diff --git a/.claude/skills/skill-creator/SKILL.md b/.claude/skills/skill-creator/SKILL.md new file mode 100644 index 0000000000..b49da5ac68 --- /dev/null +++ b/.claude/skills/skill-creator/SKILL.md @@ -0,0 +1,355 @@ +--- +name: skill-creator +description: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. +--- + +# Skill Creator + +This skill provides guidance for creating effective skills. + +## About Skills + +Skills are modular, self-contained packages that extend Claude's capabilities by providing +specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific +domains or tasks—they transform Claude from a general-purpose agent into a specialized agent +equipped with procedural knowledge that no model can fully possess. + +### What Skills Provide + +1. Specialized workflows - Multi-step procedures for specific domains +2. Tool integrations - Instructions for working with specific file formats or APIs +3. Domain expertise - Company-specific knowledge, schemas, business logic +4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks + +## Core Principles + +### Concise is Key + +The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request. + +**Default assumption: Claude is already very smart.** Only add context Claude doesn't already have. Challenge each piece of information: "Does Claude really need this explanation?" and "Does this paragraph justify its token cost?" + +Prefer concise examples over verbose explanations. + +### Set Appropriate Degrees of Freedom + +Match the level of specificity to the task's fragility and variability: + +**High freedom (text-based instructions)**: Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach. + +**Medium freedom (pseudocode or scripts with parameters)**: Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior. + +**Low freedom (specific scripts, few parameters)**: Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed. + +Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom). + +### Anatomy of a Skill + +Every skill consists of a required SKILL.md file and optional bundled resources: + +``` +skill-name/ +├── SKILL.md (required) +│ ├── YAML frontmatter metadata (required) +│ │ ├── name: (required) +│ │ └── description: (required) +│ └── Markdown instructions (required) +└── Bundled Resources (optional) + ├── scripts/ - Executable code (Python/Bash/etc.) + ├── references/ - Documentation intended to be loaded into context as needed + └── assets/ - Files used in output (templates, icons, fonts, etc.) +``` + +#### SKILL.md (required) + +Every SKILL.md consists of: + +- **Frontmatter** (YAML): Contains `name` and `description` fields. These are the only fields that Claude reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used. +- **Body** (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all). + +#### Bundled Resources (optional) + +##### Scripts (`scripts/`) + +Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten. + +- **When to include**: When the same code is being rewritten repeatedly or deterministic reliability is needed +- **Example**: `scripts/rotate_pdf.py` for PDF rotation tasks +- **Benefits**: Token efficient, deterministic, may be executed without loading into context +- **Note**: Scripts may still need to be read by Claude for patching or environment-specific adjustments + +##### References (`references/`) + +Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking. + +- **When to include**: For documentation that Claude should reference while working +- **Examples**: `references/finance.md` for financial schemas, `references/mnda.md` for company NDA template, `references/policies.md` for company policies, `references/api_docs.md` for API specifications +- **Use cases**: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides +- **Benefits**: Keeps SKILL.md lean, loaded only when Claude determines it's needed +- **Best practice**: If files are large (>10k words), include grep search patterns in SKILL.md +- **Avoid duplication**: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files. + +##### Assets (`assets/`) + +Files not intended to be loaded into context, but rather used within the output Claude produces. + +- **When to include**: When the skill needs files that will be used in the final output +- **Examples**: `assets/logo.png` for brand assets, `assets/slides.pptx` for PowerPoint templates, `assets/frontend-template/` for HTML/React boilerplate, `assets/font.ttf` for typography +- **Use cases**: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified +- **Benefits**: Separates output resources from documentation, enables Claude to use files without loading them into context + +#### What to Not Include in a Skill + +A skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including: + +- README.md +- INSTALLATION_GUIDE.md +- QUICK_REFERENCE.md +- CHANGELOG.md +- etc. + +The skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxilary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion. + +### Progressive Disclosure Design Principle + +Skills use a three-level loading system to manage context efficiently: + +1. **Metadata (name + description)** - Always in context (~100 words) +2. **SKILL.md body** - When skill triggers (<5k words) +3. **Bundled resources** - As needed by Claude (Unlimited because scripts can be executed without reading into context window) + +#### Progressive Disclosure Patterns + +Keep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them. + +**Key principle:** When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files. + +**Pattern 1: High-level guide with references** + +```markdown +# PDF Processing + +## Quick start + +Extract text with pdfplumber: +[code example] + +## Advanced features + +- **Form filling**: See [FORMS.md](FORMS.md) for complete guide +- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods +- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns +``` + +Claude loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed. + +**Pattern 2: Domain-specific organization** + +For Skills with multiple domains, organize content by domain to avoid loading irrelevant context: + +``` +bigquery-skill/ +├── SKILL.md (overview and navigation) +└── reference/ + ├── finance.md (revenue, billing metrics) + ├── sales.md (opportunities, pipeline) + ├── product.md (API usage, features) + └── marketing.md (campaigns, attribution) +``` + +When a user asks about sales metrics, Claude only reads sales.md. + +Similarly, for skills supporting multiple frameworks or variants, organize by variant: + +``` +cloud-deploy/ +├── SKILL.md (workflow + provider selection) +└── references/ + ├── aws.md (AWS deployment patterns) + ├── gcp.md (GCP deployment patterns) + └── azure.md (Azure deployment patterns) +``` + +When the user chooses AWS, Claude only reads aws.md. + +**Pattern 3: Conditional details** + +Show basic content, link to advanced content: + +```markdown +# DOCX Processing + +## Creating documents + +Use docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md). + +## Editing documents + +For simple edits, modify the XML directly. + +**For tracked changes**: See [REDLINING.md](REDLINING.md) +**For OOXML details**: See [OOXML.md](OOXML.md) +``` + +Claude reads REDLINING.md or OOXML.md only when the user needs those features. + +**Important guidelines:** + +- **Avoid deeply nested references** - Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md. +- **Structure longer reference files** - For files longer than 100 lines, include a table of contents at the top so Claude can see the full scope when previewing. + +## Skill Creation Process + +Skill creation involves these steps: + +1. Understand the skill with concrete examples +2. Plan reusable skill contents (scripts, references, assets) +3. Initialize the skill (run init_skill.py) +4. Edit the skill (implement resources and write SKILL.md) +5. Package the skill (run package_skill.py) +6. Iterate based on real usage + +Follow these steps in order, skipping only if there is a clear reason why they are not applicable. + +### Step 1: Understanding the Skill with Concrete Examples + +Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill. + +To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback. + +For example, when building an image-editor skill, relevant questions include: + +- "What functionality should the image-editor skill support? Editing, rotating, anything else?" +- "Can you give some examples of how this skill would be used?" +- "I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?" +- "What would a user say that should trigger this skill?" + +To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness. + +Conclude this step when there is a clear sense of the functionality the skill should support. + +### Step 2: Planning the Reusable Skill Contents + +To turn concrete examples into an effective skill, analyze each example by: + +1. Considering how to execute on the example from scratch +2. Identifying what scripts, references, and assets would be helpful when executing these workflows repeatedly + +Example: When building a `pdf-editor` skill to handle queries like "Help me rotate this PDF," the analysis shows: + +1. Rotating a PDF requires re-writing the same code each time +2. A `scripts/rotate_pdf.py` script would be helpful to store in the skill + +Example: When designing a `frontend-webapp-builder` skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows: + +1. Writing a frontend webapp requires the same boilerplate HTML/React each time +2. An `assets/hello-world/` template containing the boilerplate HTML/React project files would be helpful to store in the skill + +Example: When building a `big-query` skill to handle queries like "How many users have logged in today?" the analysis shows: + +1. Querying BigQuery requires re-discovering the table schemas and relationships each time +2. A `references/schema.md` file documenting the table schemas would be helpful to store in the skill + +To establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets. + +### Step 3: Initializing the Skill + +At this point, it is time to actually create the skill. + +Skip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step. + +When creating a new skill from scratch, always run the `init_skill.py` script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable. + +Usage: + +```bash +scripts/init_skill.py --path +``` + +The script: + +- Creates the skill directory at the specified path +- Generates a SKILL.md template with proper frontmatter and TODO placeholders +- Creates example resource directories: `scripts/`, `references/`, and `assets/` +- Adds example files in each directory that can be customized or deleted + +After initialization, customize or remove the generated SKILL.md and example files as needed. + +### Step 4: Edit the Skill + +When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Claude to use. Include information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively. + +#### Learn Proven Design Patterns + +Consult these helpful guides based on your skill's needs: + +- **Multi-step processes**: See references/workflows.md for sequential workflows and conditional logic +- **Specific output formats or quality standards**: See references/output-patterns.md for template and example patterns + +These files contain established best practices for effective skill design. + +#### Start with Reusable Skill Contents + +To begin implementation, start with the reusable resources identified above: `scripts/`, `references/`, and `assets/` files. Note that this step may require user input. For example, when implementing a `brand-guidelines` skill, the user may need to provide brand assets or templates to store in `assets/`, or documentation to store in `references/`. + +Added scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion. + +Any example files and directories not needed for the skill should be deleted. The initialization script creates example files in `scripts/`, `references/`, and `assets/` to demonstrate structure, but most skills won't need all of them. + +#### Update SKILL.md + +**Writing Guidelines:** Always use imperative/infinitive form. + +##### Frontmatter + +Write the YAML frontmatter with `name` and `description`: + +- `name`: The skill name +- `description`: This is the primary triggering mechanism for your skill, and helps Claude understand when to use the skill. + - Include both what the Skill does and specific triggers/contexts for when to use it. + - Include all "when to use" information here - Not in the body. The body is only loaded after triggering, so "When to Use This Skill" sections in the body are not helpful to Claude. + - Example description for a `docx` skill: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks" + +Do not include any other fields in YAML frontmatter. + +##### Body + +Write instructions for using the skill and its bundled resources. + +### Step 5: Packaging a Skill + +Once development of the skill is complete, it must be packaged into a distributable .skill file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements: + +```bash +scripts/package_skill.py +``` + +Optional output directory specification: + +```bash +scripts/package_skill.py ./dist +``` + +The packaging script will: + +1. **Validate** the skill automatically, checking: + + - YAML frontmatter format and required fields + - Skill naming conventions and directory structure + - Description completeness and quality + - File organization and resource references + +2. **Package** the skill if validation passes, creating a .skill file named after the skill (e.g., `my-skill.skill`) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension. + +If validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again. + +### Step 6: Iterate + +After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed. + +**Iteration workflow:** + +1. Use the skill on real tasks +2. Notice struggles or inefficiencies +3. Identify how SKILL.md or bundled resources should be updated +4. Implement changes and test again diff --git a/.claude/skills/skill-creator/references/output-patterns.md b/.claude/skills/skill-creator/references/output-patterns.md new file mode 100644 index 0000000000..022e85fe5e --- /dev/null +++ b/.claude/skills/skill-creator/references/output-patterns.md @@ -0,0 +1,86 @@ +# Output Patterns + +Use these patterns when skills need to produce consistent, high-quality output. + +## Template Pattern + +Provide templates for output format. Match the level of strictness to your needs. + +**For strict requirements (like API responses or data formats):** + +```markdown +## Report structure + +ALWAYS use this exact template structure: + +# [Analysis Title] + +## Executive summary +[One-paragraph overview of key findings] + +## Key findings +- Finding 1 with supporting data +- Finding 2 with supporting data +- Finding 3 with supporting data + +## Recommendations +1. Specific actionable recommendation +2. Specific actionable recommendation +``` + +**For flexible guidance (when adaptation is useful):** + +```markdown +## Report structure + +Here is a sensible default format, but use your best judgment: + +# [Analysis Title] + +## Executive summary +[Overview] + +## Key findings +[Adapt sections based on what you discover] + +## Recommendations +[Tailor to the specific context] + +Adjust sections as needed for the specific analysis type. +``` + +## Examples Pattern + +For skills where output quality depends on seeing examples, provide input/output pairs: + +```markdown +## Commit message format + +Generate commit messages following these examples: + +**Example 1:** +Input: Added user authentication with JWT tokens +Output: +``` + +feat(auth): implement JWT-based authentication + +Add login endpoint and token validation middleware + +``` + +**Example 2:** +Input: Fixed bug where dates displayed incorrectly in reports +Output: +``` + +fix(reports): correct date formatting in timezone conversion + +Use UTC timestamps consistently across report generation + +``` + +Follow this style: type(scope): brief description, then detailed explanation. +``` + +Examples help Claude understand the desired style and level of detail more clearly than descriptions alone. diff --git a/.claude/skills/skill-creator/references/workflows.md b/.claude/skills/skill-creator/references/workflows.md new file mode 100644 index 0000000000..54b0174078 --- /dev/null +++ b/.claude/skills/skill-creator/references/workflows.md @@ -0,0 +1,28 @@ +# Workflow Patterns + +## Sequential Workflows + +For complex tasks, break operations into clear, sequential steps. It is often helpful to give Claude an overview of the process towards the beginning of SKILL.md: + +```markdown +Filling a PDF form involves these steps: + +1. Analyze the form (run analyze_form.py) +2. Create field mapping (edit fields.json) +3. Validate mapping (run validate_fields.py) +4. Fill the form (run fill_form.py) +5. Verify output (run verify_output.py) +``` + +## Conditional Workflows + +For tasks with branching logic, guide Claude through decision points: + +```markdown +1. Determine the modification type: + **Creating new content?** → Follow "Creation workflow" below + **Editing existing content?** → Follow "Editing workflow" below + +2. Creation workflow: [steps] +3. Editing workflow: [steps] +``` diff --git a/.claude/skills/skill-creator/scripts/init_skill.py b/.claude/skills/skill-creator/scripts/init_skill.py new file mode 100755 index 0000000000..249fffcbbd --- /dev/null +++ b/.claude/skills/skill-creator/scripts/init_skill.py @@ -0,0 +1,300 @@ +#!/usr/bin/env python3 +""" +Skill Initializer - Creates a new skill from template + +Usage: + init_skill.py --path + +Examples: + init_skill.py my-new-skill --path skills/public + init_skill.py my-api-helper --path skills/private + init_skill.py custom-skill --path /custom/location +""" + +import sys +from pathlib import Path + + +SKILL_TEMPLATE = """--- +name: {skill_name} +description: [TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.] +--- + +# {skill_title} + +## Overview + +[TODO: 1-2 sentences explaining what this skill enables] + +## Structuring This Skill + +[TODO: Choose the structure that best fits this skill's purpose. Common patterns: + +**1. Workflow-Based** (best for sequential processes) +- Works well when there are clear step-by-step procedures +- Example: DOCX skill with "Workflow Decision Tree" → "Reading" → "Creating" → "Editing" +- Structure: ## Overview → ## Workflow Decision Tree → ## Step 1 → ## Step 2... + +**2. Task-Based** (best for tool collections) +- Works well when the skill offers different operations/capabilities +- Example: PDF skill with "Quick Start" → "Merge PDFs" → "Split PDFs" → "Extract Text" +- Structure: ## Overview → ## Quick Start → ## Task Category 1 → ## Task Category 2... + +**3. Reference/Guidelines** (best for standards or specifications) +- Works well for brand guidelines, coding standards, or requirements +- Example: Brand styling with "Brand Guidelines" → "Colors" → "Typography" → "Features" +- Structure: ## Overview → ## Guidelines → ## Specifications → ## Usage... + +**4. Capabilities-Based** (best for integrated systems) +- Works well when the skill provides multiple interrelated features +- Example: Product Management with "Core Capabilities" → numbered capability list +- Structure: ## Overview → ## Core Capabilities → ### 1. Feature → ### 2. Feature... + +Patterns can be mixed and matched as needed. Most skills combine patterns (e.g., start with task-based, add workflow for complex operations). + +Delete this entire "Structuring This Skill" section when done - it's just guidance.] + +## [TODO: Replace with the first main section based on chosen structure] + +[TODO: Add content here. See examples in existing skills: +- Code samples for technical skills +- Decision trees for complex workflows +- Concrete examples with realistic user requests +- References to scripts/templates/references as needed] + +## Resources + +This skill includes example resource directories that demonstrate how to organize different types of bundled resources: + +### scripts/ +Executable code (Python/Bash/etc.) that can be run directly to perform specific operations. + +**Examples from other skills:** +- PDF skill: `fill_fillable_fields.py`, `extract_form_field_info.py` - utilities for PDF manipulation +- DOCX skill: `document.py`, `utilities.py` - Python modules for document processing + +**Appropriate for:** Python scripts, shell scripts, or any executable code that performs automation, data processing, or specific operations. + +**Note:** Scripts may be executed without loading into context, but can still be read by Claude for patching or environment adjustments. + +### references/ +Documentation and reference material intended to be loaded into context to inform Claude's process and thinking. + +**Examples from other skills:** +- Product management: `communication.md`, `context_building.md` - detailed workflow guides +- BigQuery: API reference documentation and query examples +- Finance: Schema documentation, company policies + +**Appropriate for:** In-depth documentation, API references, database schemas, comprehensive guides, or any detailed information that Claude should reference while working. + +### assets/ +Files not intended to be loaded into context, but rather used within the output Claude produces. + +**Examples from other skills:** +- Brand styling: PowerPoint template files (.pptx), logo files +- Frontend builder: HTML/React boilerplate project directories +- Typography: Font files (.ttf, .woff2) + +**Appropriate for:** Templates, boilerplate code, document templates, images, icons, fonts, or any files meant to be copied or used in the final output. + +--- + +**Any unneeded directories can be deleted.** Not every skill requires all three types of resources. +""" + +EXAMPLE_SCRIPT = '''#!