent potential confusion for developers.
* chore(python): disable deprecated UP038 rule in Ruff
The UP038 rule is deprecated and its suggested practice is not recommended.
Disabling this rule helps avoid unnecessary code rewrites.
Introduce the flake8-builtins (A) ruleset to prevent accidental shadowing
of Python's built-in functions.
Address existing issues primarily by adding `# noqa` to suppress warnings where necessary.
* chore(python): update .gitignore for Python SDK
Adjust .gitignore for Python SDK based on the templated generated by
gitignore.io, with minor custom modifications.
* chore: add .editorconfig for consistent formatting
Add a .editorconfig file to enforce consistent file encoding,
indentation, and end-of-line characters across the project.
* chore(python): upgrade ruff version to v0.11.2
* feat(python): Integrate flake8-bandit ruleset for security linting
Enable the flake8-bandit (S) ruleset in ruff to enforce security-related
best practices and mitigate potential vulnerabilities in the codebase.
Suppress existing issues in the current code using `noqa` comments, primarily for
instances of `requests` calls without a specified `timeout` parameter.
* fix:add function to validate only stream mode model credentials
* fix:add function to validate only stream mode model credentials
* fix:add function to validate only stream mode model credentials
* update: Stream credentials validation failed
* update: Stream credentials validation failed
---------
Co-authored-by: Xenos <sm2052@admindeMacBook-Pro.local>
Harry