/usr/bin/env python3 +""" +Example helper script for {skill_name} + +This is a placeholder script that can be executed directly. +Replace with actual implementation or delete if not needed. + +Example real scripts from other skills: +- pdf/scripts/fill_fillable_fields.py - Fills PDF form fields +- pdf/scripts/convert_pdf_to_images.py - Converts PDF pages to images +""" + +def main(): + print("This is an example script for {skill_name}") + # TODO: Add actual script logic here + # This could be data processing, file conversion, API calls, etc. + +if __name__ == "__main__": + main() +''' + +EXAMPLE_REFERENCE = """# Reference Documentation for {skill_title} + +This is a placeholder for detailed reference documentation. +Replace with actual reference content or delete if not needed. + +Example real reference docs from other skills: +- product-management/references/communication.md - Comprehensive guide for status updates +- product-management/references/context_building.md - Deep-dive on gathering context +- bigquery/references/ - API references and query examples + +## When Reference Docs Are Useful + +Reference docs are ideal for: +- Comprehensive API documentation +- Detailed workflow guides +- Complex multi-step processes +- Information too lengthy for main SKILL.md +- Content that's only needed for specific use cases + +## Structure Suggestions + +### API Reference Example +- Overview +- Authentication +- Endpoints with examples +- Error codes +- Rate limits + +### Workflow Guide Example +- Prerequisites +- Step-by-step instructions +- Common patterns +- Troubleshooting +- Best practices +""" + +EXAMPLE_ASSET = """# Example Asset File + +This placeholder represents where asset files would be stored. +Replace with actual asset files (templates, images, fonts, etc.) or delete if not needed. + +Asset files are NOT intended to be loaded into context, but rather used within +the output Claude produces. + +Example asset files from other skills: +- Brand guidelines: logo.png, slides_template.pptx +- Frontend builder: hello-world/ directory with HTML/React boilerplate +- Typography: custom-font.ttf, font-family.woff2 +- Data: sample_data.csv, test_dataset.json + +## Common Asset Types + +- Templates: .pptx, .docx, boilerplate directories +- Images: .png, .jpg, .svg, .gif +- Fonts: .ttf, .otf, .woff, .woff2 +- Boilerplate code: Project directories, starter files +- Icons: .ico, .svg +- Data files: .csv, .json, .xml, .yaml + +Note: This is a text placeholder. Actual assets can be any file type. +""" + + +def title_case_skill_name(skill_name): + """Convert hyphenated skill name to Title Case for display.""" + return " ".join(word.capitalize() for word in skill_name.split("-")) + + +def init_skill(skill_name, path): + """ + Initialize a new skill directory with template SKILL.md. + + Args: + skill_name: Name of the skill + path: Path where the skill directory should be created + + Returns: + Path to created skill directory, or None if error + """ + # Determine skill directory path + skill_dir = Path(path).resolve() / skill_name + + # Check if directory already exists + if skill_dir.exists(): + print(f"❌ Error: Skill directory already exists: {skill_dir}") + return None + + # Create skill directory + try: + skill_dir.mkdir(parents=True, exist_ok=False) + print(f"✅ Created skill directory: {skill_dir}") + except Exception as e: + print(f"❌ Error creating directory: {e}") + return None + + # Create SKILL.md from template + skill_title = title_case_skill_name(skill_name) + skill_content = SKILL_TEMPLATE.format(skill_name=skill_name, skill_title=skill_title) + + skill_md_path = skill_dir / "SKILL.md" + try: + skill_md_path.write_text(skill_content) + print("✅ Created SKILL.md") + except Exception as e: + print(f"❌ Error creating SKILL.md: {e}") + return None + + # Create resource directories with example files + try: + # Create scripts/ directory with example script + scripts_dir = skill_dir / "scripts" + scripts_dir.mkdir(exist_ok=True) + example_script = scripts_dir / "example.py" + example_script.write_text(EXAMPLE_SCRIPT.format(skill_name=skill_name)) + example_script.chmod(0o755) + print("✅ Created scripts/example.py") + + # Create references/ directory with example reference doc + references_dir = skill_dir / "references" + references_dir.mkdir(exist_ok=True) + example_reference = references_dir / "api_reference.md" + example_reference.write_text(EXAMPLE_REFERENCE.format(skill_title=skill_title)) + print("✅ Created references/api_reference.md") + + # Create assets/ directory with example asset placeholder + assets_dir = skill_dir / "assets" + assets_dir.mkdir(exist_ok=True) + example_asset = assets_dir / "example_asset.txt" + example_asset.write_text(EXAMPLE_ASSET) + print("✅ Created assets/example_asset.txt") + except Exception as e: + print(f"❌ Error creating resource directories: {e}") + return None + + # Print next steps + print(f"\n✅ Skill '{skill_name}' initialized successfully at {skill_dir}") + print("\nNext steps:") + print("1. Edit SKILL.md to complete the TODO items and update the description") + print("2. Customize or delete the example files in scripts/, references/, and assets/") + print("3. Run the validator when ready to check the skill structure") + + return skill_dir + + +def main(): + if len(sys.argv) < 4 or sys.argv[2] != "--path": + print("Usage: init_skill.py --path ") + print("\nSkill name requirements:") + print(" - Hyphen-case identifier (e.g., 'data-analyzer')") + print(" - Lowercase letters, digits, and hyphens only") + print(" - Max 40 characters") + print(" - Must match directory name exactly") + print("\nExamples:") + print(" init_skill.py my-new-skill --path skills/public") + print(" init_skill.py my-api-helper --path skills/private") + print(" init_skill.py custom-skill --path /custom/location") + sys.exit(1) + + skill_name = sys.argv[1] + path = sys.argv[3] + + print(f"🚀 Initializing skill: {skill_name}") + print(f" Location: {path}") + print() + + result = init_skill(skill_name, path) + + if result: + sys.exit(0) + else: + sys.exit(1) + + +if __name__ == "__main__": + main() diff --git a/.claude/skills/skill-creator/scripts/package_skill.py b/.claude/skills/skill-creator/scripts/package_skill.py new file mode 100755 index 0000000000..736b928be0 --- /dev/null +++ b/.claude/skills/skill-creator/scripts/package_skill.py @@ -0,0 +1,110 @@ +#!/usr/bin/env python3 +""" +Skill Packager - Creates a distributable .skill file of a skill folder + +Usage: + python utils/package_skill.py [output-directory] + +Example: + python utils/package_skill.py skills/public/my-skill + python utils/package_skill.py skills/public/my-skill ./dist +""" + +import sys +import zipfile +from pathlib import Path +from quick_validate import validate_skill + + +def package_skill(skill_path, output_dir=None): + """ + Package a skill folder into a .skill file. + + Args: + skill_path: Path to the skill folder + output_dir: Optional output directory for the .skill file (defaults to current directory) + + Returns: + Path to the created .skill file, or None if error + """ + skill_path = Path(skill_path).resolve() + + # Validate skill folder exists + if not skill_path.exists(): + print(f"❌ Error: Skill folder not found: {skill_path}") + return None + + if not skill_path.is_dir(): + print(f"❌ Error: Path is not a directory: {skill_path}") + return None + + # Validate SKILL.md exists + skill_md = skill_path / "SKILL.md" + if not skill_md.exists(): + print(f"❌ Error: SKILL.md not found in {skill_path}") + return None + + # Run validation before packaging + print("🔍 Validating skill...") + valid, message = validate_skill(skill_path) + if not valid: + print(f"❌ Validation failed: {message}") + print(" Please fix the validation errors before packaging.") + return None + print(f"✅ {message}\n") + + # Determine output location + skill_name = skill_path.name + if output_dir: + output_path = Path(output_dir).resolve() + output_path.mkdir(parents=True, exist_ok=True) + else: + output_path = Path.cwd() + + skill_filename = output_path / f"{skill_name}.skill" + + # Create the .skill file (zip format) + try: + with zipfile.ZipFile(skill_filename, "w", zipfile.ZIP_DEFLATED) as zipf: + # Walk through the skill directory + for file_path in skill_path.rglob("*"): + if file_path.is_file(): + # Calculate the relative path within the zip + arcname = file_path.relative_to(skill_path.parent) + zipf.write(file_path, arcname) + print(f" Added: {arcname}") + + print(f"\n✅ Successfully packaged skill to: {skill_filename}") + return skill_filename + + except Exception as e: + print(f"❌ Error creating .skill file: {e}") + return None + + +def main(): + if len(sys.argv) < 2: + print("Usage: python utils/package_skill.py [output-directory]") + print("\nExample:") + print(" python utils/package_skill.py skills/public/my-skill") + print(" python utils/package_skill.py skills/public/my-skill ./dist") + sys.exit(1) + + skill_path = sys.argv[1] + output_dir = sys.argv[2] if len(sys.argv) > 2 else None + + print(f"📦 Packaging skill: {skill_path}") + if output_dir: + print(f" Output directory: {output_dir}") + print() + + result = package_skill(skill_path, output_dir) + + if result: + sys.exit(0) + else: + sys.exit(1) + + +if __name__ == "__main__": + main() diff --git a/.claude/skills/skill-creator/scripts/quick_validate.py b/.claude/skills/skill-creator/scripts/quick_validate.py new file mode 100755 index 0000000000..66eb0a71bf --- /dev/null +++ b/.claude/skills/skill-creator/scripts/quick_validate.py @@ -0,0 +1,97 @@ +#!/usr/bin/env python3 +""" +Quick validation script for skills - minimal version +""" + +import sys +import os +import re +import yaml +from pathlib import Path + + +def validate_skill(skill_path): + """Basic validation of a skill""" + skill_path = Path(skill_path) + + # Check SKILL.md exists + skill_md = skill_path / "SKILL.md" + if not skill_md.exists(): + return False, "SKILL.md not found" + + # Read and validate frontmatter + content = skill_md.read_text() + if not content.startswith("---"): + return False, "No YAML frontmatter found" + + # Extract frontmatter + match = re.match(r"^---\n(.*?)\n---", content, re.DOTALL) + if not match: + return False, "Invalid frontmatter format" + + frontmatter_text = match.group(1) + + # Parse YAML frontmatter + try: + frontmatter = yaml.safe_load(frontmatter_text) + if not isinstance(frontmatter, dict): + return False, "Frontmatter must be a YAML dictionary" + except yaml.YAMLError as e: + return False, f"Invalid YAML in frontmatter: {e}" + + # Define allowed properties + ALLOWED_PROPERTIES = {"name", "description", "license", "allowed-tools", "metadata"} + + # Check for unexpected properties (excluding nested keys under metadata) + unexpected_keys = set(frontmatter.keys()) - ALLOWED_PROPERTIES + if unexpected_keys: + return False, ( + f"Unexpected key(s) in SKILL.md frontmatter: {', '.join(sorted(unexpected_keys))}. " + f"Allowed properties are: {', '.join(sorted(ALLOWED_PROPERTIES))}" + ) + + # Check required fields + if "name" not in frontmatter: + return False, "Missing 'name' in frontmatter" + if "description" not in frontmatter: + return False, "Missing 'description' in frontmatter" + + # Extract name for validation + name = frontmatter.get("name", "") + if not isinstance(name, str): + return False, f"Name must be a string, got {type(name).__name__}" + name = name.strip() + if name: + # Check naming convention (hyphen-case: lowercase with hyphens) + if not re.match(r"^[a-z0-9-]+$", name): + return False, f"Name '{name}' should be hyphen-case (lowercase letters, digits, and hyphens only)" + if name.startswith("-") or name.endswith("-") or "--" in name: + return False, f"Name '{name}' cannot start/end with hyphen or contain consecutive hyphens" + # Check name length (max 64 characters per spec) + if len(name) > 64: + return False, f"Name is too long ({len(name)} characters). Maximum is 64 characters." + + # Extract and validate description + description = frontmatter.get("description", "") + if not isinstance(description, str): + return False, f"Description must be a string, got {type(description).__name__}" + description = description.strip() + if description: + # Check for angle brackets + if "<" in description or ">" in description: + return False, "Description cannot contain angle brackets (< or >)" + # Check description length (max 1024 characters per spec) + if len(description) > 1024: + return False, f"Description is too long ({len(description)} characters). Maximum is 1024 characters." + + return True, "Skill is valid!" + + +if __name__ == "__main__": + if len(sys.argv) != 2: + print("Usage: python quick_validate.py ") + sys.exit(1) + + valid, message = validate_skill(sys.argv[1]) + print(message) + sys.exit(0 if valid else 1) diff --git a/api/.importlinter b/api/.importlinter index acb21ae522..2dec958788 100644 --- a/api/.importlinter +++ b/api/.importlinter @@ -53,7 +53,6 @@ ignore_imports = core.workflow.nodes.llm.llm_utils -> extensions.ext_database core.workflow.nodes.llm.node -> extensions.ext_database core.workflow.nodes.tool.tool_node -> extensions.ext_database - core.workflow.nodes.variable_assigner.common.impl -> extensions.ext_database core.workflow.graph_engine.command_channels.redis_channel -> extensions.ext_redis core.workflow.graph_engine.manager -> extensions.ext_redis core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> extensions.ext_redis diff --git a/api/controllers/console/auth/login.py b/api/controllers/console/auth/login.py index 772d98822e..4a52bf8abe 100644 --- a/api/controllers/console/auth/login.py +++ b/api/controllers/console/auth/login.py @@ -1,3 +1,5 @@ +from typing import Any + import flask_login from flask import make_response, request from flask_restx import Resource @@ -96,14 +98,13 @@ class LoginApi(Resource): if is_login_error_rate_limit: raise EmailPasswordLoginLimitError() - # TODO: why invitation is re-assigned with different type? - invitation = args.invite_token # type: ignore - if invitation: - invitation = RegisterService.get_invitation_if_token_valid(None, args.email, invitation) # type: ignore + invitation_data: dict[str, Any] | None = None + if args.invite_token: + invitation_data = RegisterService.get_invitation_if_token_valid(None, args.email, args.invite_token) try: - if invitation: - data = invitation.get("data", {}) # type: ignore + if invitation_data: + data = invitation_data.get("data", {}) invitee_email = data.get("email") if data else None if invitee_email != args.email: raise InvalidEmailError() diff --git a/api/controllers/console/datasets/rag_pipeline/rag_pipeline_workflow.py b/api/controllers/console/datasets/rag_pipeline/rag_pipeline_workflow.py index 46d67f0581..02efc54eea 100644 --- a/api/controllers/console/datasets/rag_pipeline/rag_pipeline_workflow.py +++ b/api/controllers/console/datasets/rag_pipeline/rag_pipeline_workflow.py @@ -355,7 +355,7 @@ class PublishedRagPipelineRunApi(Resource): pipeline=pipeline, user=current_user, args=args, - invoke_from=InvokeFrom.DEBUGGER if payload.is_preview else InvokeFrom.PUBLISHED, + invoke_from=InvokeFrom.DEBUGGER if payload.is_preview else InvokeFrom.PUBLISHED_PIPELINE, streaming=streaming, ) diff --git a/api/controllers/console/files.py b/api/controllers/console/files.py index 29417dc896..109a3cd0d3 100644 --- a/api/controllers/console/files.py +++ b/api/controllers/console/files.py @@ -1,7 +1,7 @@ from typing import Literal from flask import request -from flask_restx import Resource, marshal_with +from flask_restx import Resource from werkzeug.exceptions import Forbidden import services @@ -15,18 +15,21 @@ from controllers.common.errors import ( TooManyFilesError, UnsupportedFileTypeError, ) +from controllers.common.schema import register_schema_models from controllers.console.wraps import ( account_initialization_required, cloud_edition_billing_resource_check, setup_required, ) from extensions.ext_database import db -from fields.file_fields import file_fields, upload_config_fields +from fields.file_fields import FileResponse, UploadConfig from libs.login import current_account_with_tenant, login_required from services.file_service import FileService from . import console_ns +register_schema_models(console_ns, UploadConfig, FileResponse) + PREVIEW_WORDS_LIMIT = 3000 @@ -35,26 +38,27 @@ class FileApi(Resource): @setup_required @login_required @account_initialization_required - @marshal_with(upload_config_fields) + @console_ns.response(200, "Success", console_ns.models[UploadConfig.__name__]) def get(self): - return { - "file_size_limit": dify_config.UPLOAD_FILE_SIZE_LIMIT, - "batch_count_limit": dify_config.UPLOAD_FILE_BATCH_LIMIT, - "file_upload_limit": dify_config.BATCH_UPLOAD_LIMIT, - "image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT, - "video_file_size_limit": dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT, - "audio_file_size_limit": dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT, - "workflow_file_upload_limit": dify_config.WORKFLOW_FILE_UPLOAD_LIMIT, - "image_file_batch_limit": dify_config.IMAGE_FILE_BATCH_LIMIT, - "single_chunk_attachment_limit": dify_config.SINGLE_CHUNK_ATTACHMENT_LIMIT, - "attachment_image_file_size_limit": dify_config.ATTACHMENT_IMAGE_FILE_SIZE_LIMIT, - }, 200 + config = UploadConfig( + file_size_limit=dify_config.UPLOAD_FILE_SIZE_LIMIT, + batch_count_limit=dify_config.UPLOAD_FILE_BATCH_LIMIT, + file_upload_limit=dify_config.BATCH_UPLOAD_LIMIT, + image_file_size_limit=dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT, + video_file_size_limit=dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT, + audio_file_size_limit=dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT, + workflow_file_upload_limit=dify_config.WORKFLOW_FILE_UPLOAD_LIMIT, + image_file_batch_limit=dify_config.IMAGE_FILE_BATCH_LIMIT, + single_chunk_attachment_limit=dify_config.SINGLE_CHUNK_ATTACHMENT_LIMIT, + attachment_image_file_size_limit=dify_config.ATTACHMENT_IMAGE_FILE_SIZE_LIMIT, + ) + return config.model_dump(mode="json"), 200 @setup_required @login_required @account_initialization_required - @marshal_with(file_fields) @cloud_edition_billing_resource_check("documents") + @console_ns.response(201, "File uploaded successfully", console_ns.models[FileResponse.__name__]) def post(self): current_user, _ = current_account_with_tenant() source_str = request.form.get("source") @@ -90,7 +94,8 @@ class FileApi(Resource): except services.errors.file.BlockedFileExtensionError as blocked_extension_error: raise BlockedFileExtensionError(blocked_extension_error.description) - return upload_file, 201 + response = FileResponse.model_validate(upload_file, from_attributes=True) + return response.model_dump(mode="json"), 201 @console_ns.route("/files//preview") diff --git a/api/controllers/console/remote_files.py b/api/controllers/console/remote_files.py index 47eef7eb7e..70c7b80ffa 100644 --- a/api/controllers/console/remote_files.py +++ b/api/controllers/console/remote_files.py @@ -1,7 +1,7 @@ import urllib.parse import httpx -from flask_restx import Resource, marshal_with +from flask_restx import Resource from pydantic import BaseModel, Field import services @@ -11,19 +11,22 @@ from controllers.common.errors import ( RemoteFileUploadError, UnsupportedFileTypeError, ) +from controllers.common.schema import register_schema_models from core.file import helpers as file_helpers from core.helper import ssrf_proxy from extensions.ext_database import db -from fields.file_fields import file_fields_with_signed_url, remote_file_info_fields +from fields.file_fields import FileWithSignedUrl, RemoteFileInfo from libs.login import current_account_with_tenant from services.file_service import FileService from . import console_ns +register_schema_models(console_ns, RemoteFileInfo, FileWithSignedUrl) + @console_ns.route("/remote-files/") class RemoteFileInfoApi(Resource): - @marshal_with(remote_file_info_fields) + @console_ns.response(200, "Remote file info", console_ns.models[RemoteFileInfo.__name__]) def get(self, url): decoded_url = urllib.parse.unquote(url) resp = ssrf_proxy.head(decoded_url) @@ -31,10 +34,11 @@ class RemoteFileInfoApi(Resource): # failed back to get method resp = ssrf_proxy.get(decoded_url, timeout=3) resp.raise_for_status() - return { - "file_type": resp.headers.get("Content-Type", "application/octet-stream"), - "file_length": int(resp.headers.get("Content-Length", 0)), - } + info = RemoteFileInfo( + file_type=resp.headers.get("Content-Type", "application/octet-stream"), + file_length=int(resp.headers.get("Content-Length", 0)), + ) + return info.model_dump(mode="json") class RemoteFileUploadPayload(BaseModel): @@ -50,7 +54,7 @@ console_ns.schema_model( @console_ns.route("/remote-files/upload") class RemoteFileUploadApi(Resource): @console_ns.expect(console_ns.models[RemoteFileUploadPayload.__name__]) - @marshal_with(file_fields_with_signed_url) + @console_ns.response(201, "Remote file uploaded", console_ns.models[FileWithSignedUrl.__name__]) def post(self): args = RemoteFileUploadPayload.model_validate(console_ns.payload) url = args.url @@ -85,13 +89,14 @@ class RemoteFileUploadApi(Resource): except services.errors.file.UnsupportedFileTypeError: raise UnsupportedFileTypeError() - return { - "id": upload_file.id, - "name": upload_file.name, - "size": upload_file.size, - "extension": upload_file.extension, - "url": file_helpers.get_signed_file_url(upload_file_id=upload_file.id), - "mime_type": upload_file.mime_type, - "created_by": upload_file.created_by, - "created_at": upload_file.created_at, - }, 201 + payload = FileWithSignedUrl( + id=upload_file.id, + name=upload_file.name, + size=upload_file.size, + extension=upload_file.extension, + url=file_helpers.get_signed_file_url(upload_file_id=upload_file.id), + mime_type=upload_file.mime_type, + created_by=upload_file.created_by, + created_at=int(upload_file.created_at.timestamp()), + ) + return payload.model_dump(mode="json"), 201 diff --git a/api/controllers/console/workspace/account.py b/api/controllers/console/workspace/account.py index 55eaa2f09f..03ad0f423b 100644 --- a/api/controllers/console/workspace/account.py +++ b/api/controllers/console/workspace/account.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from datetime import datetime from typing import Literal @@ -99,7 +101,7 @@ class AccountPasswordPayload(BaseModel): repeat_new_password: str @model_validator(mode="after") - def check_passwords_match(self) -> "AccountPasswordPayload": + def check_passwords_match(self) -> AccountPasswordPayload: if self.new_password != self.repeat_new_password: raise RepeatPasswordNotMatchError() return self diff --git a/api/controllers/files/upload.py b/api/controllers/files/upload.py index 6096a87c56..28ec4b3935 100644 --- a/api/controllers/files/upload.py +++ b/api/controllers/files/upload.py @@ -4,18 +4,18 @@ from flask import request from flask_restx import Resource from flask_restx.api import HTTPStatus from pydantic import BaseModel, Field -from werkzeug.datastructures import FileStorage from werkzeug.exceptions import Forbidden import services from core.file.helpers import verify_plugin_file_signature from core.tools.tool_file_manager import ToolFileManager -from fields.file_fields import build_file_model +from fields.file_fields import FileResponse from ..common.errors import ( FileTooLargeError, UnsupportedFileTypeError, ) +from ..common.schema import register_schema_models from ..console.wraps import setup_required from ..files import files_ns from ..inner_api.plugin.wraps import get_user @@ -35,6 +35,8 @@ files_ns.schema_model( PluginUploadQuery.__name__, PluginUploadQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0) ) +register_schema_models(files_ns, FileResponse) + @files_ns.route("/upload/for-plugin") class PluginUploadFileApi(Resource): @@ -51,7 +53,7 @@ class PluginUploadFileApi(Resource): 415: "Unsupported file type", } ) - @files_ns.marshal_with(build_file_model(files_ns), code=HTTPStatus.CREATED) + @files_ns.response(HTTPStatus.CREATED, "File uploaded", files_ns.models[FileResponse.__name__]) def post(self): """Upload a file for plugin usage. @@ -69,7 +71,7 @@ class PluginUploadFileApi(Resource): """ args = PluginUploadQuery.model_validate(request.args.to_dict(flat=True)) # type: ignore - file: FileStorage | None = request.files.get("file") + file = request.files.get("file") if file is None: raise Forbidden("File is required.") @@ -80,8 +82,8 @@ class PluginUploadFileApi(Resource): user_id = args.user_id user = get_user(tenant_id, user_id) - filename: str | None = file.filename - mimetype: str | None = file.mimetype + filename = file.filename + mimetype = file.mimetype if not filename or not mimetype: raise Forbidden("Invalid request.") @@ -111,22 +113,22 @@ class PluginUploadFileApi(Resource): preview_url = ToolFileManager.sign_file(tool_file_id=tool_file.id, extension=extension) # Create a dictionary with all the necessary attributes - result = { - "id": tool_file.id, - "user_id": tool_file.user_id, - "tenant_id": tool_file.tenant_id, - "conversation_id": tool_file.conversation_id, - "file_key": tool_file.file_key, - "mimetype": tool_file.mimetype, - "original_url": tool_file.original_url, - "name": tool_file.name, - "size": tool_file.size, - "mime_type": mimetype, - "extension": extension, - "preview_url": preview_url, - } + result = FileResponse( + id=tool_file.id, + name=tool_file.name, + size=tool_file.size, + extension=extension, + mime_type=mimetype, + preview_url=preview_url, + source_url=tool_file.original_url, + original_url=tool_file.original_url, + user_id=tool_file.user_id, + tenant_id=tool_file.tenant_id, + conversation_id=tool_file.conversation_id, + file_key=tool_file.file_key, + ) - return result, 201 + return result.model_dump(mode="json"), 201 except services.errors.file.FileTooLargeError as file_too_large_error: raise FileTooLargeError(file_too_large_error.description) except services.errors.file.UnsupportedFileTypeError: diff --git a/api/controllers/service_api/app/file.py b/api/controllers/service_api/app/file.py index ffe4e0b492..6f6dadf768 100644 --- a/api/controllers/service_api/app/file.py +++ b/api/controllers/service_api/app/file.py @@ -10,13 +10,16 @@ from controllers.common.errors import ( TooManyFilesError, UnsupportedFileTypeError, ) +from controllers.common.schema import register_schema_models from controllers.service_api import service_api_ns from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token from extensions.ext_database import db -from fields.file_fields import build_file_model +from fields.file_fields import FileResponse from models import App, EndUser from services.file_service import FileService +register_schema_models(service_api_ns, FileResponse) + @service_api_ns.route("/files/upload") class FileApi(Resource): @@ -31,8 +34,8 @@ class FileApi(Resource): 415: "Unsupported file type", } ) - @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.FORM)) - @service_api_ns.marshal_with(build_file_model(service_api_ns), code=HTTPStatus.CREATED) + @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.FORM)) # type: ignore + @service_api_ns.response(HTTPStatus.CREATED, "File uploaded", service_api_ns.models[FileResponse.__name__]) def post(self, app_model: App, end_user: EndUser): """Upload a file for use in conversations. @@ -64,4 +67,5 @@ class FileApi(Resource): except services.errors.file.UnsupportedFileTypeError: raise UnsupportedFileTypeError() - return upload_file, 201 + response = FileResponse.model_validate(upload_file, from_attributes=True) + return response.model_dump(mode="json"), 201 diff --git a/api/controllers/service_api/dataset/rag_pipeline/rag_pipeline_workflow.py b/api/controllers/service_api/dataset/rag_pipeline/rag_pipeline_workflow.py index 0a2017e2bd..70b5030237 100644 --- a/api/controllers/service_api/dataset/rag_pipeline/rag_pipeline_workflow.py +++ b/api/controllers/service_api/dataset/rag_pipeline/rag_pipeline_workflow.py @@ -174,7 +174,7 @@ class PipelineRunApi(DatasetApiResource): pipeline=pipeline, user=current_user, args=payload.model_dump(), - invoke_from=InvokeFrom.PUBLISHED if payload.is_published else InvokeFrom.DEBUGGER, + invoke_from=InvokeFrom.PUBLISHED_PIPELINE if payload.is_published else InvokeFrom.DEBUGGER, streaming=payload.response_mode == "streaming", ) diff --git a/api/controllers/web/files.py b/api/controllers/web/files.py index 80ad61e549..0036c90800 100644 --- a/api/controllers/web/files.py +++ b/api/controllers/web/files.py @@ -1,5 +1,4 @@ from flask import request -from flask_restx import marshal_with import services from controllers.common.errors import ( @@ -9,12 +8,15 @@ from controllers.common.errors import ( TooManyFilesError, UnsupportedFileTypeError, ) +from controllers.common.schema import register_schema_models from controllers.web import web_ns from controllers.web.wraps import WebApiResource from extensions.ext_database import db -from fields.file_fields import build_file_model +from fields.file_fields import FileResponse from services.file_service import FileService +register_schema_models(web_ns, FileResponse) + @web_ns.route("/files/upload") class FileApi(WebApiResource): @@ -28,7 +30,7 @@ class FileApi(WebApiResource): 415: "Unsupported file type", } ) - @marshal_with(build_file_model(web_ns)) + @web_ns.response(201, "File uploaded successfully", web_ns.models[FileResponse.__name__]) def post(self, app_model, end_user): """Upload a file for use in web applications. @@ -81,4 +83,5 @@ class FileApi(WebApiResource): except services.errors.file.UnsupportedFileTypeError: raise UnsupportedFileTypeError() - return upload_file, 201 + response = FileResponse.model_validate(upload_file, from_attributes=True) + return response.model_dump(mode="json"), 201 diff --git a/api/controllers/web/remote_files.py b/api/controllers/web/remote_files.py index c1f976829f..b08b3fe858 100644 --- a/api/controllers/web/remote_files.py +++ b/api/controllers/web/remote_files.py @@ -1,7 +1,6 @@ import urllib.parse import httpx -from flask_restx import marshal_with from pydantic import BaseModel, Field, HttpUrl import services @@ -14,7 +13,7 @@ from controllers.common.errors import ( from core.file import helpers as file_helpers from core.helper import ssrf_proxy from extensions.ext_database import db -from fields.file_fields import build_file_with_signed_url_model, build_remote_file_info_model +from fields.file_fields import FileWithSignedUrl, RemoteFileInfo from services.file_service import FileService from ..common.schema import register_schema_models @@ -26,7 +25,7 @@ class RemoteFileUploadPayload(BaseModel): url: HttpUrl = Field(description="Remote file URL") -register_schema_models(web_ns, RemoteFileUploadPayload) +register_schema_models(web_ns, RemoteFileUploadPayload, RemoteFileInfo, FileWithSignedUrl) @web_ns.route("/remote-files/") @@ -41,7 +40,7 @@ class RemoteFileInfoApi(WebApiResource): 500: "Failed to fetch remote file", } ) - @marshal_with(build_remote_file_info_model(web_ns)) + @web_ns.response(200, "Remote file info", web_ns.models[RemoteFileInfo.__name__]) def get(self, app_model, end_user, url): """Get information about a remote file. @@ -65,10 +64,11 @@ class RemoteFileInfoApi(WebApiResource): # failed back to get method resp = ssrf_proxy.get(decoded_url, timeout=3) resp.raise_for_status() - return { - "file_type": resp.headers.get("Content-Type", "application/octet-stream"), - "file_length": int(resp.headers.get("Content-Length", -1)), - } + info = RemoteFileInfo( + file_type=resp.headers.get("Content-Type", "application/octet-stream"), + file_length=int(resp.headers.get("Content-Length", -1)), + ) + return info.model_dump(mode="json") @web_ns.route("/remote-files/upload") @@ -84,7 +84,7 @@ class RemoteFileUploadApi(WebApiResource): 500: "Failed to fetch remote file", } ) - @marshal_with(build_file_with_signed_url_model(web_ns)) + @web_ns.response(201, "Remote file uploaded", web_ns.models[FileWithSignedUrl.__name__]) def post(self, app_model, end_user): """Upload a file from a remote URL. @@ -139,13 +139,14 @@ class RemoteFileUploadApi(WebApiResource): except services.errors.file.UnsupportedFileTypeError: raise UnsupportedFileTypeError - return { - "id": upload_file.id, - "name": upload_file.name, - "size": upload_file.size, - "extension": upload_file.extension, - "url": file_helpers.get_signed_file_url(upload_file_id=upload_file.id), - "mime_type": upload_file.mime_type, - "created_by": upload_file.created_by, - "created_at": upload_file.created_at, - }, 201 + payload1 = FileWithSignedUrl( + id=upload_file.id, + name=upload_file.name, + size=upload_file.size, + extension=upload_file.extension, + url=file_helpers.get_signed_file_url(upload_file_id=upload_file.id), + mime_type=upload_file.mime_type, + created_by=upload_file.created_by, + created_at=int(upload_file.created_at.timestamp()), + ) + return payload1.model_dump(mode="json"), 201 diff --git a/api/core/app/apps/advanced_chat/app_runner.py b/api/core/app/apps/advanced_chat/app_runner.py index ee092e55c5..a2ae8dec5b 100644 --- a/api/core/app/apps/advanced_chat/app_runner.py +++ b/api/core/app/apps/advanced_chat/app_runner.py @@ -20,6 +20,8 @@ from core.app.entities.queue_entities import ( QueueTextChunkEvent, ) from core.app.features.annotation_reply.annotation_reply import AnnotationReplyFeature +from core.app.layers.conversation_variable_persist_layer import ConversationVariablePersistenceLayer +from core.db.session_factory import session_factory from core.moderation.base import ModerationError from core.moderation.input_moderation import InputModeration from core.variables.variables import VariableUnion @@ -40,6 +42,7 @@ from models import Workflow from models.enums import UserFrom from models.model import App, Conversation, Message, MessageAnnotation from models.workflow import ConversationVariable +from services.conversation_variable_updater import ConversationVariableUpdater logger = logging.getLogger(__name__) @@ -200,6 +203,10 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner): ) workflow_entry.graph_engine.layer(persistence_layer) + conversation_variable_layer = ConversationVariablePersistenceLayer( + ConversationVariableUpdater(session_factory.get_session_maker()) + ) + workflow_entry.graph_engine.layer(conversation_variable_layer) for layer in self._graph_engine_layers: workflow_entry.graph_engine.layer(layer) diff --git a/api/core/app/apps/pipeline/pipeline_generator.py b/api/core/app/apps/pipeline/pipeline_generator.py index 13eb40fd60..ea4441b5d8 100644 --- a/api/core/app/apps/pipeline/pipeline_generator.py +++ b/api/core/app/apps/pipeline/pipeline_generator.py @@ -130,7 +130,7 @@ class PipelineGenerator(BaseAppGenerator): pipeline=pipeline, workflow=workflow, start_node_id=start_node_id ) documents: list[Document] = [] - if invoke_from == InvokeFrom.PUBLISHED and not is_retry and not args.get("original_document_id"): + if invoke_from == InvokeFrom.PUBLISHED_PIPELINE and not is_retry and not args.get("original_document_id"): from services.dataset_service import DocumentService for datasource_info in datasource_info_list: @@ -156,7 +156,7 @@ class PipelineGenerator(BaseAppGenerator): for i, datasource_info in enumerate(datasource_info_list): workflow_run_id = str(uuid.uuid4()) document_id = args.get("original_document_id") or None - if invoke_from == InvokeFrom.PUBLISHED and not is_retry: + if invoke_from == InvokeFrom.PUBLISHED_PIPELINE and not is_retry: document_id = document_id or documents[i].id document_pipeline_execution_log = DocumentPipelineExecutionLog( document_id=document_id, diff --git a/api/core/app/entities/app_invoke_entities.py b/api/core/app/entities/app_invoke_entities.py index 0cb573cb86..5bc453420d 100644 --- a/api/core/app/entities/app_invoke_entities.py +++ b/api/core/app/entities/app_invoke_entities.py @@ -42,7 +42,8 @@ class InvokeFrom(StrEnum): # DEBUGGER indicates that this invocation is from # the workflow (or chatflow) edit page. DEBUGGER = "debugger" - PUBLISHED = "published" + # PUBLISHED_PIPELINE indicates that this invocation runs a published RAG pipeline workflow. + PUBLISHED_PIPELINE = "published" # VALIDATION indicates that this invocation is from validation. VALIDATION = "validation" diff --git a/api/core/app/layers/conversation_variable_persist_layer.py b/api/core/app/layers/conversation_variable_persist_layer.py new file mode 100644 index 0000000000..77cc00bdc9 --- /dev/null +++ b/api/core/app/layers/conversation_variable_persist_layer.py @@ -0,0 +1,60 @@ +import logging + +from core.variables import Variable +from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID +from core.workflow.conversation_variable_updater import ConversationVariableUpdater +from core.workflow.enums import NodeType +from core.workflow.graph_engine.layers.base import GraphEngineLayer +from core.workflow.graph_events import GraphEngineEvent, NodeRunSucceededEvent +from core.workflow.nodes.variable_assigner.common import helpers as common_helpers + +logger = logging.getLogger(__name__) + + +class ConversationVariablePersistenceLayer(GraphEngineLayer): + def __init__(self, conversation_variable_updater: ConversationVariableUpdater) -> None: + super().__init__() + self._conversation_variable_updater = conversation_variable_updater + + def on_graph_start(self) -> None: + pass + + def on_event(self, event: GraphEngineEvent) -> None: + if not isinstance(event, NodeRunSucceededEvent): + return + if event.node_type != NodeType.VARIABLE_ASSIGNER: + return + if self.graph_runtime_state is None: + return + + updated_variables = common_helpers.get_updated_variables(event.node_run_result.process_data) or [] + if not updated_variables: + return + + conversation_id = self.graph_runtime_state.system_variable.conversation_id + if conversation_id is None: + return + + updated_any = False + for item in updated_variables: + selector = item.selector + if len(selector) < 2: + logger.warning("Conversation variable selector invalid. selector=%s", selector) + continue + if selector[0] != CONVERSATION_VARIABLE_NODE_ID: + continue + variable = self.graph_runtime_state.variable_pool.get(selector) + if not isinstance(variable, Variable): + logger.warning( + "Conversation variable not found in variable pool. selector=%s", + selector, + ) + continue + self._conversation_variable_updater.update(conversation_id=conversation_id, variable=variable) + updated_any = True + + if updated_any: + self._conversation_variable_updater.flush() + + def on_graph_end(self, error: Exception | None) -> None: + pass diff --git a/api/core/datasource/__base/datasource_plugin.py b/api/core/datasource/__base/datasource_plugin.py index 50c7249fe4..451e4fda0e 100644 --- a/api/core/datasource/__base/datasource_plugin.py +++ b/api/core/datasource/__base/datasource_plugin.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from abc import ABC, abstractmethod from configs import dify_config @@ -30,7 +32,7 @@ class DatasourcePlugin(ABC): """ return DatasourceProviderType.LOCAL_FILE - def fork_datasource_runtime(self, runtime: DatasourceRuntime) -> "DatasourcePlugin": + def fork_datasource_runtime(self, runtime: DatasourceRuntime) -> DatasourcePlugin: return self.__class__( entity=self.entity.model_copy(), runtime=runtime, diff --git a/api/core/datasource/entities/datasource_entities.py b/api/core/datasource/entities/datasource_entities.py index 260dcf04f5..dde7d59726 100644 --- a/api/core/datasource/entities/datasource_entities.py +++ b/api/core/datasource/entities/datasource_entities.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import enum from enum import StrEnum from typing import Any @@ -31,7 +33,7 @@ class DatasourceProviderType(enum.StrEnum): ONLINE_DRIVE = "online_drive" @classmethod - def value_of(cls, value: str) -> "DatasourceProviderType": + def value_of(cls, value: str) -> DatasourceProviderType: """ Get value of given mode. @@ -81,7 +83,7 @@ class DatasourceParameter(PluginParameter): typ: DatasourceParameterType, required: bool, options: list[str] | None = None, - ) -> "DatasourceParameter": + ) -> DatasourceParameter: """ get a simple datasource parameter @@ -187,14 +189,14 @@ class DatasourceInvokeMeta(BaseModel): tool_config: dict | None = None @classmethod - def empty(cls) -> "DatasourceInvokeMeta": + def empty(cls) -> DatasourceInvokeMeta: """ Get an empty instance of DatasourceInvokeMeta """ return cls(time_cost=0.0, error=None, tool_config={}) @classmethod - def error_instance(cls, error: str) -> "DatasourceInvokeMeta": + def error_instance(cls, error: str) -> DatasourceInvokeMeta: """ Get an instance of DatasourceInvokeMeta with error """ diff --git a/api/core/db/session_factory.py b/api/core/db/session_factory.py index 1dae2eafd4..45d4bc4594 100644 --- a/api/core/db/session_factory.py +++ b/api/core/db/session_factory.py @@ -1,7 +1,7 @@ from sqlalchemy import Engine from sqlalchemy.orm import Session, sessionmaker -_session_maker: sessionmaker | None = None +_session_maker: sessionmaker[Session] | None = None def configure_session_factory(engine: Engine, expire_on_commit: bool = False): @@ -10,7 +10,7 @@ def configure_session_factory(engine: Engine, expire_on_commit: bool = False): _session_maker = sessionmaker(bind=engine, expire_on_commit=expire_on_commit) -def get_session_maker() -> sessionmaker: +def get_session_maker() -> sessionmaker[Session]: if _session_maker is None: raise RuntimeError("Session factory not configured. Call configure_session_factory() first.") return _session_maker @@ -27,7 +27,7 @@ class SessionFactory: configure_session_factory(engine, expire_on_commit) @staticmethod - def get_session_maker() -> sessionmaker: + def get_session_maker() -> sessionmaker[Session]: return get_session_maker() @staticmethod diff --git a/api/core/entities/mcp_provider.py b/api/core/entities/mcp_provider.py index 7fdf5e4be6..135d2a4945 100644 --- a/api/core/entities/mcp_provider.py +++ b/api/core/entities/mcp_provider.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import json from datetime import datetime from enum import StrEnum @@ -75,7 +77,7 @@ class MCPProviderEntity(BaseModel): updated_at: datetime @classmethod - def from_db_model(cls, db_provider: "MCPToolProvider") -> "MCPProviderEntity": + def from_db_model(cls, db_provider: MCPToolProvider) -> MCPProviderEntity: """Create entity from database model with decryption""" return cls( diff --git a/api/core/entities/provider_entities.py b/api/core/entities/provider_entities.py index 8a8067332d..0078ec7e4f 100644 --- a/api/core/entities/provider_entities.py +++ b/api/core/entities/provider_entities.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from enum import StrEnum, auto from typing import Union @@ -178,7 +180,7 @@ class BasicProviderConfig(BaseModel): TOOLS_SELECTOR = CommonParameterType.TOOLS_SELECTOR @classmethod - def value_of(cls, value: str) -> "ProviderConfig.Type": + def value_of(cls, value: str) -> ProviderConfig.Type: """ Get value of given mode. diff --git a/api/core/file/helpers.py b/api/core/file/helpers.py index 6d553d7dc6..2ac483673a 100644 --- a/api/core/file/helpers.py +++ b/api/core/file/helpers.py @@ -8,8 +8,9 @@ import urllib.parse from configs import dify_config -def get_signed_file_url(upload_file_id: str, as_attachment=False) -> str: - url = f"{dify_config.FILES_URL}/files/{upload_file_id}/file-preview" +def get_signed_file_url(upload_file_id: str, as_attachment=False, for_external: bool = True) -> str: + base_url = dify_config.FILES_URL if for_external else (dify_config.INTERNAL_FILES_URL or dify_config.FILES_URL) + url = f"{base_url}/files/{upload_file_id}/file-preview" timestamp = str(int(time.time())) nonce = os.urandom(16).hex() diff --git a/api/core/file/models.py b/api/core/file/models.py index d149205d77..6324523b22 100644 --- a/api/core/file/models.py +++ b/api/core/file/models.py @@ -112,17 +112,17 @@ class File(BaseModel): return text - def generate_url(self) -> str | None: + def generate_url(self, for_external: bool = True) -> str | None: if self.transfer_method == FileTransferMethod.REMOTE_URL: return self.remote_url elif self.transfer_method == FileTransferMethod.LOCAL_FILE: if self.related_id is None: raise ValueError("Missing file related_id") - return helpers.get_signed_file_url(upload_file_id=self.related_id) + return helpers.get_signed_file_url(upload_file_id=self.related_id, for_external=for_external) elif self.transfer_method in [FileTransferMethod.TOOL_FILE, FileTransferMethod.DATASOURCE_FILE]: assert self.related_id is not None assert self.extension is not None - return sign_tool_file(tool_file_id=self.related_id, extension=self.extension) + return sign_tool_file(tool_file_id=self.related_id, extension=self.extension, for_external=for_external) return None def to_plugin_parameter(self) -> dict[str, Any]: @@ -133,7 +133,7 @@ class File(BaseModel): "extension": self.extension, "size": self.size, "type": self.type, - "url": self.generate_url(), + "url": self.generate_url(for_external=False), } @model_validator(mode="after") diff --git a/api/core/helper/code_executor/template_transformer.py b/api/core/helper/code_executor/template_transformer.py index 6fda073913..5cdea19a8d 100644 --- a/api/core/helper/code_executor/template_transformer.py +++ b/api/core/helper/code_executor/template_transformer.py @@ -76,7 +76,7 @@ class TemplateTransformer(ABC): Post-process the result to convert scientific notation strings back to numbers """ - def convert_scientific_notation(value): + def convert_scientific_notation(value: Any) -> Any: if isinstance(value, str): # Check if the string looks like scientific notation if re.match(r"^-?\d+\.?\d*e[+-]\d+$", value, re.IGNORECASE): @@ -90,7 +90,7 @@ class TemplateTransformer(ABC): return [convert_scientific_notation(v) for v in value] return value - return convert_scientific_notation(result) # type: ignore[no-any-return] + return convert_scientific_notation(result) @classmethod @abstractmethod diff --git a/api/core/mcp/session/base_session.py b/api/core/mcp/session/base_session.py index c97ae6eac7..84a6fd0d1f 100644 --- a/api/core/mcp/session/base_session.py +++ b/api/core/mcp/session/base_session.py @@ -68,13 +68,7 @@ class RequestResponder(Generic[ReceiveRequestT, SendResultT]): request_id: RequestId, request_meta: RequestParams.Meta | None, request: ReceiveRequestT, - session: """BaseSession[ - SendRequestT, - SendNotificationT, - SendResultT, - ReceiveRequestT, - ReceiveNotificationT - ]""", + session: """BaseSession[SendRequestT, SendNotificationT, SendResultT, ReceiveRequestT, ReceiveNotificationT]""", on_complete: Callable[["RequestResponder[ReceiveRequestT, SendResultT]"], Any], ): self.request_id = request_id diff --git a/api/core/model_runtime/entities/message_entities.py b/api/core/model_runtime/entities/message_entities.py index 89dae2dbff..3ac83b4c96 100644 --- a/api/core/model_runtime/entities/message_entities.py +++ b/api/core/model_runtime/entities/message_entities.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from abc import ABC from collections.abc import Mapping, Sequence from enum import StrEnum, auto @@ -17,7 +19,7 @@ class PromptMessageRole(StrEnum): TOOL = auto() @classmethod - def value_of(cls, value: str) -> "PromptMessageRole": + def value_of(cls, value: str) -> PromptMessageRole: """ Get value of given mode. diff --git a/api/core/model_runtime/entities/model_entities.py b/api/core/model_runtime/entities/model_entities.py index aee6ce1108..19194d162c 100644 --- a/api/core/model_runtime/entities/model_entities.py +++ b/api/core/model_runtime/entities/model_entities.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from decimal import Decimal from enum import StrEnum, auto from typing import Any @@ -20,7 +22,7 @@ class ModelType(StrEnum): TTS = auto() @classmethod - def value_of(cls, origin_model_type: str) -> "ModelType": + def value_of(cls, origin_model_type: str) -> ModelType: """ Get model type from origin model type. @@ -103,7 +105,7 @@ class DefaultParameterName(StrEnum): JSON_SCHEMA = auto() @classmethod - def value_of(cls, value: Any) -> "DefaultParameterName": + def value_of(cls, value: Any) -> DefaultParameterName: """ Get parameter name from value. diff --git a/api/core/model_runtime/model_providers/model_provider_factory.py b/api/core/model_runtime/model_providers/model_provider_factory.py index 12a202ce64..28f162a928 100644 --- a/api/core/model_runtime/model_providers/model_provider_factory.py +++ b/api/core/model_runtime/model_providers/model_provider_factory.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import hashlib import logging from collections.abc import Sequence @@ -38,7 +40,7 @@ class ModelProviderFactory: plugin_providers = self.get_plugin_model_providers() return [provider.declaration for provider in plugin_providers] - def get_plugin_model_providers(self) -> Sequence["PluginModelProviderEntity"]: + def get_plugin_model_providers(self) -> Sequence[PluginModelProviderEntity]: """ Get all plugin model providers :return: list of plugin model providers @@ -76,7 +78,7 @@ class ModelProviderFactory: plugin_model_provider_entity = self.get_plugin_model_provider(provider=provider) return plugin_model_provider_entity.declaration - def get_plugin_model_provider(self, provider: str) -> "PluginModelProviderEntity": + def get_plugin_model_provider(self, provider: str) -> PluginModelProviderEntity: """ Get plugin model provider :param provider: provider name diff --git a/api/core/plugin/entities/plugin_daemon.py b/api/core/plugin/entities/plugin_daemon.py index 3b83121357..6674228dc0 100644 --- a/api/core/plugin/entities/plugin_daemon.py +++ b/api/core/plugin/entities/plugin_daemon.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import enum from collections.abc import Mapping, Sequence from datetime import datetime @@ -242,7 +244,7 @@ class CredentialType(enum.StrEnum): return [item.value for item in cls] @classmethod - def of(cls, credential_type: str) -> "CredentialType": + def of(cls, credential_type: str) -> CredentialType: type_name = credential_type.lower() if type_name in {"api-key", "api_key"}: return cls.API_KEY diff --git a/api/core/rag/datasource/vdb/clickzetta/clickzetta_vector.py b/api/core/rag/datasource/vdb/clickzetta/clickzetta_vector.py index e05b70ba22..91bb71bfa6 100644 --- a/api/core/rag/datasource/vdb/clickzetta/clickzetta_vector.py +++ b/api/core/rag/datasource/vdb/clickzetta/clickzetta_vector.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import contextlib import json import logging @@ -6,7 +8,7 @@ import re import threading import time import uuid -from typing import TYPE_CHECKING, Any, Optional +from typing import TYPE_CHECKING, Any import clickzetta # type: ignore from pydantic import BaseModel, model_validator @@ -76,7 +78,7 @@ class ClickzettaConnectionPool: Manages connection reuse across ClickzettaVector instances. """ - _instance: Optional["ClickzettaConnectionPool"] = None + _instance: ClickzettaConnectionPool | None = None _lock = threading.Lock() def __init__(self): @@ -89,7 +91,7 @@ class ClickzettaConnectionPool: self._start_cleanup_thread() @classmethod - def get_instance(cls) -> "ClickzettaConnectionPool": + def get_instance(cls) -> ClickzettaConnectionPool: """Get singleton instance of connection pool.""" if cls._instance is None: with cls._lock: @@ -104,7 +106,7 @@ class ClickzettaConnectionPool: f"{config.workspace}:{config.vcluster}:{config.schema_name}" ) - def _create_connection(self, config: ClickzettaConfig) -> "Connection": + def _create_connection(self, config: ClickzettaConfig) -> Connection: """Create a new ClickZetta connection.""" max_retries = 3 retry_delay = 1.0 @@ -134,7 +136,7 @@ class ClickzettaConnectionPool: raise RuntimeError(f"Failed to create ClickZetta connection after {max_retries} attempts") - def _configure_connection(self, connection: "Connection"): + def _configure_connection(self, connection: Connection): """Configure connection session settings.""" try: with connection.cursor() as cursor: @@ -181,7 +183,7 @@ class ClickzettaConnectionPool: except Exception: logger.exception("Failed to configure connection, continuing with defaults") - def _is_connection_valid(self, connection: "Connection") -> bool: + def _is_connection_valid(self, connection: Connection) -> bool: """Check if connection is still valid.""" try: with connection.cursor() as cursor: @@ -190,7 +192,7 @@ class ClickzettaConnectionPool: except Exception: return False - def get_connection(self, config: ClickzettaConfig) -> "Connection": + def get_connection(self, config: ClickzettaConfig) -> Connection: """Get a connection from the pool or create a new one.""" config_key = self._get_config_key(config) @@ -221,7 +223,7 @@ class ClickzettaConnectionPool: # No valid connection found, create new one return self._create_connection(config) - def return_connection(self, config: ClickzettaConfig, connection: "Connection"): + def return_connection(self, config: ClickzettaConfig, connection: Connection): """Return a connection to the pool.""" config_key = self._get_config_key(config) @@ -315,22 +317,22 @@ class ClickzettaVector(BaseVector): self._connection_pool = ClickzettaConnectionPool.get_instance() self._init_write_queue() - def _get_connection(self) -> "Connection": + def _get_connection(self) -> Connection: """Get a connection from the pool.""" return self._connection_pool.get_connection(self._config) - def _return_connection(self, connection: "Connection"): + def _return_connection(self, connection: Connection): """Return a connection to the pool.""" self._connection_pool.return_connection(self._config, connection) class ConnectionContext: """Context manager for borrowing and returning connections.""" - def __init__(self, vector_instance: "ClickzettaVector"): + def __init__(self, vector_instance: ClickzettaVector): self.vector = vector_instance self.connection: Connection | None = None - def __enter__(self) -> "Connection": + def __enter__(self) -> Connection: self.connection = self.vector._get_connection() return self.connection @@ -338,7 +340,7 @@ class ClickzettaVector(BaseVector): if self.connection: self.vector._return_connection(self.connection) - def get_connection_context(self) -> "ClickzettaVector.ConnectionContext": + def get_connection_context(self) -> ClickzettaVector.ConnectionContext: """Get a connection context manager.""" return self.ConnectionContext(self) @@ -437,7 +439,7 @@ class ClickzettaVector(BaseVector): """Return the vector database type.""" return "clickzetta" - def _ensure_connection(self) -> "Connection": + def _ensure_connection(self) -> Connection: """Get a connection from the pool.""" return self._get_connection() diff --git a/api/core/rag/docstore/dataset_docstore.py b/api/core/rag/docstore/dataset_docstore.py index 1fe74d3042..69adac522d 100644 --- a/api/core/rag/docstore/dataset_docstore.py +++ b/api/core/rag/docstore/dataset_docstore.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from collections.abc import Sequence from typing import Any @@ -22,7 +24,7 @@ class DatasetDocumentStore: self._document_id = document_id @classmethod - def from_dict(cls, config_dict: dict[str, Any]) -> "DatasetDocumentStore": + def from_dict(cls, config_dict: dict[str, Any]) -> DatasetDocumentStore: return cls(**config_dict) def to_dict(self) -> dict[str, Any]: diff --git a/api/core/rag/extractor/word_extractor.py b/api/core/rag/extractor/word_extractor.py index f67f613e9d..511f5a698d 100644 --- a/api/core/rag/extractor/word_extractor.py +++ b/api/core/rag/extractor/word_extractor.py @@ -7,10 +7,11 @@ import re import tempfile import uuid from urllib.parse import urlparse -from xml.etree import ElementTree import httpx from docx import Document as DocxDocument +from docx.oxml.ns import qn +from docx.text.run import Run from configs import dify_config from core.helper import ssrf_proxy @@ -229,44 +230,20 @@ class WordExtractor(BaseExtractor): image_map = self._extract_images_from_docx(doc) - hyperlinks_url = None - url_pattern = re.compile(r"http://[^\s+]+//|https://[^\s+]+") - for para in doc.paragraphs: - for run in para.runs: - if run.text and hyperlinks_url: - result = f" [{run.text}]({hyperlinks_url}) " - run.text = result - hyperlinks_url = None - if "HYPERLINK" in run.element.xml: - try: - xml = ElementTree.XML(run.element.xml) - x_child = [c for c in xml.iter() if c is not None] - for x in x_child: - if x is None: - continue - if x.tag.endswith("instrText"): - if x.text is None: - continue - for i in url_pattern.findall(x.text): - hyperlinks_url = str(i) - except Exception: - logger.exception("Failed to parse HYPERLINK xml") - def parse_paragraph(paragraph): - paragraph_content = [] - - def append_image_link(image_id, has_drawing): + def append_image_link(image_id, has_drawing, target_buffer): """Helper to append image link from image_map based on relationship type.""" rel = doc.part.rels[image_id] if rel.is_external: if image_id in image_map and not has_drawing: - paragraph_content.append(image_map[image_id]) + target_buffer.append(image_map[image_id]) else: image_part = rel.target_part if image_part in image_map and not has_drawing: - paragraph_content.append(image_map[image_part]) + target_buffer.append(image_map[image_part]) - for run in paragraph.runs: + def process_run(run, target_buffer): + # Helper to extract text and embedded images from a run element and append them to target_buffer if hasattr(run.element, "tag") and isinstance(run.element.tag, str) and run.element.tag.endswith("r"): # Process drawing type images drawing_elements = run.element.findall( @@ -287,13 +264,13 @@ class WordExtractor(BaseExtractor): # External image: use embed_id as key if embed_id in image_map: has_drawing = True - paragraph_content.append(image_map[embed_id]) + target_buffer.append(image_map[embed_id]) else: # Internal image: use target_part as key image_part = doc.part.related_parts.get(embed_id) if image_part in image_map: has_drawing = True - paragraph_content.append(image_map[image_part]) + target_buffer.append(image_map[image_part]) # Process pict type images shape_elements = run.element.findall( ".//{http://schemas.openxmlformats.org/wordprocessingml/2006/main}pict" @@ -308,7 +285,7 @@ class WordExtractor(BaseExtractor): "{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id" ) if image_id and image_id in doc.part.rels: - append_image_link(image_id, has_drawing) + append_image_link(image_id, has_drawing, target_buffer) # Find imagedata element in VML image_data = shape.find(".//{urn:schemas-microsoft-com:vml}imagedata") if image_data is not None: @@ -316,9 +293,93 @@ class WordExtractor(BaseExtractor): "{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id" ) if image_id and image_id in doc.part.rels: - append_image_link(image_id, has_drawing) + append_image_link(image_id, has_drawing, target_buffer) if run.text.strip(): - paragraph_content.append(run.text.strip()) + target_buffer.append(run.text.strip()) + + def process_hyperlink(hyperlink_elem, target_buffer): + # Helper to extract text from a hyperlink element and append it to target_buffer + r_id = hyperlink_elem.get(qn("r:id")) + + # Extract text from runs inside the hyperlink + link_text_parts = [] + for run_elem in hyperlink_elem.findall(qn("w:r")): + run = Run(run_elem, paragraph) + # Hyperlink text may be split across multiple runs (e.g., with different formatting), + # so collect all run texts first + if run.text: + link_text_parts.append(run.text) + + link_text = "".join(link_text_parts).strip() + + # Resolve URL + if r_id: + try: + rel = doc.part.rels.get(r_id) + if rel and rel.is_external: + link_text = f"[{link_text or rel.target_ref}]({rel.target_ref})" + except Exception: + logger.exception("Failed to resolve URL for hyperlink with r:id: %s", r_id) + + if link_text: + target_buffer.append(link_text) + + paragraph_content = [] + # State for legacy HYPERLINK fields + hyperlink_field_url = None + hyperlink_field_text_parts: list = [] + is_collecting_field_text = False + # Iterate through paragraph elements in document order + for child in paragraph._element: + tag = child.tag + if tag == qn("w:r"): + # Regular run + run = Run(child, paragraph) + + # Check for fldChar (begin/end/separate) and instrText for legacy hyperlinks + fld_chars = child.findall(qn("w:fldChar")) + instr_texts = child.findall(qn("w:instrText")) + + # Handle Fields + if fld_chars or instr_texts: + # Process instrText to find HYPERLINK "url" + for instr in instr_texts: + if instr.text and "HYPERLINK" in instr.text: + # Quick regex to extract URL + match = re.search(r'HYPERLINK\s+"([^"]+)"', instr.text, re.IGNORECASE) + if match: + hyperlink_field_url = match.group(1) + + # Process fldChar + for fld_char in fld_chars: + fld_char_type = fld_char.get(qn("w:fldCharType")) + if fld_char_type == "begin": + # Start of a field: reset legacy link state + hyperlink_field_url = None + hyperlink_field_text_parts = [] + is_collecting_field_text = False + elif fld_char_type == "separate": + # Separator: if we found a URL, start collecting visible text + if hyperlink_field_url: + is_collecting_field_text = True + elif fld_char_type == "end": + # End of field + if is_collecting_field_text and hyperlink_field_url: + # Create markdown link and append to main content + display_text = "".join(hyperlink_field_text_parts).strip() + if display_text: + link_md = f"[{display_text}]({hyperlink_field_url})" + paragraph_content.append(link_md) + # Reset state + hyperlink_field_url = None + hyperlink_field_text_parts = [] + is_collecting_field_text = False + + # Decide where to append content + target_buffer = hyperlink_field_text_parts if is_collecting_field_text else paragraph_content + process_run(run, target_buffer) + elif tag == qn("w:hyperlink"): + process_hyperlink(child, paragraph_content) return "".join(paragraph_content) if paragraph_content else "" paragraphs = doc.paragraphs.copy() diff --git a/api/core/rag/pipeline/queue.py b/api/core/rag/pipeline/queue.py index 7472598a7f..bf8db95b4e 100644 --- a/api/core/rag/pipeline/queue.py +++ b/api/core/rag/pipeline/queue.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import json from collections.abc import Sequence from typing import Any @@ -16,7 +18,7 @@ class TaskWrapper(BaseModel): return self.model_dump_json() @classmethod - def deserialize(cls, serialized_data: str) -> "TaskWrapper": + def deserialize(cls, serialized_data: str) -> TaskWrapper: return cls.model_validate_json(serialized_data) diff --git a/api/core/schemas/registry.py b/api/core/schemas/registry.py index 51bfae1cd3..b4ecfe47ff 100644 --- a/api/core/schemas/registry.py +++ b/api/core/schemas/registry.py @@ -1,9 +1,11 @@ +from __future__ import annotations + import json import logging import threading from collections.abc import Mapping, MutableMapping from pathlib import Path -from typing import Any, ClassVar, Optional +from typing import Any, ClassVar class SchemaRegistry: @@ -11,7 +13,7 @@ class SchemaRegistry: logger: ClassVar[logging.Logger] = logging.getLogger(__name__) - _default_instance: ClassVar[Optional["SchemaRegistry"]] = None + _default_instance: ClassVar[SchemaRegistry | None] = None _lock: ClassVar[threading.Lock] = threading.Lock() def __init__(self, base_dir: str): @@ -20,7 +22,7 @@ class SchemaRegistry: self.metadata: MutableMapping[str, MutableMapping[str, Any]] = {} @classmethod - def default_registry(cls) -> "SchemaRegistry": + def default_registry(cls) -> SchemaRegistry: """Returns the default schema registry for builtin schemas (thread-safe singleton)""" if cls._default_instance is None: with cls._lock: diff --git a/api/core/tools/__base/tool.py b/api/core/tools/__base/tool.py index 8ca4eabb7a..ebd200a822 100644 --- a/api/core/tools/__base/tool.py +++ b/api/core/tools/__base/tool.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from abc import ABC, abstractmethod from collections.abc import Generator from copy import deepcopy @@ -24,7 +26,7 @@ class Tool(ABC): self.entity = entity self.runtime = runtime - def fork_tool_runtime(self, runtime: ToolRuntime) -> "Tool": + def fork_tool_runtime(self, runtime: ToolRuntime) -> Tool: """ fork a new tool with metadata :return: the new tool @@ -166,7 +168,7 @@ class Tool(ABC): type=ToolInvokeMessage.MessageType.IMAGE, message=ToolInvokeMessage.TextMessage(text=image) ) - def create_file_message(self, file: "File") -> ToolInvokeMessage: + def create_file_message(self, file: File) -> ToolInvokeMessage: return ToolInvokeMessage( type=ToolInvokeMessage.MessageType.FILE, message=ToolInvokeMessage.FileMessage(), diff --git a/api/core/tools/builtin_tool/tool.py b/api/core/tools/builtin_tool/tool.py index 84efefba07..51b0407886 100644 --- a/api/core/tools/builtin_tool/tool.py +++ b/api/core/tools/builtin_tool/tool.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from core.model_runtime.entities.llm_entities import LLMResult from core.model_runtime.entities.message_entities import PromptMessage, SystemPromptMessage, UserPromptMessage from core.tools.__base.tool import Tool @@ -24,7 +26,7 @@ class BuiltinTool(Tool): super().__init__(**kwargs) self.provider = provider - def fork_tool_runtime(self, runtime: ToolRuntime) -> "BuiltinTool": + def fork_tool_runtime(self, runtime: ToolRuntime) -> BuiltinTool: """ fork a new tool with metadata :return: the new tool diff --git a/api/core/tools/custom_tool/provider.py b/api/core/tools/custom_tool/provider.py index 0cc992155a..e2f6c00555 100644 --- a/api/core/tools/custom_tool/provider.py +++ b/api/core/tools/custom_tool/provider.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from pydantic import Field from sqlalchemy import select @@ -32,7 +34,7 @@ class ApiToolProviderController(ToolProviderController): self.tools = [] @classmethod - def from_db(cls, db_provider: ApiToolProvider, auth_type: ApiProviderAuthType) -> "ApiToolProviderController": + def from_db(cls, db_provider: ApiToolProvider, auth_type: ApiProviderAuthType) -> ApiToolProviderController: credentials_schema = [ ProviderConfig( name="auth_type", diff --git a/api/core/tools/entities/tool_entities.py b/api/core/tools/entities/tool_entities.py index 583a3584f7..b5c7a6310c 100644 --- a/api/core/tools/entities/tool_entities.py +++ b/api/core/tools/entities/tool_entities.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import base64 import contextlib from collections.abc import Mapping @@ -55,7 +57,7 @@ class ToolProviderType(StrEnum): MCP = auto() @classmethod - def value_of(cls, value: str) -> "ToolProviderType": + def value_of(cls, value: str) -> ToolProviderType: """ Get value of given mode. @@ -79,7 +81,7 @@ class ApiProviderSchemaType(StrEnum): OPENAI_ACTIONS = auto() @classmethod - def value_of(cls, value: str) -> "ApiProviderSchemaType": + def value_of(cls, value: str) -> ApiProviderSchemaType: """ Get value of given mode. @@ -102,7 +104,7 @@ class ApiProviderAuthType(StrEnum): API_KEY_QUERY = auto() @classmethod - def value_of(cls, value: str) -> "ApiProviderAuthType": + def value_of(cls, value: str) -> ApiProviderAuthType: """ Get value of given mode. @@ -307,7 +309,7 @@ class ToolParameter(PluginParameter): typ: ToolParameterType, required: bool, options: list[str] | None = None, - ) -> "ToolParameter": + ) -> ToolParameter: """ get a simple tool parameter @@ -429,14 +431,14 @@ class ToolInvokeMeta(BaseModel): tool_config: dict | None = None @classmethod - def empty(cls) -> "ToolInvokeMeta": + def empty(cls) -> ToolInvokeMeta: """ Get an empty instance of ToolInvokeMeta """ return cls(time_cost=0.0, error=None, tool_config={}) @classmethod - def error_instance(cls, error: str) -> "ToolInvokeMeta": + def error_instance(cls, error: str) -> ToolInvokeMeta: """ Get an instance of ToolInvokeMeta with error """ diff --git a/api/core/tools/mcp_tool/tool.py b/api/core/tools/mcp_tool/tool.py index 96917045e3..ef9e9c103a 100644 --- a/api/core/tools/mcp_tool/tool.py +++ b/api/core/tools/mcp_tool/tool.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import base64 import json import logging @@ -118,7 +120,7 @@ class MCPTool(Tool): for item in json_list: yield self.create_json_message(item) - def fork_tool_runtime(self, runtime: ToolRuntime) -> "MCPTool": + def fork_tool_runtime(self, runtime: ToolRuntime) -> MCPTool: return MCPTool( entity=self.entity, runtime=runtime, diff --git a/api/core/tools/plugin_tool/tool.py b/api/core/tools/plugin_tool/tool.py index 828dc3b810..d3a2ad488c 100644 --- a/api/core/tools/plugin_tool/tool.py +++ b/api/core/tools/plugin_tool/tool.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from collections.abc import Generator from typing import Any @@ -46,7 +48,7 @@ class PluginTool(Tool): message_id=message_id, ) - def fork_tool_runtime(self, runtime: ToolRuntime) -> "PluginTool": + def fork_tool_runtime(self, runtime: ToolRuntime) -> PluginTool: return PluginTool( entity=self.entity, runtime=runtime, diff --git a/api/core/tools/signature.py b/api/core/tools/signature.py index fef3157f27..22e099deba 100644 --- a/api/core/tools/signature.py +++ b/api/core/tools/signature.py @@ -7,12 +7,12 @@ import time from configs import dify_config -def sign_tool_file(tool_file_id: str, extension: str) -> str: +def sign_tool_file(tool_file_id: str, extension: str, for_external: bool = True) -> str: """ sign file to get a temporary url for plugin access """ - # Use internal URL for plugin/tool file access in Docker environments - base_url = dify_config.INTERNAL_FILES_URL or dify_config.FILES_URL + # Use internal URL for plugin/tool file access in Docker environments, unless for_external is True + base_url = dify_config.FILES_URL if for_external else (dify_config.INTERNAL_FILES_URL or dify_config.FILES_URL) file_preview_url = f"{base_url}/files/tools/{tool_file_id}{extension}" timestamp = str(int(time.time())) diff --git a/api/core/tools/workflow_as_tool/provider.py b/api/core/tools/workflow_as_tool/provider.py index 5422f5250b..a706f101ca 100644 --- a/api/core/tools/workflow_as_tool/provider.py +++ b/api/core/tools/workflow_as_tool/provider.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from collections.abc import Mapping from pydantic import Field @@ -47,7 +49,7 @@ class WorkflowToolProviderController(ToolProviderController): self.provider_id = provider_id @classmethod - def from_db(cls, db_provider: WorkflowToolProvider) -> "WorkflowToolProviderController": + def from_db(cls, db_provider: WorkflowToolProvider) -> WorkflowToolProviderController: with session_factory.create_session() as session, session.begin(): app = session.get(App, db_provider.app_id) if not app: diff --git a/api/core/tools/workflow_as_tool/tool.py b/api/core/tools/workflow_as_tool/tool.py index 30334f5da8..81a1d54199 100644 --- a/api/core/tools/workflow_as_tool/tool.py +++ b/api/core/tools/workflow_as_tool/tool.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import json import logging from collections.abc import Generator, Mapping, Sequence @@ -181,7 +183,7 @@ class WorkflowTool(Tool): return found return None - def fork_tool_runtime(self, runtime: ToolRuntime) -> "WorkflowTool": + def fork_tool_runtime(self, runtime: ToolRuntime) -> WorkflowTool: """ fork a new tool with metadata diff --git a/api/core/variables/types.py b/api/core/variables/types.py index ce71711344..13b926c978 100644 --- a/api/core/variables/types.py +++ b/api/core/variables/types.py @@ -1,6 +1,8 @@ +from __future__ import annotations + from collections.abc import Mapping from enum import StrEnum -from typing import TYPE_CHECKING, Any, Optional +from typing import TYPE_CHECKING, Any from core.file.models import File @@ -52,7 +54,7 @@ class SegmentType(StrEnum): return self in _ARRAY_TYPES @classmethod - def infer_segment_type(cls, value: Any) -> Optional["SegmentType"]: + def infer_segment_type(cls, value: Any) -> SegmentType | None: """ Attempt to infer the `SegmentType` based on the Python type of the `value` parameter. @@ -173,7 +175,7 @@ class SegmentType(StrEnum): raise AssertionError("this statement should be unreachable.") @staticmethod - def cast_value(value: Any, type_: "SegmentType"): + def cast_value(value: Any, type_: SegmentType): # Cast Python's `bool` type to `int` when the runtime type requires # an integer or number. # @@ -193,7 +195,7 @@ class SegmentType(StrEnum): return [int(i) for i in value] return value - def exposed_type(self) -> "SegmentType": + def exposed_type(self) -> SegmentType: """Returns the type exposed to the frontend. The frontend treats `INTEGER` and `FLOAT` as `NUMBER`, so these are returned as `NUMBER` here. @@ -202,7 +204,7 @@ class SegmentType(StrEnum): return SegmentType.NUMBER return self - def element_type(self) -> "SegmentType | None": + def element_type(self) -> SegmentType | None: """Return the element type of the current segment type, or `None` if the element type is undefined. Raises: @@ -217,7 +219,7 @@ class SegmentType(StrEnum): return _ARRAY_ELEMENT_TYPES_MAPPING.get(self) @staticmethod - def get_zero_value(t: "SegmentType"): + def get_zero_value(t: SegmentType): # Lazy import to avoid circular dependency from factories import variable_factory diff --git a/api/core/workflow/entities/workflow_execution.py b/api/core/workflow/entities/workflow_execution.py index a8a86d3db2..1b3fb36f1f 100644 --- a/api/core/workflow/entities/workflow_execution.py +++ b/api/core/workflow/entities/workflow_execution.py @@ -5,6 +5,8 @@ Models are independent of the storage mechanism and don't contain implementation details like tenant_id, app_id, etc. """ +from __future__ import annotations + from collections.abc import Mapping from datetime import datetime from typing import Any @@ -59,7 +61,7 @@ class WorkflowExecution(BaseModel): graph: Mapping[str, Any], inputs: Mapping[str, Any], started_at: datetime, - ) -> "WorkflowExecution": + ) -> WorkflowExecution: return WorkflowExecution( id_=id_, workflow_id=workflow_id, diff --git a/api/core/workflow/graph/graph.py b/api/core/workflow/graph/graph.py index ba5a01fc94..7be94c2426 100644 --- a/api/core/workflow/graph/graph.py +++ b/api/core/workflow/graph/graph.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import logging from collections import defaultdict from collections.abc import Mapping, Sequence @@ -175,7 +177,7 @@ class Graph: def _create_node_instances( cls, node_configs_map: dict[str, dict[str, object]], - node_factory: "NodeFactory", + node_factory: NodeFactory, ) -> dict[str, Node]: """ Create node instances from configurations using the node factory. @@ -197,7 +199,7 @@ class Graph: return nodes @classmethod - def new(cls) -> "GraphBuilder": + def new(cls) -> GraphBuilder: """Create a fluent builder for assembling a graph programmatically.""" return GraphBuilder(graph_cls=cls) @@ -284,9 +286,9 @@ class Graph: cls, *, graph_config: Mapping[str, object], - node_factory: "NodeFactory", + node_factory: NodeFactory, root_node_id: str | None = None, - ) -> "Graph": + ) -> Graph: """ Initialize graph @@ -383,7 +385,7 @@ class GraphBuilder: self._edges: list[Edge] = [] self._edge_counter = 0 - def add_root(self, node: Node) -> "GraphBuilder": + def add_root(self, node: Node) -> GraphBuilder: """Register the root node. Must be called exactly once.""" if self._nodes: @@ -398,7 +400,7 @@ class GraphBuilder: *, from_node_id: str | None = None, source_handle: str = "source", - ) -> "GraphBuilder": + ) -> GraphBuilder: """Append a node and connect it from the specified predecessor.""" if not self._nodes: @@ -419,7 +421,7 @@ class GraphBuilder: return self - def connect(self, *, tail: str, head: str, source_handle: str = "source") -> "GraphBuilder": + def connect(self, *, tail: str, head: str, source_handle: str = "source") -> GraphBuilder: """Connect two existing nodes without adding a new node.""" if tail not in self._nodes_by_id: diff --git a/api/core/workflow/graph_engine/graph_engine.py b/api/core/workflow/graph_engine/graph_engine.py index 500ba4487b..9a870d7bf5 100644 --- a/api/core/workflow/graph_engine/graph_engine.py +++ b/api/core/workflow/graph_engine/graph_engine.py @@ -5,6 +5,8 @@ This engine uses a modular architecture with separated packages following Domain-Driven Design principles for improved maintainability and testability. """ +from __future__ import annotations + import contextvars import logging import queue @@ -232,7 +234,7 @@ class GraphEngine: ) -> None: layer.initialize(ReadOnlyGraphRuntimeStateWrapper(self._graph_runtime_state), self._command_channel) - def layer(self, layer: GraphEngineLayer) -> "GraphEngine": + def layer(self, layer: GraphEngineLayer) -> GraphEngine: """Add a layer for extending functionality.""" self._layers.append(layer) self._bind_layer_context(layer) diff --git a/api/core/workflow/graph_engine/ready_queue/factory.py b/api/core/workflow/graph_engine/ready_queue/factory.py index 1144e1de69..a9d4f470e5 100644 --- a/api/core/workflow/graph_engine/ready_queue/factory.py +++ b/api/core/workflow/graph_engine/ready_queue/factory.py @@ -2,6 +2,8 @@ Factory for creating ReadyQueue instances from serialized state. """ +from __future__ import annotations + from typing import TYPE_CHECKING from .in_memory import InMemoryReadyQueue @@ -11,7 +13,7 @@ if TYPE_CHECKING: from .protocol import ReadyQueue -def create_ready_queue_from_state(state: ReadyQueueState) -> "ReadyQueue": +def create_ready_queue_from_state(state: ReadyQueueState) -> ReadyQueue: """ Create a ReadyQueue instance from a serialized state. diff --git a/api/core/workflow/graph_engine/response_coordinator/session.py b/api/core/workflow/graph_engine/response_coordinator/session.py index 8b7c2e441e..8ceaa428c3 100644 --- a/api/core/workflow/graph_engine/response_coordinator/session.py +++ b/api/core/workflow/graph_engine/response_coordinator/session.py @@ -5,6 +5,8 @@ This module contains the private ResponseSession class used internally by ResponseStreamCoordinator to manage streaming sessions. """ +from __future__ import annotations + from dataclasses import dataclass from core.workflow.nodes.answer.answer_node import AnswerNode @@ -27,7 +29,7 @@ class ResponseSession: index: int = 0 # Current position in the template segments @classmethod - def from_node(cls, node: Node) -> "ResponseSession": + def from_node(cls, node: Node) -> ResponseSession: """ Create a ResponseSession from an AnswerNode or EndNode. diff --git a/api/core/workflow/nodes/agent/agent_node.py b/api/core/workflow/nodes/agent/agent_node.py index 4be006de11..234651ce96 100644 --- a/api/core/workflow/nodes/agent/agent_node.py +++ b/api/core/workflow/nodes/agent/agent_node.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import json from collections.abc import Generator, Mapping, Sequence from typing import TYPE_CHECKING, Any, cast @@ -167,7 +169,7 @@ class AgentNode(Node[AgentNodeData]): variable_pool: VariablePool, node_data: AgentNodeData, for_log: bool = False, - strategy: "PluginAgentStrategy", + strategy: PluginAgentStrategy, ) -> dict[str, Any]: """ Generate parameters based on the given tool parameters, variable pool, and node data. @@ -328,7 +330,7 @@ class AgentNode(Node[AgentNodeData]): def _generate_credentials( self, parameters: dict[str, Any], - ) -> "InvokeCredentials": + ) -> InvokeCredentials: """ Generate credentials based on the given agent parameters. """ @@ -442,9 +444,7 @@ class AgentNode(Node[AgentNodeData]): model_schema.features.remove(feature) return model_schema - def _filter_mcp_type_tool( - self, strategy: "PluginAgentStrategy", tools: list[dict[str, Any]] - ) -> list[dict[str, Any]]: + def _filter_mcp_type_tool(self, strategy: PluginAgentStrategy, tools: list[dict[str, Any]]) -> list[dict[str, Any]]: """ Filter MCP type tool :param strategy: plugin agent strategy diff --git a/api/core/workflow/nodes/base/entities.py b/api/core/workflow/nodes/base/entities.py index 5aab6bbde4..e5a20c8e91 100644 --- a/api/core/workflow/nodes/base/entities.py +++ b/api/core/workflow/nodes/base/entities.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import json from abc import ABC from builtins import type as type_ @@ -111,7 +113,7 @@ class DefaultValue(BaseModel): raise DefaultValueTypeError(f"Cannot convert to number: {value}") @model_validator(mode="after") - def validate_value_type(self) -> "DefaultValue": + def validate_value_type(self) -> DefaultValue: # Type validation configuration type_validators = { DefaultValueType.STRING: { diff --git a/api/core/workflow/nodes/base/node.py b/api/core/workflow/nodes/base/node.py index e7282313b6..55c8db40ea 100644 --- a/api/core/workflow/nodes/base/node.py +++ b/api/core/workflow/nodes/base/node.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import importlib import logging import operator @@ -59,7 +61,7 @@ logger = logging.getLogger(__name__) class Node(Generic[NodeDataT]): - node_type: ClassVar["NodeType"] + node_type: ClassVar[NodeType] execution_type: NodeExecutionType = NodeExecutionType.EXECUTABLE _node_data_type: ClassVar[type[BaseNodeData]] = BaseNodeData @@ -198,14 +200,14 @@ class Node(Generic[NodeDataT]): return None # Global registry populated via __init_subclass__ - _registry: ClassVar[dict["NodeType", dict[str, type["Node"]]]] = {} + _registry: ClassVar[dict[NodeType, dict[str, type[Node]]]] = {} def __init__( self, id: str, config: Mapping[str, Any], - graph_init_params: "GraphInitParams", - graph_runtime_state: "GraphRuntimeState", + graph_init_params: GraphInitParams, + graph_runtime_state: GraphRuntimeState, ) -> None: self._graph_init_params = graph_init_params self.id = id @@ -241,7 +243,7 @@ class Node(Generic[NodeDataT]): return @property - def graph_init_params(self) -> "GraphInitParams": + def graph_init_params(self) -> GraphInitParams: return self._graph_init_params @property @@ -457,7 +459,7 @@ class Node(Generic[NodeDataT]): raise NotImplementedError("subclasses of BaseNode must implement `version` method.") @classmethod - def get_node_type_classes_mapping(cls) -> Mapping["NodeType", Mapping[str, type["Node"]]]: + def get_node_type_classes_mapping(cls) -> Mapping[NodeType, Mapping[str, type[Node]]]: """Return mapping of NodeType -> {version -> Node subclass} using __init_subclass__ registry. Import all modules under core.workflow.nodes so subclasses register themselves on import. diff --git a/api/core/workflow/nodes/base/template.py b/api/core/workflow/nodes/base/template.py index ba3e2058cf..81f4b9f6fb 100644 --- a/api/core/workflow/nodes/base/template.py +++ b/api/core/workflow/nodes/base/template.py @@ -4,6 +4,8 @@ This module provides a unified template structure for both Answer and End nodes, similar to SegmentGroup but focused on template representation without values. """ +from __future__ import annotations + from abc import ABC, abstractmethod from collections.abc import Sequence from dataclasses import dataclass @@ -58,7 +60,7 @@ class Template: segments: list[TemplateSegmentUnion] @classmethod - def from_answer_template(cls, template_str: str) -> "Template": + def from_answer_template(cls, template_str: str) -> Template: """Create a Template from an Answer node template string. Example: @@ -107,7 +109,7 @@ class Template: return cls(segments=segments) @classmethod - def from_end_outputs(cls, outputs_config: list[dict[str, Any]]) -> "Template": + def from_end_outputs(cls, outputs_config: list[dict[str, Any]]) -> Template: """Create a Template from an End node outputs configuration. End nodes are treated as templates of concatenated variables with newlines. diff --git a/api/core/workflow/nodes/llm/node.py b/api/core/workflow/nodes/llm/node.py index 04e2802191..dfb55dcd80 100644 --- a/api/core/workflow/nodes/llm/node.py +++ b/api/core/workflow/nodes/llm/node.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import base64 import io import json @@ -113,7 +115,7 @@ class LLMNode(Node[LLMNodeData]): # Instance attributes specific to LLMNode. # Output variable for file - _file_outputs: list["File"] + _file_outputs: list[File] _llm_file_saver: LLMFileSaver @@ -121,8 +123,8 @@ class LLMNode(Node[LLMNodeData]): self, id: str, config: Mapping[str, Any], - graph_init_params: "GraphInitParams", - graph_runtime_state: "GraphRuntimeState", + graph_init_params: GraphInitParams, + graph_runtime_state: GraphRuntimeState, *, llm_file_saver: LLMFileSaver | None = None, ): @@ -361,7 +363,7 @@ class LLMNode(Node[LLMNodeData]): structured_output_enabled: bool, structured_output: Mapping[str, Any] | None = None, file_saver: LLMFileSaver, - file_outputs: list["File"], + file_outputs: list[File], node_id: str, node_type: NodeType, reasoning_format: Literal["separated", "tagged"] = "tagged", @@ -415,7 +417,7 @@ class LLMNode(Node[LLMNodeData]): *, invoke_result: LLMResult | Generator[LLMResultChunk | LLMStructuredOutput, None, None], file_saver: LLMFileSaver, - file_outputs: list["File"], + file_outputs: list[File], node_id: str, node_type: NodeType, reasoning_format: Literal["separated", "tagged"] = "tagged", @@ -525,7 +527,7 @@ class LLMNode(Node[LLMNodeData]): ) @staticmethod - def _image_file_to_markdown(file: "File", /): + def _image_file_to_markdown(file: File, /): text_chunk = f"![]({file.generate_url()})" return text_chunk @@ -774,7 +776,7 @@ class LLMNode(Node[LLMNodeData]): def fetch_prompt_messages( *, sys_query: str | None = None, - sys_files: Sequence["File"], + sys_files: Sequence[File], context: str | None = None, memory: TokenBufferMemory | None = None, model_config: ModelConfigWithCredentialsEntity, @@ -785,7 +787,7 @@ class LLMNode(Node[LLMNodeData]): variable_pool: VariablePool, jinja2_variables: Sequence[VariableSelector], tenant_id: str, - context_files: list["File"] | None = None, + context_files: list[File] | None = None, ) -> tuple[Sequence[PromptMessage], Sequence[str] | None]: prompt_messages: list[PromptMessage] = [] @@ -1137,7 +1139,7 @@ class LLMNode(Node[LLMNodeData]): *, invoke_result: LLMResult | LLMResultWithStructuredOutput, saver: LLMFileSaver, - file_outputs: list["File"], + file_outputs: list[File], reasoning_format: Literal["separated", "tagged"] = "tagged", request_latency: float | None = None, ) -> ModelInvokeCompletedEvent: @@ -1179,7 +1181,7 @@ class LLMNode(Node[LLMNodeData]): *, content: ImagePromptMessageContent, file_saver: LLMFileSaver, - ) -> "File": + ) -> File: """_save_multimodal_output saves multi-modal contents generated by LLM plugins. There are two kinds of multimodal outputs: @@ -1229,7 +1231,7 @@ class LLMNode(Node[LLMNodeData]): *, contents: str | list[PromptMessageContentUnionTypes] | None, file_saver: LLMFileSaver, - file_outputs: list["File"], + file_outputs: list[File], ) -> Generator[str, None, None]: """Convert intermediate prompt messages into strings and yield them to the caller. diff --git a/api/core/workflow/nodes/node_factory.py b/api/core/workflow/nodes/node_factory.py index f177aef665..557d3a330d 100644 --- a/api/core/workflow/nodes/node_factory.py +++ b/api/core/workflow/nodes/node_factory.py @@ -113,7 +113,6 @@ class DifyNodeFactory(NodeFactory): code_providers=self._code_providers, code_limits=self._code_limits, ) - if node_type == NodeType.TEMPLATE_TRANSFORM: return TemplateTransformNode( id=node_id, diff --git a/api/core/workflow/nodes/variable_assigner/common/impl.py b/api/core/workflow/nodes/variable_assigner/common/impl.py deleted file mode 100644 index 050e213535..0000000000 --- a/api/core/workflow/nodes/variable_assigner/common/impl.py +++ /dev/null @@ -1,28 +0,0 @@ -from sqlalchemy import select -from sqlalchemy.orm import Session - -from core.variables.variables import Variable -from extensions.ext_database import db -from models import ConversationVariable - -from .exc import VariableOperatorNodeError - - -class ConversationVariableUpdaterImpl: - def update(self, conversation_id: str, variable: Variable): - stmt = select(ConversationVariable).where( - ConversationVariable.id == variable.id, ConversationVariable.conversation_id == conversation_id - ) - with Session(db.engine) as session: - row = session.scalar(stmt) - if not row: - raise VariableOperatorNodeError("conversation variable not found in the database") - row.data = variable.model_dump_json() - session.commit() - - def flush(self): - pass - - -def conversation_variable_updater_factory() -> ConversationVariableUpdaterImpl: - return ConversationVariableUpdaterImpl() diff --git a/api/core/workflow/nodes/variable_assigner/v1/node.py b/api/core/workflow/nodes/variable_assigner/v1/node.py index da23207b62..d2ea7d94ea 100644 --- a/api/core/workflow/nodes/variable_assigner/v1/node.py +++ b/api/core/workflow/nodes/variable_assigner/v1/node.py @@ -1,9 +1,8 @@ -from collections.abc import Callable, Mapping, Sequence -from typing import TYPE_CHECKING, Any, TypeAlias +from collections.abc import Mapping, Sequence +from typing import TYPE_CHECKING, Any from core.variables import SegmentType, Variable from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID -from core.workflow.conversation_variable_updater import ConversationVariableUpdater from core.workflow.entities import GraphInitParams from core.workflow.enums import NodeType, WorkflowNodeExecutionStatus from core.workflow.node_events import NodeRunResult @@ -11,19 +10,14 @@ from core.workflow.nodes.base.node import Node from core.workflow.nodes.variable_assigner.common import helpers as common_helpers from core.workflow.nodes.variable_assigner.common.exc import VariableOperatorNodeError -from ..common.impl import conversation_variable_updater_factory from .node_data import VariableAssignerData, WriteMode if TYPE_CHECKING: from core.workflow.runtime import GraphRuntimeState -_CONV_VAR_UPDATER_FACTORY: TypeAlias = Callable[[], ConversationVariableUpdater] - - class VariableAssignerNode(Node[VariableAssignerData]): node_type = NodeType.VARIABLE_ASSIGNER - _conv_var_updater_factory: _CONV_VAR_UPDATER_FACTORY def __init__( self, @@ -31,7 +25,6 @@ class VariableAssignerNode(Node[VariableAssignerData]): config: Mapping[str, Any], graph_init_params: "GraphInitParams", graph_runtime_state: "GraphRuntimeState", - conv_var_updater_factory: _CONV_VAR_UPDATER_FACTORY = conversation_variable_updater_factory, ): super().__init__( id=id, @@ -39,7 +32,6 @@ class VariableAssignerNode(Node[VariableAssignerData]): graph_init_params=graph_init_params, graph_runtime_state=graph_runtime_state, ) - self._conv_var_updater_factory = conv_var_updater_factory @classmethod def version(cls) -> str: @@ -96,16 +88,7 @@ class VariableAssignerNode(Node[VariableAssignerData]): # Over write the variable. self.graph_runtime_state.variable_pool.add(assigned_variable_selector, updated_variable) - # TODO: Move database operation to the pipeline. - # Update conversation variable. - conversation_id = self.graph_runtime_state.variable_pool.get(["sys", "conversation_id"]) - if not conversation_id: - raise VariableOperatorNodeError("conversation_id not found") - conv_var_updater = self._conv_var_updater_factory() - conv_var_updater.update(conversation_id=conversation_id.text, variable=updated_variable) - conv_var_updater.flush() updated_variables = [common_helpers.variable_to_processed_data(assigned_variable_selector, updated_variable)] - return NodeRunResult( status=WorkflowNodeExecutionStatus.SUCCEEDED, inputs={ diff --git a/api/core/workflow/nodes/variable_assigner/v2/node.py b/api/core/workflow/nodes/variable_assigner/v2/node.py index 389fb54d35..486e6bb6a7 100644 --- a/api/core/workflow/nodes/variable_assigner/v2/node.py +++ b/api/core/workflow/nodes/variable_assigner/v2/node.py @@ -1,24 +1,20 @@ import json from collections.abc import Mapping, MutableMapping, Sequence -from typing import Any, cast +from typing import TYPE_CHECKING, Any -from core.app.entities.app_invoke_entities import InvokeFrom from core.variables import SegmentType, Variable from core.variables.consts import SELECTORS_LENGTH from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID -from core.workflow.conversation_variable_updater import ConversationVariableUpdater from core.workflow.enums import NodeType, WorkflowNodeExecutionStatus from core.workflow.node_events import NodeRunResult from core.workflow.nodes.base.node import Node from core.workflow.nodes.variable_assigner.common import helpers as common_helpers from core.workflow.nodes.variable_assigner.common.exc import VariableOperatorNodeError -from core.workflow.nodes.variable_assigner.common.impl import conversation_variable_updater_factory from . import helpers from .entities import VariableAssignerNodeData, VariableOperationItem from .enums import InputType, Operation from .exc import ( - ConversationIDNotFoundError, InputTypeNotSupportedError, InvalidDataError, InvalidInputValueError, @@ -26,6 +22,10 @@ from .exc import ( VariableNotFoundError, ) +if TYPE_CHECKING: + from core.workflow.entities import GraphInitParams + from core.workflow.runtime import GraphRuntimeState + def _target_mapping_from_item(mapping: MutableMapping[str, Sequence[str]], node_id: str, item: VariableOperationItem): selector_node_id = item.variable_selector[0] @@ -53,6 +53,20 @@ def _source_mapping_from_item(mapping: MutableMapping[str, Sequence[str]], node_ class VariableAssignerNode(Node[VariableAssignerNodeData]): node_type = NodeType.VARIABLE_ASSIGNER + def __init__( + self, + id: str, + config: Mapping[str, Any], + graph_init_params: "GraphInitParams", + graph_runtime_state: "GraphRuntimeState", + ): + super().__init__( + id=id, + config=config, + graph_init_params=graph_init_params, + graph_runtime_state=graph_runtime_state, + ) + def blocks_variable_output(self, variable_selectors: set[tuple[str, ...]]) -> bool: """ Check if this Variable Assigner node blocks the output of specific variables. @@ -70,9 +84,6 @@ class VariableAssignerNode(Node[VariableAssignerNodeData]): return False - def _conv_var_updater_factory(self) -> ConversationVariableUpdater: - return conversation_variable_updater_factory() - @classmethod def version(cls) -> str: return "2" @@ -179,26 +190,12 @@ class VariableAssignerNode(Node[VariableAssignerNodeData]): # remove the duplicated items first. updated_variable_selectors = list(set(map(tuple, updated_variable_selectors))) - conv_var_updater = self._conv_var_updater_factory() - # Update variables for selector in updated_variable_selectors: variable = self.graph_runtime_state.variable_pool.get(selector) if not isinstance(variable, Variable): raise VariableNotFoundError(variable_selector=selector) process_data[variable.name] = variable.value - if variable.selector[0] == CONVERSATION_VARIABLE_NODE_ID: - conversation_id = self.graph_runtime_state.variable_pool.get(["sys", "conversation_id"]) - if not conversation_id: - if self.invoke_from != InvokeFrom.DEBUGGER: - raise ConversationIDNotFoundError - else: - conversation_id = conversation_id.value - conv_var_updater.update( - conversation_id=cast(str, conversation_id), - variable=variable, - ) - conv_var_updater.flush() updated_variables = [ common_helpers.variable_to_processed_data(selector, seg) for selector in updated_variable_selectors diff --git a/api/core/workflow/repositories/draft_variable_repository.py b/api/core/workflow/repositories/draft_variable_repository.py index 97bfcd5666..66ef714c16 100644 --- a/api/core/workflow/repositories/draft_variable_repository.py +++ b/api/core/workflow/repositories/draft_variable_repository.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import abc from collections.abc import Mapping from typing import Any, Protocol @@ -23,7 +25,7 @@ class DraftVariableSaverFactory(Protocol): node_type: NodeType, node_execution_id: str, enclosing_node_id: str | None = None, - ) -> "DraftVariableSaver": + ) -> DraftVariableSaver: pass diff --git a/api/core/workflow/runtime/graph_runtime_state_protocol.py b/api/core/workflow/runtime/graph_runtime_state_protocol.py index 5e0878e873..bfbb5ba704 100644 --- a/api/core/workflow/runtime/graph_runtime_state_protocol.py +++ b/api/core/workflow/runtime/graph_runtime_state_protocol.py @@ -1,4 +1,4 @@ -from collections.abc import Mapping +from collections.abc import Mapping, Sequence from typing import Any, Protocol from core.model_runtime.entities.llm_entities import LLMUsage @@ -9,7 +9,7 @@ from core.workflow.system_variable import SystemVariableReadOnlyView class ReadOnlyVariablePool(Protocol): """Read-only interface for VariablePool.""" - def get(self, node_id: str, variable_key: str) -> Segment | None: + def get(self, selector: Sequence[str], /) -> Segment | None: """Get a variable value (read-only).""" ... diff --git a/api/core/workflow/runtime/read_only_wrappers.py b/api/core/workflow/runtime/read_only_wrappers.py index 8539727fd6..d3e4c60d9b 100644 --- a/api/core/workflow/runtime/read_only_wrappers.py +++ b/api/core/workflow/runtime/read_only_wrappers.py @@ -1,6 +1,6 @@ from __future__ import annotations -from collections.abc import Mapping +from collections.abc import Mapping, Sequence from copy import deepcopy from typing import Any @@ -18,9 +18,9 @@ class ReadOnlyVariablePoolWrapper: def __init__(self, variable_pool: VariablePool) -> None: self._variable_pool = variable_pool - def get(self, node_id: str, variable_key: str) -> Segment | None: + def get(self, selector: Sequence[str], /) -> Segment | None: """Return a copy of a variable value if present.""" - value = self._variable_pool.get([node_id, variable_key]) + value = self._variable_pool.get(selector) return deepcopy(value) if value is not None else None def get_all_by_node(self, node_id: str) -> Mapping[str, object]: diff --git a/api/core/workflow/runtime/variable_pool.py b/api/core/workflow/runtime/variable_pool.py index 7fbaec9e70..85ceb9d59e 100644 --- a/api/core/workflow/runtime/variable_pool.py +++ b/api/core/workflow/runtime/variable_pool.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import re from collections import defaultdict from collections.abc import Mapping, Sequence @@ -267,6 +269,6 @@ class VariablePool(BaseModel): self.add(selector, value) @classmethod - def empty(cls) -> "VariablePool": + def empty(cls) -> VariablePool: """Create an empty variable pool.""" return cls(system_variables=SystemVariable.empty()) diff --git a/api/core/workflow/system_variable.py b/api/core/workflow/system_variable.py index ad925912a4..cda8091771 100644 --- a/api/core/workflow/system_variable.py +++ b/api/core/workflow/system_variable.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from collections.abc import Mapping, Sequence from types import MappingProxyType from typing import Any @@ -70,7 +72,7 @@ class SystemVariable(BaseModel): return data @classmethod - def empty(cls) -> "SystemVariable": + def empty(cls) -> SystemVariable: return cls() def to_dict(self) -> dict[SystemVariableKey, Any]: @@ -114,7 +116,7 @@ class SystemVariable(BaseModel): d[SystemVariableKey.TIMESTAMP] = self.timestamp return d - def as_view(self) -> "SystemVariableReadOnlyView": + def as_view(self) -> SystemVariableReadOnlyView: return SystemVariableReadOnlyView(self) diff --git a/api/docker/entrypoint.sh b/api/docker/entrypoint.sh index 5a69eb15ac..c0279f893b 100755 --- a/api/docker/entrypoint.sh +++ b/api/docker/entrypoint.sh @@ -3,8 +3,9 @@ set -e # Set UTF-8 encoding to address potential encoding issues in containerized environments -export LANG=${LANG:-en_US.UTF-8} -export LC_ALL=${LC_ALL:-en_US.UTF-8} +# Use C.UTF-8 which is universally available in all containers +export LANG=${LANG:-C.UTF-8} +export LC_ALL=${LC_ALL:-C.UTF-8} export PYTHONIOENCODING=${PYTHONIOENCODING:-utf-8} if [[ "${MIGRATION_ENABLED}" == "true" ]]; then diff --git a/api/extensions/ext_blueprints.py b/api/extensions/ext_blueprints.py index cf994c11df..7d13f0c061 100644 --- a/api/extensions/ext_blueprints.py +++ b/api/extensions/ext_blueprints.py @@ -6,6 +6,7 @@ BASE_CORS_HEADERS: tuple[str, ...] = ("Content-Type", HEADER_NAME_APP_CODE, HEAD SERVICE_API_HEADERS: tuple[str, ...] = (*BASE_CORS_HEADERS, "Authorization") AUTHENTICATED_HEADERS: tuple[str, ...] = (*SERVICE_API_HEADERS, HEADER_NAME_CSRF_TOKEN) FILES_HEADERS: tuple[str, ...] = (*BASE_CORS_HEADERS, HEADER_NAME_CSRF_TOKEN) +EMBED_HEADERS: tuple[str, ...] = ("Content-Type", HEADER_NAME_APP_CODE) EXPOSED_HEADERS: tuple[str, ...] = ("X-Version", "X-Env", "X-Trace-Id") @@ -42,10 +43,28 @@ def init_app(app: DifyApp): _apply_cors_once( web_bp, - resources={r"/*": {"origins": dify_config.WEB_API_CORS_ALLOW_ORIGINS}}, - supports_credentials=True, - allow_headers=list(AUTHENTICATED_HEADERS), - methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"], + resources={ + # Embedded bot endpoints (unauthenticated, cross-origin safe) + r"^/chat-messages$": { + "origins": dify_config.WEB_API_CORS_ALLOW_ORIGINS, + "supports_credentials": False, + "allow_headers": list(EMBED_HEADERS), + "methods": ["GET", "POST", "OPTIONS"], + }, + r"^/chat-messages/.*": { + "origins": dify_config.WEB_API_CORS_ALLOW_ORIGINS, + "supports_credentials": False, + "allow_headers": list(EMBED_HEADERS), + "methods": ["GET", "POST", "OPTIONS"], + }, + # Default web application endpoints (authenticated) + r"/*": { + "origins": dify_config.WEB_API_CORS_ALLOW_ORIGINS, + "supports_credentials": True, + "allow_headers": list(AUTHENTICATED_HEADERS), + "methods": ["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"], + }, + }, expose_headers=list(EXPOSED_HEADERS), ) app.register_blueprint(web_bp) diff --git a/api/extensions/logstore/aliyun_logstore.py b/api/extensions/logstore/aliyun_logstore.py index 22d1f473a3..8c64a25be4 100644 --- a/api/extensions/logstore/aliyun_logstore.py +++ b/api/extensions/logstore/aliyun_logstore.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import logging import os import threading @@ -33,7 +35,7 @@ class AliyunLogStore: Ensures only one instance exists to prevent multiple PG connection pools. """ - _instance: "AliyunLogStore | None" = None + _instance: AliyunLogStore | None = None _initialized: bool = False # Track delayed PG connection for newly created projects @@ -66,7 +68,7 @@ class AliyunLogStore: "\t", ] - def __new__(cls) -> "AliyunLogStore": + def __new__(cls) -> AliyunLogStore: """Implement singleton pattern.""" if cls._instance is None: cls._instance = super().__new__(cls) diff --git a/api/extensions/storage/clickzetta_volume/file_lifecycle.py b/api/extensions/storage/clickzetta_volume/file_lifecycle.py index 51a97b20f8..1d9911465b 100644 --- a/api/extensions/storage/clickzetta_volume/file_lifecycle.py +++ b/api/extensions/storage/clickzetta_volume/file_lifecycle.py @@ -5,6 +5,8 @@ automatic cleanup, backup and restore. Supports complete lifecycle management for knowledge base files. """ +from __future__ import annotations + import json import logging import operator @@ -48,7 +50,7 @@ class FileMetadata: return data @classmethod - def from_dict(cls, data: dict) -> "FileMetadata": + def from_dict(cls, data: dict) -> FileMetadata: """Create instance from dictionary""" data = data.copy() data["created_at"] = datetime.fromisoformat(data["created_at"]) diff --git a/api/fields/file_fields.py b/api/fields/file_fields.py index 70138404c7..913fb675f9 100644 --- a/api/fields/file_fields.py +++ b/api/fields/file_fields.py @@ -1,93 +1,85 @@ -from flask_restx import Namespace, fields +from __future__ import annotations -from libs.helper import TimestampField +from datetime import datetime -upload_config_fields = { - "file_size_limit": fields.Integer, - "batch_count_limit": fields.Integer, - "image_file_size_limit": fields.Integer, - "video_file_size_limit": fields.Integer, - "audio_file_size_limit": fields.Integer, - "workflow_file_upload_limit": fields.Integer, - "image_file_batch_limit": fields.Integer, - "single_chunk_attachment_limit": fields.Integer, -} +from pydantic import BaseModel, ConfigDict, field_validator -def build_upload_config_model(api_or_ns: Namespace): - """Build the upload config model for the API or Namespace. - - Args: - api_or_ns: Flask-RestX Api or Namespace instance - - Returns: - The registered model - """ - return api_or_ns.model("UploadConfig", upload_config_fields) +class ResponseModel(BaseModel): + model_config = ConfigDict( + from_attributes=True, + extra="ignore", + populate_by_name=True, + serialize_by_alias=True, + protected_namespaces=(), + ) -file_fields = { - "id": fields.String, - "name": fields.String, - "size": fields.Integer, - "extension": fields.String, - "mime_type": fields.String, - "created_by": fields.String, - "created_at": TimestampField, - "preview_url": fields.String, - "source_url": fields.String, -} +def _to_timestamp(value: datetime | int | None) -> int | None: + if isinstance(value, datetime): + return int(value.timestamp()) + return value -def build_file_model(api_or_ns: Namespace): - """Build the file model for the API or Namespace. - - Args: - api_or_ns: Flask-RestX Api or Namespace instance - - Returns: - The registered model - """ - return api_or_ns.model("File", file_fields) +class UploadConfig(ResponseModel): + file_size_limit: int + batch_count_limit: int + file_upload_limit: int | None = None + image_file_size_limit: int + video_file_size_limit: int + audio_file_size_limit: int + workflow_file_upload_limit: int + image_file_batch_limit: int + single_chunk_attachment_limit: int + attachment_image_file_size_limit: int | None = None -remote_file_info_fields = { - "file_type": fields.String(attribute="file_type"), - "file_length": fields.Integer(attribute="file_length"), -} +class FileResponse(ResponseModel): + id: str + name: str + size: int + extension: str | None = None + mime_type: str | None = None + created_by: str | None = None + created_at: int | None = None + preview_url: str | None = None + source_url: str | None = None + original_url: str | None = None + user_id: str | None = None + tenant_id: str | None = None + conversation_id: str | None = None + file_key: str | None = None + + @field_validator("created_at", mode="before") + @classmethod + def _normalize_created_at(cls, value: datetime | int | None) -> int | None: + return _to_timestamp(value) -def build_remote_file_info_model(api_or_ns: Namespace): - """Build the remote file info model for the API or Namespace. - - Args: - api_or_ns: Flask-RestX Api or Namespace instance - - Returns: - The registered model - """ - return api_or_ns.model("RemoteFileInfo", remote_file_info_fields) +class RemoteFileInfo(ResponseModel): + file_type: str + file_length: int -file_fields_with_signed_url = { - "id": fields.String, - "name": fields.String, - "size": fields.Integer, - "extension": fields.String, - "url": fields.String, - "mime_type": fields.String, - "created_by": fields.String, - "created_at": TimestampField, -} +class FileWithSignedUrl(ResponseModel): + id: str + name: str + size: int + extension: str | None = None + url: str | None = None + mime_type: str | None = None + created_by: str | None = None + created_at: int | None = None + + @field_validator("created_at", mode="before") + @classmethod + def _normalize_created_at(cls, value: datetime | int | None) -> int | None: + return _to_timestamp(value) -def build_file_with_signed_url_model(api_or_ns: Namespace): - """Build the file with signed URL model for the API or Namespace. - - Args: - api_or_ns: Flask-RestX Api or Namespace instance - - Returns: - The registered model - """ - return api_or_ns.model("FileWithSignedUrl", file_fields_with_signed_url) +__all__ = [ + "FileResponse", + "FileWithSignedUrl", + "RemoteFileInfo", + "UploadConfig", +] diff --git a/api/libs/broadcast_channel/channel.py b/api/libs/broadcast_channel/channel.py index 5bbf0c79a3..d4cb3e9971 100644 --- a/api/libs/broadcast_channel/channel.py +++ b/api/libs/broadcast_channel/channel.py @@ -2,6 +2,8 @@ Broadcast channel for Pub/Sub messaging. """ +from __future__ import annotations + import types from abc import abstractmethod from collections.abc import Iterator @@ -129,6 +131,6 @@ class BroadcastChannel(Protocol): """ @abstractmethod - def topic(self, topic: str) -> "Topic": + def topic(self, topic: str) -> Topic: """topic returns a `Topic` instance for the given topic name.""" ... diff --git a/api/libs/broadcast_channel/redis/channel.py b/api/libs/broadcast_channel/redis/channel.py index 1fc3db8156..5bb4f579c1 100644 --- a/api/libs/broadcast_channel/redis/channel.py +++ b/api/libs/broadcast_channel/redis/channel.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from libs.broadcast_channel.channel import Producer, Subscriber, Subscription from redis import Redis @@ -20,7 +22,7 @@ class BroadcastChannel: ): self._client = redis_client - def topic(self, topic: str) -> "Topic": + def topic(self, topic: str) -> Topic: return Topic(self._client, topic) diff --git a/api/libs/broadcast_channel/redis/sharded_channel.py b/api/libs/broadcast_channel/redis/sharded_channel.py index 16e3a80ee1..d190c51bbc 100644 --- a/api/libs/broadcast_channel/redis/sharded_channel.py +++ b/api/libs/broadcast_channel/redis/sharded_channel.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from libs.broadcast_channel.channel import Producer, Subscriber, Subscription from redis import Redis @@ -18,7 +20,7 @@ class ShardedRedisBroadcastChannel: ): self._client = redis_client - def topic(self, topic: str) -> "ShardedTopic": + def topic(self, topic: str) -> ShardedTopic: return ShardedTopic(self._client, topic) diff --git a/api/libs/email_i18n.py b/api/libs/email_i18n.py index ff74ccbe8e..0828cf80bf 100644 --- a/api/libs/email_i18n.py +++ b/api/libs/email_i18n.py @@ -6,6 +6,8 @@ in Dify. It follows Domain-Driven Design principles with proper type hints and eliminates the need for repetitive language switching logic. """ +from __future__ import annotations + from dataclasses import dataclass from enum import StrEnum, auto from typing import Any, Protocol @@ -53,7 +55,7 @@ class EmailLanguage(StrEnum): ZH_HANS = "zh-Hans" @classmethod - def from_language_code(cls, language_code: str) -> "EmailLanguage": + def from_language_code(cls, language_code: str) -> EmailLanguage: """Convert a language code to EmailLanguage with fallback to English.""" if language_code == "zh-Hans": return cls.ZH_HANS diff --git a/api/models/model.py b/api/models/model.py index b6f2751a72..46df047237 100644 --- a/api/models/model.py +++ b/api/models/model.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import json import re import uuid @@ -5,7 +7,7 @@ from collections.abc import Mapping from datetime import datetime from decimal import Decimal from enum import StrEnum, auto -from typing import TYPE_CHECKING, Any, Literal, Optional, cast +from typing import TYPE_CHECKING, Any, Literal, cast from uuid import uuid4 import sqlalchemy as sa @@ -54,7 +56,7 @@ class AppMode(StrEnum): RAG_PIPELINE = "rag-pipeline" @classmethod - def value_of(cls, value: str) -> "AppMode": + def value_of(cls, value: str) -> AppMode: """ Get value of given mode. @@ -121,19 +123,19 @@ class App(Base): return "" @property - def site(self) -> Optional["Site"]: + def site(self) -> Site | None: site = db.session.query(Site).where(Site.app_id == self.id).first() return site @property - def app_model_config(self) -> Optional["AppModelConfig"]: + def app_model_config(self) -> AppModelConfig | None: if self.app_model_config_id: return db.session.query(AppModelConfig).where(AppModelConfig.id == self.app_model_config_id).first() return None @property - def workflow(self) -> Optional["Workflow"]: + def workflow(self) -> Workflow | None: if self.workflow_id: from .workflow import Workflow @@ -288,7 +290,7 @@ class App(Base): return deleted_tools @property - def tags(self) -> list["Tag"]: + def tags(self) -> list[Tag]: tags = ( db.session.query(Tag) .join(TagBinding, Tag.id == TagBinding.tag_id) @@ -1194,7 +1196,7 @@ class Message(Base): return json.loads(self.message_metadata) if self.message_metadata else {} @property - def agent_thoughts(self) -> list["MessageAgentThought"]: + def agent_thoughts(self) -> list[MessageAgentThought]: return ( db.session.query(MessageAgentThought) .where(MessageAgentThought.message_id == self.id) @@ -1307,7 +1309,7 @@ class Message(Base): } @classmethod - def from_dict(cls, data: dict[str, Any]) -> "Message": + def from_dict(cls, data: dict[str, Any]) -> Message: return cls( id=data["id"], app_id=data["app_id"], @@ -1534,7 +1536,7 @@ class OperationLog(TypeBase): tenant_id: Mapped[str] = mapped_column(StringUUID, nullable=False) account_id: Mapped[str] = mapped_column(StringUUID, nullable=False) action: Mapped[str] = mapped_column(String(255), nullable=False) - content: Mapped[Any] = mapped_column(sa.JSON) + content: Mapped[Any | None] = mapped_column(sa.JSON, nullable=True) created_at: Mapped[datetime] = mapped_column( sa.DateTime, nullable=False, server_default=func.current_timestamp(), init=False ) diff --git a/api/models/provider.py b/api/models/provider.py index 2afd8c5329..441b54c797 100644 --- a/api/models/provider.py +++ b/api/models/provider.py @@ -1,3 +1,5 @@ +from __future__ import annotations + from datetime import datetime from enum import StrEnum, auto from functools import cached_property @@ -19,7 +21,7 @@ class ProviderType(StrEnum): SYSTEM = auto() @staticmethod - def value_of(value: str) -> "ProviderType": + def value_of(value: str) -> ProviderType: for member in ProviderType: if member.value == value: return member @@ -37,7 +39,7 @@ class ProviderQuotaType(StrEnum): """hosted trial quota""" @staticmethod - def value_of(value: str) -> "ProviderQuotaType": + def value_of(value: str) -> ProviderQuotaType: for member in ProviderQuotaType: if member.value == value: return member @@ -76,7 +78,7 @@ class Provider(TypeBase): quota_type: Mapped[str | None] = mapped_column(String(40), nullable=True, server_default=text("''"), default="") quota_limit: Mapped[int | None] = mapped_column(sa.BigInteger, nullable=True, default=None) - quota_used: Mapped[int] = mapped_column(sa.BigInteger, nullable=False, default=0) + quota_used: Mapped[int | None] = mapped_column(sa.BigInteger, nullable=True, default=0) created_at: Mapped[datetime] = mapped_column( DateTime, nullable=False, server_default=func.current_timestamp(), init=False diff --git a/api/models/tools.py b/api/models/tools.py index e4f9bcb582..e7b98dcf27 100644 --- a/api/models/tools.py +++ b/api/models/tools.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import json from datetime import datetime from decimal import Decimal @@ -167,11 +169,11 @@ class ApiToolProvider(TypeBase): ) @property - def schema_type(self) -> "ApiProviderSchemaType": + def schema_type(self) -> ApiProviderSchemaType: return ApiProviderSchemaType.value_of(self.schema_type_str) @property - def tools(self) -> list["ApiToolBundle"]: + def tools(self) -> list[ApiToolBundle]: return [ApiToolBundle.model_validate(tool) for tool in json.loads(self.tools_str)] @property @@ -267,7 +269,7 @@ class WorkflowToolProvider(TypeBase): return db.session.query(Tenant).where(Tenant.id == self.tenant_id).first() @property - def parameter_configurations(self) -> list["WorkflowToolParameterConfiguration"]: + def parameter_configurations(self) -> list[WorkflowToolParameterConfiguration]: return [ WorkflowToolParameterConfiguration.model_validate(config) for config in json.loads(self.parameter_configuration) @@ -359,7 +361,7 @@ class MCPToolProvider(TypeBase): except (json.JSONDecodeError, TypeError): return [] - def to_entity(self) -> "MCPProviderEntity": + def to_entity(self) -> MCPProviderEntity: """Convert to domain entity""" from core.entities.mcp_provider import MCPProviderEntity @@ -533,5 +535,5 @@ class DeprecatedPublishedAppTool(TypeBase): ) @property - def description_i18n(self) -> "I18nObject": + def description_i18n(self) -> I18nObject: return I18nObject.model_validate(json.loads(self.description)) diff --git a/api/models/trigger.py b/api/models/trigger.py index 87e2a5ccfc..209345eb84 100644 --- a/api/models/trigger.py +++ b/api/models/trigger.py @@ -415,7 +415,7 @@ class AppTrigger(TypeBase): node_id: Mapped[str | None] = mapped_column(String(64), nullable=False) trigger_type: Mapped[str] = mapped_column(EnumText(AppTriggerType, length=50), nullable=False) title: Mapped[str] = mapped_column(String(255), nullable=False) - provider_name: Mapped[str] = mapped_column(String(255), server_default="", default="") # why it is nullable? + provider_name: Mapped[str | None] = mapped_column(String(255), nullable=True, server_default="", default="") status: Mapped[str] = mapped_column( EnumText(AppTriggerStatus, length=50), nullable=False, default=AppTriggerStatus.ENABLED ) diff --git a/api/models/workflow.py b/api/models/workflow.py index 853d5afefc..a18939523b 100644 --- a/api/models/workflow.py +++ b/api/models/workflow.py @@ -1,9 +1,11 @@ +from __future__ import annotations + import json import logging from collections.abc import Generator, Mapping, Sequence from datetime import datetime from enum import StrEnum -from typing import TYPE_CHECKING, Any, Optional, Union, cast +from typing import TYPE_CHECKING, Any, Union, cast from uuid import uuid4 import sqlalchemy as sa @@ -67,7 +69,7 @@ class WorkflowType(StrEnum): RAG_PIPELINE = "rag-pipeline" @classmethod - def value_of(cls, value: str) -> "WorkflowType": + def value_of(cls, value: str) -> WorkflowType: """ Get value of given mode. @@ -80,7 +82,7 @@ class WorkflowType(StrEnum): raise ValueError(f"invalid workflow type value {value}") @classmethod - def from_app_mode(cls, app_mode: Union[str, "AppMode"]) -> "WorkflowType": + def from_app_mode(cls, app_mode: Union[str, AppMode]) -> WorkflowType: """ Get workflow type from app mode. @@ -181,7 +183,7 @@ class Workflow(Base): # bug rag_pipeline_variables: list[dict], marked_name: str = "", marked_comment: str = "", - ) -> "Workflow": + ) -> Workflow: workflow = Workflow() workflow.id = str(uuid4()) workflow.tenant_id = tenant_id @@ -619,7 +621,7 @@ class WorkflowRun(Base): finished_at: Mapped[datetime | None] = mapped_column(DateTime) exceptions_count: Mapped[int] = mapped_column(sa.Integer, server_default=sa.text("0"), nullable=True) - pause: Mapped[Optional["WorkflowPause"]] = orm.relationship( + pause: Mapped[WorkflowPause | None] = orm.relationship( "WorkflowPause", primaryjoin="WorkflowRun.id == foreign(WorkflowPause.workflow_run_id)", uselist=False, @@ -689,7 +691,7 @@ class WorkflowRun(Base): } @classmethod - def from_dict(cls, data: dict[str, Any]) -> "WorkflowRun": + def from_dict(cls, data: dict[str, Any]) -> WorkflowRun: return cls( id=data.get("id"), tenant_id=data.get("tenant_id"), @@ -841,7 +843,7 @@ class WorkflowNodeExecutionModel(Base): # This model is expected to have `offlo created_by: Mapped[str] = mapped_column(StringUUID) finished_at: Mapped[datetime | None] = mapped_column(DateTime) - offload_data: Mapped[list["WorkflowNodeExecutionOffload"]] = orm.relationship( + offload_data: Mapped[list[WorkflowNodeExecutionOffload]] = orm.relationship( "WorkflowNodeExecutionOffload", primaryjoin="WorkflowNodeExecutionModel.id == foreign(WorkflowNodeExecutionOffload.node_execution_id)", uselist=True, @@ -851,13 +853,13 @@ class WorkflowNodeExecutionModel(Base): # This model is expected to have `offlo @staticmethod def preload_offload_data( - query: Select[tuple["WorkflowNodeExecutionModel"]] | orm.Query["WorkflowNodeExecutionModel"], + query: Select[tuple[WorkflowNodeExecutionModel]] | orm.Query[WorkflowNodeExecutionModel], ): return query.options(orm.selectinload(WorkflowNodeExecutionModel.offload_data)) @staticmethod def preload_offload_data_and_files( - query: Select[tuple["WorkflowNodeExecutionModel"]] | orm.Query["WorkflowNodeExecutionModel"], + query: Select[tuple[WorkflowNodeExecutionModel]] | orm.Query[WorkflowNodeExecutionModel], ): return query.options( orm.selectinload(WorkflowNodeExecutionModel.offload_data).options( @@ -932,7 +934,7 @@ class WorkflowNodeExecutionModel(Base): # This model is expected to have `offlo ) return extras - def _get_offload_by_type(self, type_: ExecutionOffLoadType) -> Optional["WorkflowNodeExecutionOffload"]: + def _get_offload_by_type(self, type_: ExecutionOffLoadType) -> WorkflowNodeExecutionOffload | None: return next(iter([i for i in self.offload_data if i.type_ == type_]), None) @property @@ -1046,7 +1048,7 @@ class WorkflowNodeExecutionOffload(Base): back_populates="offload_data", ) - file: Mapped[Optional["UploadFile"]] = orm.relationship( + file: Mapped[UploadFile | None] = orm.relationship( foreign_keys=[file_id], lazy="raise", uselist=False, @@ -1064,7 +1066,7 @@ class WorkflowAppLogCreatedFrom(StrEnum): INSTALLED_APP = "installed-app" @classmethod - def value_of(cls, value: str) -> "WorkflowAppLogCreatedFrom": + def value_of(cls, value: str) -> WorkflowAppLogCreatedFrom: """ Get value of given mode. @@ -1181,7 +1183,7 @@ class ConversationVariable(TypeBase): ) @classmethod - def from_variable(cls, *, app_id: str, conversation_id: str, variable: Variable) -> "ConversationVariable": + def from_variable(cls, *, app_id: str, conversation_id: str, variable: Variable) -> ConversationVariable: obj = cls( id=variable.id, app_id=app_id, @@ -1334,7 +1336,7 @@ class WorkflowDraftVariable(Base): ) # Relationship to WorkflowDraftVariableFile - variable_file: Mapped[Optional["WorkflowDraftVariableFile"]] = orm.relationship( + variable_file: Mapped[WorkflowDraftVariableFile | None] = orm.relationship( foreign_keys=[file_id], lazy="raise", uselist=False, @@ -1504,8 +1506,9 @@ class WorkflowDraftVariable(Base): node_execution_id: str | None, description: str = "", file_id: str | None = None, - ) -> "WorkflowDraftVariable": + ) -> WorkflowDraftVariable: variable = WorkflowDraftVariable() + variable.id = str(uuid4()) variable.created_at = naive_utc_now() variable.updated_at = naive_utc_now() variable.description = description @@ -1526,7 +1529,7 @@ class WorkflowDraftVariable(Base): name: str, value: Segment, description: str = "", - ) -> "WorkflowDraftVariable": + ) -> WorkflowDraftVariable: variable = cls._new( app_id=app_id, node_id=CONVERSATION_VARIABLE_NODE_ID, @@ -1547,7 +1550,7 @@ class WorkflowDraftVariable(Base): value: Segment, node_execution_id: str, editable: bool = False, - ) -> "WorkflowDraftVariable": + ) -> WorkflowDraftVariable: variable = cls._new( app_id=app_id, node_id=SYSTEM_VARIABLE_NODE_ID, @@ -1570,7 +1573,7 @@ class WorkflowDraftVariable(Base): visible: bool = True, editable: bool = True, file_id: str | None = None, - ) -> "WorkflowDraftVariable": + ) -> WorkflowDraftVariable: variable = cls._new( app_id=app_id, node_id=node_id, @@ -1666,7 +1669,7 @@ class WorkflowDraftVariableFile(Base): ) # Relationship to UploadFile - upload_file: Mapped["UploadFile"] = orm.relationship( + upload_file: Mapped[UploadFile] = orm.relationship( foreign_keys=[upload_file_id], lazy="raise", uselist=False, @@ -1733,7 +1736,7 @@ class WorkflowPause(DefaultFieldsMixin, Base): state_object_key: Mapped[str] = mapped_column(String(length=255), nullable=False) # Relationship to WorkflowRun - workflow_run: Mapped["WorkflowRun"] = orm.relationship( + workflow_run: Mapped[WorkflowRun] = orm.relationship( foreign_keys=[workflow_run_id], # require explicit preloading. lazy="raise", @@ -1789,7 +1792,7 @@ class WorkflowPauseReason(DefaultFieldsMixin, Base): ) @classmethod - def from_entity(cls, pause_reason: PauseReason) -> "WorkflowPauseReason": + def from_entity(cls, pause_reason: PauseReason) -> WorkflowPauseReason: if isinstance(pause_reason, HumanInputRequired): return cls( type_=PauseReasonType.HUMAN_INPUT_REQUIRED, form_id=pause_reason.form_id, node_id=pause_reason.node_id diff --git a/api/services/conversation_service.py b/api/services/conversation_service.py index f56de36ef7..295d48d8a1 100644 --- a/api/services/conversation_service.py +++ b/api/services/conversation_service.py @@ -11,13 +11,13 @@ from core.app.entities.app_invoke_entities import InvokeFrom from core.db.session_factory import session_factory from core.llm_generator.llm_generator import LLMGenerator from core.variables.types import SegmentType -from core.workflow.nodes.variable_assigner.common.impl import conversation_variable_updater_factory from extensions.ext_database import db from factories import variable_factory from libs.datetime_utils import naive_utc_now from libs.infinite_scroll_pagination import InfiniteScrollPagination from models import Account, ConversationVariable from models.model import App, Conversation, EndUser, Message +from services.conversation_variable_updater import ConversationVariableUpdater from services.errors.conversation import ( ConversationNotExistsError, ConversationVariableNotExistsError, @@ -337,7 +337,7 @@ class ConversationService: updated_variable = variable_factory.build_conversation_variable_from_mapping(updated_variable_dict) # Use the conversation variable updater to persist the changes - updater = conversation_variable_updater_factory() + updater = ConversationVariableUpdater(session_factory.get_session_maker()) updater.update(conversation_id, updated_variable) updater.flush() diff --git a/api/services/conversation_variable_updater.py b/api/services/conversation_variable_updater.py new file mode 100644 index 0000000000..acc0ec2b22 --- /dev/null +++ b/api/services/conversation_variable_updater.py @@ -0,0 +1,28 @@ +from sqlalchemy import select +from sqlalchemy.orm import Session, sessionmaker + +from core.variables.variables import Variable +from models import ConversationVariable + + +class ConversationVariableNotFoundError(Exception): + pass + + +class ConversationVariableUpdater: + def __init__(self, session_maker: sessionmaker[Session]) -> None: + self._session_maker: sessionmaker[Session] = session_maker + + def update(self, conversation_id: str, variable: Variable) -> None: + stmt = select(ConversationVariable).where( + ConversationVariable.id == variable.id, ConversationVariable.conversation_id == conversation_id + ) + with self._session_maker() as session: + row = session.scalar(stmt) + if not row: + raise ConversationVariableNotFoundError("conversation variable not found in the database") + row.data = variable.model_dump_json() + session.commit() + + def flush(self) -> None: + pass diff --git a/api/services/rag_pipeline/rag_pipeline.py b/api/services/rag_pipeline/rag_pipeline.py index f53448e7fe..1ba64813ba 100644 --- a/api/services/rag_pipeline/rag_pipeline.py +++ b/api/services/rag_pipeline/rag_pipeline.py @@ -874,7 +874,7 @@ class RagPipelineService: variable_pool = node_instance.graph_runtime_state.variable_pool invoke_from = variable_pool.get(["sys", SystemVariableKey.INVOKE_FROM]) if invoke_from: - if invoke_from.value == InvokeFrom.PUBLISHED: + if invoke_from.value == InvokeFrom.PUBLISHED_PIPELINE: document_id = variable_pool.get(["sys", SystemVariableKey.DOCUMENT_ID]) if document_id: document = db.session.query(Document).where(Document.id == document_id.value).first() @@ -1318,7 +1318,7 @@ class RagPipelineService: "datasource_info_list": [json.loads(document_pipeline_execution_log.datasource_info)], "original_document_id": document.id, }, - invoke_from=InvokeFrom.PUBLISHED, + invoke_from=InvokeFrom.PUBLISHED_PIPELINE, streaming=False, call_depth=0, workflow_thread_pool_id=None, diff --git a/api/services/variable_truncator.py b/api/services/variable_truncator.py index 0f969207cf..f973361341 100644 --- a/api/services/variable_truncator.py +++ b/api/services/variable_truncator.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import dataclasses from abc import ABC, abstractmethod from collections.abc import Mapping @@ -106,7 +108,7 @@ class VariableTruncator(BaseTruncator): self._max_size_bytes = max_size_bytes @classmethod - def default(cls) -> "VariableTruncator": + def default(cls) -> VariableTruncator: return VariableTruncator( max_size_bytes=dify_config.WORKFLOW_VARIABLE_TRUNCATION_MAX_SIZE, array_element_limit=dify_config.WORKFLOW_VARIABLE_TRUNCATION_ARRAY_LENGTH, diff --git a/api/services/website_service.py b/api/services/website_service.py index a23f01ec71..fe48c3b08e 100644 --- a/api/services/website_service.py +++ b/api/services/website_service.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import datetime import json from dataclasses import dataclass @@ -78,7 +80,7 @@ class WebsiteCrawlApiRequest: return CrawlRequest(url=self.url, provider=self.provider, options=options) @classmethod - def from_args(cls, args: dict) -> "WebsiteCrawlApiRequest": + def from_args(cls, args: dict) -> WebsiteCrawlApiRequest: """Create from Flask-RESTful parsed arguments.""" provider = args.get("provider") url = args.get("url") @@ -102,7 +104,7 @@ class WebsiteCrawlStatusApiRequest: job_id: str @classmethod - def from_args(cls, args: dict, job_id: str) -> "WebsiteCrawlStatusApiRequest": + def from_args(cls, args: dict, job_id: str) -> WebsiteCrawlStatusApiRequest: """Create from Flask-RESTful parsed arguments.""" provider = args.get("provider") if not provider: diff --git a/api/services/workflow_draft_variable_service.py b/api/services/workflow_draft_variable_service.py index f299ce3baa..9407a2b3f0 100644 --- a/api/services/workflow_draft_variable_service.py +++ b/api/services/workflow_draft_variable_service.py @@ -679,6 +679,7 @@ def _batch_upsert_draft_variable( def _model_to_insertion_dict(model: WorkflowDraftVariable) -> dict[str, Any]: d: dict[str, Any] = { + "id": model.id, "app_id": model.app_id, "last_edited_at": None, "node_id": model.node_id, diff --git a/api/tasks/rag_pipeline/priority_rag_pipeline_run_task.py b/api/tasks/rag_pipeline/priority_rag_pipeline_run_task.py index 1eef361a92..3c5e152520 100644 --- a/api/tasks/rag_pipeline/priority_rag_pipeline_run_task.py +++ b/api/tasks/rag_pipeline/priority_rag_pipeline_run_task.py @@ -178,7 +178,7 @@ def run_single_rag_pipeline_task(rag_pipeline_invoke_entity: Mapping[str, Any], workflow_id=workflow_id, user=account, application_generate_entity=entity, - invoke_from=InvokeFrom.PUBLISHED, + invoke_from=InvokeFrom.PUBLISHED_PIPELINE, workflow_execution_repository=workflow_execution_repository, workflow_node_execution_repository=workflow_node_execution_repository, streaming=streaming, diff --git a/api/tasks/rag_pipeline/rag_pipeline_run_task.py b/api/tasks/rag_pipeline/rag_pipeline_run_task.py index 275f5abe6e..093342d1a3 100644 --- a/api/tasks/rag_pipeline/rag_pipeline_run_task.py +++ b/api/tasks/rag_pipeline/rag_pipeline_run_task.py @@ -178,7 +178,7 @@ def run_single_rag_pipeline_task(rag_pipeline_invoke_entity: Mapping[str, Any], workflow_id=workflow_id, user=account, application_generate_entity=entity, - invoke_from=InvokeFrom.PUBLISHED, + invoke_from=InvokeFrom.PUBLISHED_PIPELINE, workflow_execution_repository=workflow_execution_repository, workflow_node_execution_repository=workflow_node_execution_repository, streaming=streaming, diff --git a/api/tests/test_containers_integration_tests/tasks/test_rag_pipeline_run_tasks.py b/api/tests/test_containers_integration_tests/tasks/test_rag_pipeline_run_tasks.py index e29b98037f..b9977b1fb6 100644 --- a/api/tests/test_containers_integration_tests/tasks/test_rag_pipeline_run_tasks.py +++ b/api/tests/test_containers_integration_tests/tasks/test_rag_pipeline_run_tasks.py @@ -165,7 +165,7 @@ class TestRagPipelineRunTasks: "files": [], "user_id": account.id, "stream": False, - "invoke_from": "published", + "invoke_from": InvokeFrom.PUBLISHED_PIPELINE.value, "workflow_execution_id": str(uuid.uuid4()), "pipeline_config": { "app_id": str(uuid.uuid4()), @@ -249,7 +249,7 @@ class TestRagPipelineRunTasks: assert call_kwargs["pipeline"].id == pipeline.id assert call_kwargs["workflow_id"] == workflow.id assert call_kwargs["user"].id == account.id - assert call_kwargs["invoke_from"] == InvokeFrom.PUBLISHED + assert call_kwargs["invoke_from"] == InvokeFrom.PUBLISHED_PIPELINE assert call_kwargs["streaming"] == False assert isinstance(call_kwargs["application_generate_entity"], RagPipelineGenerateEntity) @@ -294,7 +294,7 @@ class TestRagPipelineRunTasks: assert call_kwargs["pipeline"].id == pipeline.id assert call_kwargs["workflow_id"] == workflow.id assert call_kwargs["user"].id == account.id - assert call_kwargs["invoke_from"] == InvokeFrom.PUBLISHED + assert call_kwargs["invoke_from"] == InvokeFrom.PUBLISHED_PIPELINE assert call_kwargs["streaming"] == False assert isinstance(call_kwargs["application_generate_entity"], RagPipelineGenerateEntity) @@ -743,7 +743,7 @@ class TestRagPipelineRunTasks: assert call_kwargs["pipeline"].id == pipeline.id assert call_kwargs["workflow_id"] == workflow.id assert call_kwargs["user"].id == account.id - assert call_kwargs["invoke_from"] == InvokeFrom.PUBLISHED + assert call_kwargs["invoke_from"] == InvokeFrom.PUBLISHED_PIPELINE assert call_kwargs["streaming"] == False assert isinstance(call_kwargs["application_generate_entity"], RagPipelineGenerateEntity) diff --git a/api/tests/unit_tests/configs/test_dify_config.py b/api/tests/unit_tests/configs/test_dify_config.py index 209b6bf59b..6fce7849f9 100644 --- a/api/tests/unit_tests/configs/test_dify_config.py +++ b/api/tests/unit_tests/configs/test_dify_config.py @@ -16,6 +16,7 @@ def test_dify_config(monkeypatch: pytest.MonkeyPatch): monkeypatch.setenv("CONSOLE_API_URL", "https://example.com") monkeypatch.setenv("CONSOLE_WEB_URL", "https://example.com") monkeypatch.setenv("HTTP_REQUEST_MAX_WRITE_TIMEOUT", "30") # Custom value for testing + monkeypatch.setenv("DB_TYPE", "postgresql") monkeypatch.setenv("DB_USERNAME", "postgres") monkeypatch.setenv("DB_PASSWORD", "postgres") monkeypatch.setenv("DB_HOST", "localhost") @@ -51,6 +52,7 @@ def test_http_timeout_defaults(monkeypatch: pytest.MonkeyPatch): os.environ.clear() # Set minimal required env vars + monkeypatch.setenv("DB_TYPE", "postgresql") monkeypatch.setenv("DB_USERNAME", "postgres") monkeypatch.setenv("DB_PASSWORD", "postgres") monkeypatch.setenv("DB_HOST", "localhost") @@ -75,6 +77,7 @@ def test_flask_configs(monkeypatch: pytest.MonkeyPatch): # Set environment variables using monkeypatch monkeypatch.setenv("CONSOLE_API_URL", "https://example.com") monkeypatch.setenv("CONSOLE_WEB_URL", "https://example.com") + monkeypatch.setenv("DB_TYPE", "postgresql") monkeypatch.setenv("DB_USERNAME", "postgres") monkeypatch.setenv("DB_PASSWORD", "postgres") monkeypatch.setenv("DB_HOST", "localhost") @@ -124,6 +127,7 @@ def test_inner_api_config_exist(monkeypatch: pytest.MonkeyPatch): # Set environment variables using monkeypatch monkeypatch.setenv("CONSOLE_API_URL", "https://example.com") monkeypatch.setenv("CONSOLE_WEB_URL", "https://example.com") + monkeypatch.setenv("DB_TYPE", "postgresql") monkeypatch.setenv("DB_USERNAME", "postgres") monkeypatch.setenv("DB_PASSWORD", "postgres") monkeypatch.setenv("DB_HOST", "localhost") @@ -140,6 +144,7 @@ def test_inner_api_config_exist(monkeypatch: pytest.MonkeyPatch): def test_db_extras_options_merging(monkeypatch: pytest.MonkeyPatch): """Test that DB_EXTRAS options are properly merged with default timezone setting""" # Set environment variables + monkeypatch.setenv("DB_TYPE", "postgresql") monkeypatch.setenv("DB_USERNAME", "postgres") monkeypatch.setenv("DB_PASSWORD", "postgres") monkeypatch.setenv("DB_HOST", "localhost") @@ -199,6 +204,7 @@ def test_celery_broker_url_with_special_chars_password( # Set up basic required environment variables (following existing pattern) monkeypatch.setenv("CONSOLE_API_URL", "https://example.com") monkeypatch.setenv("CONSOLE_WEB_URL", "https://example.com") + monkeypatch.setenv("DB_TYPE", "postgresql") monkeypatch.setenv("DB_USERNAME", "postgres") monkeypatch.setenv("DB_PASSWORD", "postgres") monkeypatch.setenv("DB_HOST", "localhost") diff --git a/api/tests/unit_tests/controllers/console/test_files_security.py b/api/tests/unit_tests/controllers/console/test_files_security.py index 2630fbcfd0..370bf63fdb 100644 --- a/api/tests/unit_tests/controllers/console/test_files_security.py +++ b/api/tests/unit_tests/controllers/console/test_files_security.py @@ -1,7 +1,9 @@ +import builtins import io from unittest.mock import patch import pytest +from flask.views import MethodView from werkzeug.exceptions import Forbidden from controllers.common.errors import ( @@ -14,6 +16,9 @@ from controllers.common.errors import ( from services.errors.file import FileTooLargeError as ServiceFileTooLargeError from services.errors.file import UnsupportedFileTypeError as ServiceUnsupportedFileTypeError +if not hasattr(builtins, "MethodView"): + builtins.MethodView = MethodView # type: ignore[attr-defined] + class TestFileUploadSecurity: """Test file upload security logic without complex framework setup""" @@ -128,7 +133,7 @@ class TestFileUploadSecurity: # Test passes if no exception is raised # Test 4: Service error handling - @patch("services.file_service.FileService.upload_file") + @patch("controllers.console.files.FileService.upload_file") def test_should_handle_file_too_large_error(self, mock_upload): """Test that service FileTooLargeError is properly converted""" mock_upload.side_effect = ServiceFileTooLargeError("File too large") @@ -140,7 +145,7 @@ class TestFileUploadSecurity: with pytest.raises(FileTooLargeError): raise FileTooLargeError(e.description) - @patch("services.file_service.FileService.upload_file") + @patch("controllers.console.files.FileService.upload_file") def test_should_handle_unsupported_file_type_error(self, mock_upload): """Test that service UnsupportedFileTypeError is properly converted""" mock_upload.side_effect = ServiceUnsupportedFileTypeError() diff --git a/api/tests/unit_tests/core/app/apps/common/test_workflow_response_converter_truncation.py b/api/tests/unit_tests/core/app/apps/common/test_workflow_response_converter_truncation.py index 1c9f577a50..6b40bf462b 100644 --- a/api/tests/unit_tests/core/app/apps/common/test_workflow_response_converter_truncation.py +++ b/api/tests/unit_tests/core/app/apps/common/test_workflow_response_converter_truncation.py @@ -431,10 +431,10 @@ class TestWorkflowResponseConverterServiceApiTruncation: description="Explore calls should have truncation enabled", ), TestCase( - name="published_truncation_enabled", - invoke_from=InvokeFrom.PUBLISHED, + name="published_pipeline_truncation_enabled", + invoke_from=InvokeFrom.PUBLISHED_PIPELINE, expected_truncation_enabled=True, - description="Published app calls should have truncation enabled", + description="Published pipeline calls should have truncation enabled", ), ], ids=lambda x: x.name, diff --git a/api/tests/unit_tests/core/app/layers/test_conversation_variable_persist_layer.py b/api/tests/unit_tests/core/app/layers/test_conversation_variable_persist_layer.py new file mode 100644 index 0000000000..b6e8cc9c8e --- /dev/null +++ b/api/tests/unit_tests/core/app/layers/test_conversation_variable_persist_layer.py @@ -0,0 +1,144 @@ +from collections.abc import Sequence +from datetime import datetime +from unittest.mock import Mock + +from core.app.layers.conversation_variable_persist_layer import ConversationVariablePersistenceLayer +from core.variables import StringVariable +from core.variables.segments import Segment +from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID +from core.workflow.enums import NodeType, WorkflowNodeExecutionStatus +from core.workflow.graph_engine.protocols.command_channel import CommandChannel +from core.workflow.graph_events.node import NodeRunSucceededEvent +from core.workflow.node_events import NodeRunResult +from core.workflow.nodes.variable_assigner.common import helpers as common_helpers +from core.workflow.runtime.graph_runtime_state_protocol import ReadOnlyGraphRuntimeState +from core.workflow.system_variable import SystemVariable + + +class MockReadOnlyVariablePool: + def __init__(self, variables: dict[tuple[str, str], Segment] | None = None) -> None: + self._variables = variables or {} + + def get(self, selector: Sequence[str]) -> Segment | None: + if len(selector) < 2: + return None + return self._variables.get((selector[0], selector[1])) + + def get_all_by_node(self, node_id: str) -> dict[str, object]: + return {key: value for (nid, key), value in self._variables.items() if nid == node_id} + + def get_by_prefix(self, prefix: str) -> dict[str, object]: + return {key: value for (nid, key), value in self._variables.items() if nid == prefix} + + +def _build_graph_runtime_state( + variable_pool: MockReadOnlyVariablePool, + conversation_id: str | None = None, +) -> ReadOnlyGraphRuntimeState: + graph_runtime_state = Mock(spec=ReadOnlyGraphRuntimeState) + graph_runtime_state.variable_pool = variable_pool + graph_runtime_state.system_variable = SystemVariable(conversation_id=conversation_id).as_view() + return graph_runtime_state + + +def _build_node_run_succeeded_event( + *, + node_type: NodeType, + outputs: dict[str, object] | None = None, + process_data: dict[str, object] | None = None, +) -> NodeRunSucceededEvent: + return NodeRunSucceededEvent( + id="node-exec-id", + node_id="assigner", + node_type=node_type, + start_at=datetime.utcnow(), + node_run_result=NodeRunResult( + status=WorkflowNodeExecutionStatus.SUCCEEDED, + outputs=outputs or {}, + process_data=process_data or {}, + ), + ) + + +def test_persists_conversation_variables_from_assigner_output(): + conversation_id = "conv-123" + variable = StringVariable( + id="var-1", + name="name", + value="updated", + selector=[CONVERSATION_VARIABLE_NODE_ID, "name"], + ) + process_data = common_helpers.set_updated_variables( + {}, [common_helpers.variable_to_processed_data(variable.selector, variable)] + ) + + variable_pool = MockReadOnlyVariablePool({(CONVERSATION_VARIABLE_NODE_ID, "name"): variable}) + + updater = Mock() + layer = ConversationVariablePersistenceLayer(updater) + layer.initialize(_build_graph_runtime_state(variable_pool, conversation_id), Mock(spec=CommandChannel)) + + event = _build_node_run_succeeded_event(node_type=NodeType.VARIABLE_ASSIGNER, process_data=process_data) + layer.on_event(event) + + updater.update.assert_called_once_with(conversation_id=conversation_id, variable=variable) + updater.flush.assert_called_once() + + +def test_skips_when_outputs_missing(): + conversation_id = "conv-456" + variable = StringVariable( + id="var-2", + name="name", + value="updated", + selector=[CONVERSATION_VARIABLE_NODE_ID, "name"], + ) + + variable_pool = MockReadOnlyVariablePool({(CONVERSATION_VARIABLE_NODE_ID, "name"): variable}) + + updater = Mock() + layer = ConversationVariablePersistenceLayer(updater) + layer.initialize(_build_graph_runtime_state(variable_pool, conversation_id), Mock(spec=CommandChannel)) + + event = _build_node_run_succeeded_event(node_type=NodeType.VARIABLE_ASSIGNER) + layer.on_event(event) + + updater.update.assert_not_called() + updater.flush.assert_not_called() + + +def test_skips_non_assigner_nodes(): + updater = Mock() + layer = ConversationVariablePersistenceLayer(updater) + layer.initialize(_build_graph_runtime_state(MockReadOnlyVariablePool()), Mock(spec=CommandChannel)) + + event = _build_node_run_succeeded_event(node_type=NodeType.LLM) + layer.on_event(event) + + updater.update.assert_not_called() + updater.flush.assert_not_called() + + +def test_skips_non_conversation_variables(): + conversation_id = "conv-789" + non_conversation_variable = StringVariable( + id="var-3", + name="name", + value="updated", + selector=["environment", "name"], + ) + process_data = common_helpers.set_updated_variables( + {}, [common_helpers.variable_to_processed_data(non_conversation_variable.selector, non_conversation_variable)] + ) + + variable_pool = MockReadOnlyVariablePool() + + updater = Mock() + layer = ConversationVariablePersistenceLayer(updater) + layer.initialize(_build_graph_runtime_state(variable_pool, conversation_id), Mock(spec=CommandChannel)) + + event = _build_node_run_succeeded_event(node_type=NodeType.VARIABLE_ASSIGNER, process_data=process_data) + layer.on_event(event) + + updater.update.assert_not_called() + updater.flush.assert_not_called() diff --git a/api/tests/unit_tests/core/app/layers/test_pause_state_persist_layer.py b/api/tests/unit_tests/core/app/layers/test_pause_state_persist_layer.py index 5a5386ee57..1d885f6b2e 100644 --- a/api/tests/unit_tests/core/app/layers/test_pause_state_persist_layer.py +++ b/api/tests/unit_tests/core/app/layers/test_pause_state_persist_layer.py @@ -1,4 +1,5 @@ import json +from collections.abc import Sequence from time import time from unittest.mock import Mock @@ -67,8 +68,10 @@ class MockReadOnlyVariablePool: def __init__(self, variables: dict[tuple[str, str], object] | None = None): self._variables = variables or {} - def get(self, node_id: str, variable_key: str) -> Segment | None: - value = self._variables.get((node_id, variable_key)) + def get(self, selector: Sequence[str]) -> Segment | None: + if len(selector) < 2: + return None + value = self._variables.get((selector[0], selector[1])) if value is None: return None mock_segment = Mock(spec=Segment) diff --git a/api/tests/unit_tests/core/rag/extractor/test_word_extractor.py b/api/tests/unit_tests/core/rag/extractor/test_word_extractor.py index 3203aab8c3..f9e59a5f05 100644 --- a/api/tests/unit_tests/core/rag/extractor/test_word_extractor.py +++ b/api/tests/unit_tests/core/rag/extractor/test_word_extractor.py @@ -1,8 +1,12 @@ """Primarily used for testing merged cell scenarios""" +import os +import tempfile from types import SimpleNamespace from docx import Document +from docx.oxml import OxmlElement +from docx.oxml.ns import qn import core.rag.extractor.word_extractor as we from core.rag.extractor.word_extractor import WordExtractor @@ -165,3 +169,110 @@ def test_extract_images_from_docx_uses_internal_files_url(): dify_config.FILES_URL = original_files_url if original_internal_files_url is not None: dify_config.INTERNAL_FILES_URL = original_internal_files_url + + +def test_extract_hyperlinks(monkeypatch): + # Mock db and storage to avoid issues during image extraction (even if no images are present) + monkeypatch.setattr(we, "storage", SimpleNamespace(save=lambda k, d: None)) + db_stub = SimpleNamespace(session=SimpleNamespace(add=lambda o: None, commit=lambda: None)) + monkeypatch.setattr(we, "db", db_stub) + monkeypatch.setattr(we.dify_config, "FILES_URL", "http://files.local", raising=False) + monkeypatch.setattr(we.dify_config, "STORAGE_TYPE", "local", raising=False) + + doc = Document() + p = doc.add_paragraph("Visit ") + + # Adding a hyperlink manually + r_id = "rId99" + hyperlink = OxmlElement("w:hyperlink") + hyperlink.set(qn("r:id"), r_id) + + new_run = OxmlElement("w:r") + t = OxmlElement("w:t") + t.text = "Dify" + new_run.append(t) + hyperlink.append(new_run) + p._p.append(hyperlink) + + # Add relationship to the part + doc.part.rels.add_relationship( + "http://schemas.openxmlformats.org/officeDocument/2006/relationships/hyperlink", + "https://dify.ai", + r_id, + is_external=True, + ) + + with tempfile.NamedTemporaryFile(suffix=".docx", delete=False) as tmp: + doc.save(tmp.name) + tmp_path = tmp.name + + try: + extractor = WordExtractor(tmp_path, "tenant_id", "user_id") + docs = extractor.extract() + # Verify modern hyperlink extraction + assert "Visit[Dify](https://dify.ai)" in docs[0].page_content + finally: + if os.path.exists(tmp_path): + os.remove(tmp_path) + + +def test_extract_legacy_hyperlinks(monkeypatch): + # Mock db and storage + monkeypatch.setattr(we, "storage", SimpleNamespace(save=lambda k, d: None)) + db_stub = SimpleNamespace(session=SimpleNamespace(add=lambda o: None, commit=lambda: None)) + monkeypatch.setattr(we, "db", db_stub) + monkeypatch.setattr(we.dify_config, "FILES_URL", "http://files.local", raising=False) + monkeypatch.setattr(we.dify_config, "STORAGE_TYPE", "local", raising=False) + + doc = Document() + p = doc.add_paragraph() + + # Construct a legacy HYPERLINK field: + # 1. w:fldChar (begin) + # 2. w:instrText (HYPERLINK "http://example.com") + # 3. w:fldChar (separate) + # 4. w:r (visible text "Example") + # 5. w:fldChar (end) + + run1 = OxmlElement("w:r") + fldCharBegin = OxmlElement("w:fldChar") + fldCharBegin.set(qn("w:fldCharType"), "begin") + run1.append(fldCharBegin) + p._p.append(run1) + + run2 = OxmlElement("w:r") + instrText = OxmlElement("w:instrText") + instrText.text = ' HYPERLINK "http://example.com" ' + run2.append(instrText) + p._p.append(run2) + + run3 = OxmlElement("w:r") + fldCharSep = OxmlElement("w:fldChar") + fldCharSep.set(qn("w:fldCharType"), "separate") + run3.append(fldCharSep) + p._p.append(run3) + + run4 = OxmlElement("w:r") + t4 = OxmlElement("w:t") + t4.text = "Example" + run4.append(t4) + p._p.append(run4) + + run5 = OxmlElement("w:r") + fldCharEnd = OxmlElement("w:fldChar") + fldCharEnd.set(qn("w:fldCharType"), "end") + run5.append(fldCharEnd) + p._p.append(run5) + + with tempfile.NamedTemporaryFile(suffix=".docx", delete=False) as tmp: + doc.save(tmp.name) + tmp_path = tmp.name + + try: + extractor = WordExtractor(tmp_path, "tenant_id", "user_id") + docs = extractor.extract() + # Verify legacy hyperlink extraction + assert "[Example](http://example.com)" in docs[0].page_content + finally: + if os.path.exists(tmp_path): + os.remove(tmp_path) diff --git a/api/tests/unit_tests/core/workflow/graph_engine/test_mock_config.py b/api/tests/unit_tests/core/workflow/graph_engine/test_mock_config.py index b02f90588b..5ceb8dd7f7 100644 --- a/api/tests/unit_tests/core/workflow/graph_engine/test_mock_config.py +++ b/api/tests/unit_tests/core/workflow/graph_engine/test_mock_config.py @@ -5,6 +5,8 @@ This module provides a flexible configuration system for customizing the behavior of mock nodes during testing. """ +from __future__ import annotations + from collections.abc import Callable from dataclasses import dataclass, field from typing import Any @@ -95,67 +97,67 @@ class MockConfigBuilder: def __init__(self) -> None: self._config = MockConfig() - def with_auto_mock(self, enabled: bool = True) -> "MockConfigBuilder": + def with_auto_mock(self, enabled: bool = True) -> MockConfigBuilder: """Enable or disable auto-mocking.""" self._config.enable_auto_mock = enabled return self - def with_delays(self, enabled: bool = True) -> "MockConfigBuilder": + def with_delays(self, enabled: bool = True) -> MockConfigBuilder: """Enable or disable simulated execution delays.""" self._config.simulate_delays = enabled return self - def with_llm_response(self, response: str) -> "MockConfigBuilder": + def with_llm_response(self, response: str) -> MockConfigBuilder: """Set default LLM response.""" self._config.default_llm_response = response return self - def with_agent_response(self, response: str) -> "MockConfigBuilder": + def with_agent_response(self, response: str) -> MockConfigBuilder: """Set default agent response.""" self._config.default_agent_response = response return self - def with_tool_response(self, response: dict[str, Any]) -> "MockConfigBuilder": + def with_tool_response(self, response: dict[str, Any]) -> MockConfigBuilder: """Set default tool response.""" self._config.default_tool_response = response return self - def with_retrieval_response(self, response: str) -> "MockConfigBuilder": + def with_retrieval_response(self, response: str) -> MockConfigBuilder: """Set default retrieval response.""" self._config.default_retrieval_response = response return self - def with_http_response(self, response: dict[str, Any]) -> "MockConfigBuilder": + def with_http_response(self, response: dict[str, Any]) -> MockConfigBuilder: """Set default HTTP response.""" self._config.default_http_response = response return self - def with_template_transform_response(self, response: str) -> "MockConfigBuilder": + def with_template_transform_response(self, response: str) -> MockConfigBuilder: """Set default template transform response.""" self._config.default_template_transform_response = response return self - def with_code_response(self, response: dict[str, Any]) -> "MockConfigBuilder": + def with_code_response(self, response: dict[str, Any]) -> MockConfigBuilder: """Set default code execution response.""" self._config.default_code_response = response return self - def with_node_output(self, node_id: str, outputs: dict[str, Any]) -> "MockConfigBuilder": + def with_node_output(self, node_id: str, outputs: dict[str, Any]) -> MockConfigBuilder: """Set outputs for a specific node.""" self._config.set_node_outputs(node_id, outputs) return self - def with_node_error(self, node_id: str, error: str) -> "MockConfigBuilder": + def with_node_error(self, node_id: str, error: str) -> MockConfigBuilder: """Set error for a specific node.""" self._config.set_node_error(node_id, error) return self - def with_node_config(self, config: NodeMockConfig) -> "MockConfigBuilder": + def with_node_config(self, config: NodeMockConfig) -> MockConfigBuilder: """Add a node-specific configuration.""" self._config.set_node_config(config.node_id, config) return self - def with_default_config(self, node_type: NodeType, config: dict[str, Any]) -> "MockConfigBuilder": + def with_default_config(self, node_type: NodeType, config: dict[str, Any]) -> MockConfigBuilder: """Set default configuration for a node type.""" self._config.set_default_config(node_type, config) return self diff --git a/api/tests/unit_tests/core/workflow/nodes/llm/test_file_saver.py b/api/tests/unit_tests/core/workflow/nodes/llm/test_file_saver.py index e8f257bf2f..1e224d56a5 100644 --- a/api/tests/unit_tests/core/workflow/nodes/llm/test_file_saver.py +++ b/api/tests/unit_tests/core/workflow/nodes/llm/test_file_saver.py @@ -78,7 +78,7 @@ class TestFileSaverImpl: file_binary=_PNG_DATA, mimetype=mime_type, ) - mocked_sign_file.assert_called_once_with(mock_tool_file.id, ".png") + mocked_sign_file.assert_called_once_with(tool_file_id=mock_tool_file.id, extension=".png", for_external=True) def test_save_remote_url_request_failed(self, monkeypatch: pytest.MonkeyPatch): _TEST_URL = "https://example.com/image.png" diff --git a/api/tests/unit_tests/core/workflow/nodes/tool/test_tool_node.py b/api/tests/unit_tests/core/workflow/nodes/tool/test_tool_node.py index 09b8191870..06927cddcf 100644 --- a/api/tests/unit_tests/core/workflow/nodes/tool/test_tool_node.py +++ b/api/tests/unit_tests/core/workflow/nodes/tool/test_tool_node.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import sys import types from collections.abc import Generator @@ -21,7 +23,7 @@ if TYPE_CHECKING: # pragma: no cover - imported for type checking only @pytest.fixture -def tool_node(monkeypatch) -> "ToolNode": +def tool_node(monkeypatch) -> ToolNode: module_name = "core.ops.ops_trace_manager" if module_name not in sys.modules: ops_stub = types.ModuleType(module_name) @@ -85,7 +87,7 @@ def _collect_events(generator: Generator) -> tuple[list[Any], LLMUsage]: return events, stop.value -def _run_transform(tool_node: "ToolNode", message: ToolInvokeMessage) -> tuple[list[Any], LLMUsage]: +def _run_transform(tool_node: ToolNode, message: ToolInvokeMessage) -> tuple[list[Any], LLMUsage]: def _identity_transform(messages, *_args, **_kwargs): return messages @@ -103,7 +105,7 @@ def _run_transform(tool_node: "ToolNode", message: ToolInvokeMessage) -> tuple[l return _collect_events(generator) -def test_link_messages_with_file_populate_files_output(tool_node: "ToolNode"): +def test_link_messages_with_file_populate_files_output(tool_node: ToolNode): file_obj = File( tenant_id="tenant-id", type=FileType.DOCUMENT, @@ -139,7 +141,7 @@ def test_link_messages_with_file_populate_files_output(tool_node: "ToolNode"): assert files_segment.value == [file_obj] -def test_plain_link_messages_remain_links(tool_node: "ToolNode"): +def test_plain_link_messages_remain_links(tool_node: ToolNode): message = ToolInvokeMessage( type=ToolInvokeMessage.MessageType.LINK, message=ToolInvokeMessage.TextMessage(text="https://dify.ai"), diff --git a/api/tests/unit_tests/core/workflow/nodes/variable_assigner/v1/test_variable_assigner_v1.py b/api/tests/unit_tests/core/workflow/nodes/variable_assigner/v1/test_variable_assigner_v1.py index c62fc4d8fe..1df75380af 100644 --- a/api/tests/unit_tests/core/workflow/nodes/variable_assigner/v1/test_variable_assigner_v1.py +++ b/api/tests/unit_tests/core/workflow/nodes/variable_assigner/v1/test_variable_assigner_v1.py @@ -1,14 +1,14 @@ import time import uuid -from unittest import mock from uuid import uuid4 from core.app.entities.app_invoke_entities import InvokeFrom from core.variables import ArrayStringVariable, StringVariable -from core.workflow.conversation_variable_updater import ConversationVariableUpdater from core.workflow.entities import GraphInitParams from core.workflow.graph import Graph +from core.workflow.graph_events.node import NodeRunSucceededEvent from core.workflow.nodes.node_factory import DifyNodeFactory +from core.workflow.nodes.variable_assigner.common import helpers as common_helpers from core.workflow.nodes.variable_assigner.v1 import VariableAssignerNode from core.workflow.nodes.variable_assigner.v1.node_data import WriteMode from core.workflow.runtime import GraphRuntimeState, VariablePool @@ -86,9 +86,6 @@ def test_overwrite_string_variable(): ) graph = Graph.init(graph_config=graph_config, node_factory=node_factory) - mock_conv_var_updater = mock.Mock(spec=ConversationVariableUpdater) - mock_conv_var_updater_factory = mock.Mock(return_value=mock_conv_var_updater) - node_config = { "id": "node_id", "data": { @@ -104,20 +101,14 @@ def test_overwrite_string_variable(): graph_init_params=init_params, graph_runtime_state=graph_runtime_state, config=node_config, - conv_var_updater_factory=mock_conv_var_updater_factory, ) - list(node.run()) - expected_var = StringVariable( - id=conversation_variable.id, - name=conversation_variable.name, - description=conversation_variable.description, - selector=conversation_variable.selector, - value_type=conversation_variable.value_type, - value=input_variable.value, - ) - mock_conv_var_updater.update.assert_called_once_with(conversation_id=conversation_id, variable=expected_var) - mock_conv_var_updater.flush.assert_called_once() + events = list(node.run()) + succeeded_event = next(event for event in events if isinstance(event, NodeRunSucceededEvent)) + updated_variables = common_helpers.get_updated_variables(succeeded_event.node_run_result.process_data) + assert updated_variables is not None + assert updated_variables[0].name == conversation_variable.name + assert updated_variables[0].new_value == input_variable.value got = variable_pool.get(["conversation", conversation_variable.name]) assert got is not None @@ -191,9 +182,6 @@ def test_append_variable_to_array(): ) graph = Graph.init(graph_config=graph_config, node_factory=node_factory) - mock_conv_var_updater = mock.Mock(spec=ConversationVariableUpdater) - mock_conv_var_updater_factory = mock.Mock(return_value=mock_conv_var_updater) - node_config = { "id": "node_id", "data": { @@ -209,22 +197,14 @@ def test_append_variable_to_array(): graph_init_params=init_params, graph_runtime_state=graph_runtime_state, config=node_config, - conv_var_updater_factory=mock_conv_var_updater_factory, ) - list(node.run()) - expected_value = list(conversation_variable.value) - expected_value.append(input_variable.value) - expected_var = ArrayStringVariable( - id=conversation_variable.id, - name=conversation_variable.name, - description=conversation_variable.description, - selector=conversation_variable.selector, - value_type=conversation_variable.value_type, - value=expected_value, - ) - mock_conv_var_updater.update.assert_called_once_with(conversation_id=conversation_id, variable=expected_var) - mock_conv_var_updater.flush.assert_called_once() + events = list(node.run()) + succeeded_event = next(event for event in events if isinstance(event, NodeRunSucceededEvent)) + updated_variables = common_helpers.get_updated_variables(succeeded_event.node_run_result.process_data) + assert updated_variables is not None + assert updated_variables[0].name == conversation_variable.name + assert updated_variables[0].new_value == ["the first value", "the second value"] got = variable_pool.get(["conversation", conversation_variable.name]) assert got is not None @@ -287,9 +267,6 @@ def test_clear_array(): ) graph = Graph.init(graph_config=graph_config, node_factory=node_factory) - mock_conv_var_updater = mock.Mock(spec=ConversationVariableUpdater) - mock_conv_var_updater_factory = mock.Mock(return_value=mock_conv_var_updater) - node_config = { "id": "node_id", "data": { @@ -305,20 +282,14 @@ def test_clear_array(): graph_init_params=init_params, graph_runtime_state=graph_runtime_state, config=node_config, - conv_var_updater_factory=mock_conv_var_updater_factory, ) - list(node.run()) - expected_var = ArrayStringVariable( - id=conversation_variable.id, - name=conversation_variable.name, - description=conversation_variable.description, - selector=conversation_variable.selector, - value_type=conversation_variable.value_type, - value=[], - ) - mock_conv_var_updater.update.assert_called_once_with(conversation_id=conversation_id, variable=expected_var) - mock_conv_var_updater.flush.assert_called_once() + events = list(node.run()) + succeeded_event = next(event for event in events if isinstance(event, NodeRunSucceededEvent)) + updated_variables = common_helpers.get_updated_variables(succeeded_event.node_run_result.process_data) + assert updated_variables is not None + assert updated_variables[0].name == conversation_variable.name + assert updated_variables[0].new_value == [] got = variable_pool.get(["conversation", conversation_variable.name]) assert got is not None diff --git a/api/tests/unit_tests/core/workflow/nodes/variable_assigner/v2/test_variable_assigner_v2.py b/api/tests/unit_tests/core/workflow/nodes/variable_assigner/v2/test_variable_assigner_v2.py index caa36734ad..353d56fe25 100644 --- a/api/tests/unit_tests/core/workflow/nodes/variable_assigner/v2/test_variable_assigner_v2.py +++ b/api/tests/unit_tests/core/workflow/nodes/variable_assigner/v2/test_variable_assigner_v2.py @@ -390,3 +390,42 @@ def test_remove_last_from_empty_array(): got = variable_pool.get(["conversation", conversation_variable.name]) assert got is not None assert got.to_object() == [] + + +def test_node_factory_creates_variable_assigner_node(): + graph_config = { + "edges": [], + "nodes": [ + { + "data": {"type": "assigner", "version": "2", "title": "Variable Assigner", "items": []}, + "id": "assigner", + }, + ], + } + + init_params = GraphInitParams( + tenant_id="1", + app_id="1", + workflow_id="1", + graph_config=graph_config, + user_id="1", + user_from=UserFrom.ACCOUNT, + invoke_from=InvokeFrom.DEBUGGER, + call_depth=0, + ) + variable_pool = VariablePool( + system_variables=SystemVariable(conversation_id="conversation_id"), + user_inputs={}, + environment_variables=[], + conversation_variables=[], + ) + graph_runtime_state = GraphRuntimeState(variable_pool=variable_pool, start_at=time.perf_counter()) + + node_factory = DifyNodeFactory( + graph_init_params=init_params, + graph_runtime_state=graph_runtime_state, + ) + + node = node_factory.create_node(graph_config["nodes"][0]) + + assert isinstance(node, VariableAssignerNode) diff --git a/api/tests/unit_tests/fields/test_file_fields.py b/api/tests/unit_tests/fields/test_file_fields.py new file mode 100644 index 0000000000..8be8df16f4 --- /dev/null +++ b/api/tests/unit_tests/fields/test_file_fields.py @@ -0,0 +1,78 @@ +from __future__ import annotations + +from datetime import datetime +from types import SimpleNamespace + +from fields.file_fields import FileResponse, FileWithSignedUrl, RemoteFileInfo, UploadConfig + + +def test_file_response_serializes_datetime() -> None: + created_at = datetime(2024, 1, 1, 12, 0, 0) + file_obj = SimpleNamespace( + id="file-1", + name="example.txt", + size=1024, + extension="txt", + mime_type="text/plain", + created_by="user-1", + created_at=created_at, + preview_url="https://preview", + source_url="https://source", + original_url="https://origin", + user_id="user-1", + tenant_id="tenant-1", + conversation_id="conv-1", + file_key="key-1", + ) + + serialized = FileResponse.model_validate(file_obj, from_attributes=True).model_dump(mode="json") + + assert serialized["id"] == "file-1" + assert serialized["created_at"] == int(created_at.timestamp()) + assert serialized["preview_url"] == "https://preview" + assert serialized["source_url"] == "https://source" + assert serialized["original_url"] == "https://origin" + assert serialized["user_id"] == "user-1" + assert serialized["tenant_id"] == "tenant-1" + assert serialized["conversation_id"] == "conv-1" + assert serialized["file_key"] == "key-1" + + +def test_file_with_signed_url_builds_payload() -> None: + payload = FileWithSignedUrl( + id="file-2", + name="remote.pdf", + size=2048, + extension="pdf", + url="https://signed", + mime_type="application/pdf", + created_by="user-2", + created_at=datetime(2024, 1, 2, 0, 0, 0), + ) + + dumped = payload.model_dump(mode="json") + + assert dumped["url"] == "https://signed" + assert dumped["created_at"] == int(datetime(2024, 1, 2, 0, 0, 0).timestamp()) + + +def test_remote_file_info_and_upload_config() -> None: + info = RemoteFileInfo(file_type="text/plain", file_length=123) + assert info.model_dump(mode="json") == {"file_type": "text/plain", "file_length": 123} + + config = UploadConfig( + file_size_limit=1, + batch_count_limit=2, + file_upload_limit=3, + image_file_size_limit=4, + video_file_size_limit=5, + audio_file_size_limit=6, + workflow_file_upload_limit=7, + image_file_batch_limit=8, + single_chunk_attachment_limit=9, + attachment_image_file_size_limit=10, + ) + + dumped = config.model_dump(mode="json") + assert dumped["file_upload_limit"] == 3 + assert dumped["attachment_image_file_size_limit"] == 10 diff --git a/docker/.env.example b/docker/.env.example index 66d937e8e7..09ee1060e2 100644 --- a/docker/.env.example +++ b/docker/.env.example @@ -58,8 +58,8 @@ FILES_URL= INTERNAL_FILES_URL= # Ensure UTF-8 encoding -LANG=en_US.UTF-8 -LC_ALL=en_US.UTF-8 +LANG=C.UTF-8 +LC_ALL=C.UTF-8 PYTHONIOENCODING=utf-8 # ------------------------------ diff --git a/docker/docker-compose-template.yaml b/docker/docker-compose-template.yaml index 3c88cddf8c..709aff23df 100644 --- a/docker/docker-compose-template.yaml +++ b/docker/docker-compose-template.yaml @@ -475,7 +475,8 @@ services: OB_CLUSTER_NAME: ${OCEANBASE_CLUSTER_NAME:-difyai} OB_SERVER_IP: 127.0.0.1 MODE: mini - LANG: en_US.UTF-8 + LANG: C.UTF-8 + LC_ALL: C.UTF-8 ports: - "${OCEANBASE_VECTOR_PORT:-2881}:2881" healthcheck: diff --git a/docker/docker-compose.yaml b/docker/docker-compose.yaml index 54b9e744f8..712de84c62 100644 --- a/docker/docker-compose.yaml +++ b/docker/docker-compose.yaml @@ -13,8 +13,8 @@ x-shared-env: &shared-api-worker-env APP_WEB_URL: ${APP_WEB_URL:-} FILES_URL: ${FILES_URL:-} INTERNAL_FILES_URL: ${INTERNAL_FILES_URL:-} - LANG: ${LANG:-en_US.UTF-8} - LC_ALL: ${LC_ALL:-en_US.UTF-8} + LANG: ${LANG:-C.UTF-8} + LC_ALL: ${LC_ALL:-C.UTF-8} PYTHONIOENCODING: ${PYTHONIOENCODING:-utf-8} LOG_LEVEL: ${LOG_LEVEL:-INFO} LOG_OUTPUT_FORMAT: ${LOG_OUTPUT_FORMAT:-text} @@ -1157,7 +1157,8 @@ services: OB_CLUSTER_NAME: ${OCEANBASE_CLUSTER_NAME:-difyai} OB_SERVER_IP: 127.0.0.1 MODE: mini - LANG: en_US.UTF-8 + LANG: C.UTF-8 + LC_ALL: C.UTF-8 ports: - "${OCEANBASE_VECTOR_PORT:-2881}:2881" healthcheck: diff --git a/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/settings/page.tsx b/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/settings/page.tsx index 8080b565cd..1d65e4de53 100644 --- a/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/settings/page.tsx +++ b/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/settings/page.tsx @@ -1,11 +1,8 @@ -/* eslint-disable dify-i18n/require-ns-option */ -import * as React from 'react' +import { useTranslation } from '#i18n' import Form from '@/app/components/datasets/settings/form' -import { getLocaleOnServer, getTranslation } from '@/i18n-config/server' -const Settings = async () => { - const locale = await getLocaleOnServer() - const { t } = await getTranslation(locale, 'dataset-settings') +const Settings = () => { + const { t } = useTranslation('datasetSettings') return (
diff --git a/web/app/components/apps/app-card-skeleton.tsx b/web/app/components/apps/app-card-skeleton.tsx new file mode 100644 index 0000000000..806f19973a --- /dev/null +++ b/web/app/components/apps/app-card-skeleton.tsx @@ -0,0 +1,41 @@ +'use client' + +import * as React from 'react' +import { SkeletonContainer, SkeletonRectangle, SkeletonRow } from '@/app/components/base/skeleton' + +type AppCardSkeletonProps = { + count?: number +} + +/** + * Skeleton placeholder for App cards during loading states. + * Matches the visual layout of AppCard component. + */ +export const AppCardSkeleton = React.memo(({ count = 6 }: AppCardSkeletonProps) => { + return ( + <> + {Array.from({ length: count }).map((_, index) => ( +
+ + + +
+ + +
+ +
+ + +
+ +
+ ))} + + ) +}) + +AppCardSkeleton.displayName = 'AppCardSkeleton' diff --git a/web/app/components/apps/list.tsx b/web/app/components/apps/list.tsx index 003b463595..290a73fc7c 100644 --- a/web/app/components/apps/list.tsx +++ b/web/app/components/apps/list.tsx @@ -27,7 +27,9 @@ import { useGlobalPublicStore } from '@/context/global-public-context' import { CheckModal } from '@/hooks/use-pay' import { useInfiniteAppList } from '@/service/use-apps' import { AppModeEnum } from '@/types/app' +import { cn } from '@/utils/classnames' import AppCard from './app-card' +import { AppCardSkeleton } from './app-card-skeleton' import Empty from './empty' import Footer from './footer' import useAppsQueryState from './hooks/use-apps-query-state' @@ -45,7 +47,7 @@ const List = () => { const { t } = useTranslation() const { systemFeatures } = useGlobalPublicStore() const router = useRouter() - const { isCurrentWorkspaceEditor, isCurrentWorkspaceDatasetOperator } = useAppContext() + const { isCurrentWorkspaceEditor, isCurrentWorkspaceDatasetOperator, isLoadingCurrentWorkspace } = useAppContext() const showTagManagementModal = useTagStore(s => s.showTagManagementModal) const [activeTab, setActiveTab] = useQueryState( 'category', @@ -89,6 +91,7 @@ const List = () => { const { data, isLoading, + isFetching, isFetchingNextPage, fetchNextPage, hasNextPage, @@ -172,6 +175,8 @@ const List = () => { const pages = data?.pages ?? [] const hasAnyApp = (pages[0]?.total ?? 0) > 0 + // Show skeleton during initial load or when refetching with no previous data + const showSkeleton = isLoading || (isFetching && pages.length === 0) return ( <> @@ -205,23 +210,34 @@ const List = () => { />
- {hasAnyApp - ? ( -
- {isCurrentWorkspaceEditor - && } - {pages.map(({ data: apps }) => apps.map(app => ( - - )))} -
- ) - : ( -
- {isCurrentWorkspaceEditor - && } - -
- )} +
+ {(isCurrentWorkspaceEditor || isLoadingCurrentWorkspace) && ( + + )} + {(() => { + if (showSkeleton) + return + + if (hasAnyApp) { + return pages.flatMap(({ data: apps }) => apps).map(app => ( + + )) + } + + // No apps - show empty state + return + })()} +
{isCurrentWorkspaceEditor && (
import('@/app/components/app/create-fro export type CreateAppCardProps = { className?: string + isLoading?: boolean onSuccess?: () => void ref: React.RefObject selectedAppType?: string @@ -33,6 +34,7 @@ export type CreateAppCardProps = { const CreateAppCard = ({ ref, className, + isLoading = false, onSuccess, selectedAppType, }: CreateAppCardProps) => { @@ -56,7 +58,11 @@ const CreateAppCard = ({ return (
{t('createApp', { ns: 'app' })}
diff --git a/web/app/components/base/form/hooks/use-get-form-values.ts b/web/app/components/base/form/hooks/use-get-form-values.ts index 9ea418ea00..3dd2eceb30 100644 --- a/web/app/components/base/form/hooks/use-get-form-values.ts +++ b/web/app/components/base/form/hooks/use-get-form-values.ts @@ -4,7 +4,7 @@ import type { GetValuesOptions, } from '../types' import { useCallback } from 'react' -import { getTransformedValuesWhenSecretInputPristine } from '../utils' +import { getTransformedValuesWhenSecretInputPristine } from '../utils/secret-input' import { useCheckValidated } from './use-check-validated' export const useGetFormValues = (form: AnyFormApi, formSchemas: FormSchema[]) => { diff --git a/web/app/components/base/form/utils/index.ts b/web/app/components/base/form/utils/index.ts deleted file mode 100644 index 0abb8d1ad5..0000000000 --- a/web/app/components/base/form/utils/index.ts +++ /dev/null @@ -1 +0,0 @@ -export * from './secret-input' diff --git a/web/app/components/base/form/utils/zod-submit-validator.ts b/web/app/components/base/form/utils/zod-submit-validator.ts new file mode 100644 index 0000000000..23eacaf8a4 --- /dev/null +++ b/web/app/components/base/form/utils/zod-submit-validator.ts @@ -0,0 +1,22 @@ +import type { ZodSchema } from 'zod' + +type SubmitValidator = ({ value }: { value: T }) => { fields: Record } | undefined + +export const zodSubmitValidator = (schema: ZodSchema): SubmitValidator => { + return ({ value }) => { + const result = schema.safeParse(value) + if (!result.success) { + const fieldErrors: Record = {} + for (const issue of result.error.issues) { + const path = issue.path[0] + if (path === undefined) + continue + const key = String(path) + if (!fieldErrors[key]) + fieldErrors[key] = issue.message + } + return { fields: fieldErrors } + } + return undefined + } +} diff --git a/web/app/components/datasets/create/step-one/components/data-source-type-selector.tsx b/web/app/components/datasets/create/step-one/components/data-source-type-selector.tsx new file mode 100644 index 0000000000..6bdc2ace56 --- /dev/null +++ b/web/app/components/datasets/create/step-one/components/data-source-type-selector.tsx @@ -0,0 +1,97 @@ +'use client' + +import { useCallback, useMemo } from 'react' +import { useTranslation } from 'react-i18next' +import { ENABLE_WEBSITE_FIRECRAWL, ENABLE_WEBSITE_JINAREADER, ENABLE_WEBSITE_WATERCRAWL } from '@/config' +import { DataSourceType } from '@/models/datasets' +import { cn } from '@/utils/classnames' +import s from '../index.module.css' + +type DataSourceTypeSelectorProps = { + currentType: DataSourceType + disabled: boolean + onChange: (type: DataSourceType) => void + onClearPreviews: (type: DataSourceType) => void +} + +type DataSourceLabelKey + = | 'stepOne.dataSourceType.file' + | 'stepOne.dataSourceType.notion' + | 'stepOne.dataSourceType.web' + +type DataSourceOption = { + type: DataSourceType + iconClass?: string + labelKey: DataSourceLabelKey +} + +const DATA_SOURCE_OPTIONS: DataSourceOption[] = [ + { + type: DataSourceType.FILE, + labelKey: 'stepOne.dataSourceType.file', + }, + { + type: DataSourceType.NOTION, + iconClass: s.notion, + labelKey: 'stepOne.dataSourceType.notion', + }, + { + type: DataSourceType.WEB, + iconClass: s.web, + labelKey: 'stepOne.dataSourceType.web', + }, +] + +/** + * Data source type selector component for choosing between file, notion, and web sources. + */ +function DataSourceTypeSelector({ + currentType, + disabled, + onChange, + onClearPreviews, +}: DataSourceTypeSelectorProps) { + const { t } = useTranslation() + + const isWebEnabled = ENABLE_WEBSITE_FIRECRAWL || ENABLE_WEBSITE_JINAREADER || ENABLE_WEBSITE_WATERCRAWL + + const handleTypeChange = useCallback((type: DataSourceType) => { + if (disabled) + return + onChange(type) + onClearPreviews(type) + }, [disabled, onChange, onClearPreviews]) + + const visibleOptions = useMemo(() => DATA_SOURCE_OPTIONS.filter((option) => { + if (option.type === DataSourceType.WEB) + return isWebEnabled + return true + }), [isWebEnabled]) + + return ( +
+ {visibleOptions.map(option => ( +
handleTypeChange(option.type)} + > + + + {t(option.labelKey, { ns: 'datasetCreation' })} + +
+ ))} +
+ ) +} + +export default DataSourceTypeSelector diff --git a/web/app/components/datasets/create/step-one/components/index.ts b/web/app/components/datasets/create/step-one/components/index.ts new file mode 100644 index 0000000000..5271835741 --- /dev/null +++ b/web/app/components/datasets/create/step-one/components/index.ts @@ -0,0 +1,3 @@ +export { default as DataSourceTypeSelector } from './data-source-type-selector' +export { default as NextStepButton } from './next-step-button' +export { default as PreviewPanel } from './preview-panel' diff --git a/web/app/components/datasets/create/step-one/components/next-step-button.tsx b/web/app/components/datasets/create/step-one/components/next-step-button.tsx new file mode 100644 index 0000000000..71e4e87fcf --- /dev/null +++ b/web/app/components/datasets/create/step-one/components/next-step-button.tsx @@ -0,0 +1,30 @@ +'use client' + +import { RiArrowRightLine } from '@remixicon/react' +import { useTranslation } from 'react-i18next' +import Button from '@/app/components/base/button' + +type NextStepButtonProps = { + disabled: boolean + onClick: () => void +} + +/** + * Reusable next step button component for dataset creation flow. + */ +function NextStepButton({ disabled, onClick }: NextStepButtonProps) { + const { t } = useTranslation() + + return ( +
+ +
+ ) +} + +export default NextStepButton diff --git a/web/app/components/datasets/create/step-one/components/preview-panel.tsx b/web/app/components/datasets/create/step-one/components/preview-panel.tsx new file mode 100644 index 0000000000..8ae0b7df55 --- /dev/null +++ b/web/app/components/datasets/create/step-one/components/preview-panel.tsx @@ -0,0 +1,62 @@ +'use client' + +import type { NotionPage } from '@/models/common' +import type { CrawlResultItem } from '@/models/datasets' +import { useTranslation } from 'react-i18next' +import PlanUpgradeModal from '@/app/components/billing/plan-upgrade-modal' +import FilePreview from '../../file-preview' +import NotionPagePreview from '../../notion-page-preview' +import WebsitePreview from '../../website/preview' + +type PreviewPanelProps = { + currentFile: File | undefined + currentNotionPage: NotionPage | undefined + currentWebsite: CrawlResultItem | undefined + notionCredentialId: string + isShowPlanUpgradeModal: boolean + hideFilePreview: () => void + hideNotionPagePreview: () => void + hideWebsitePreview: () => void + hidePlanUpgradeModal: () => void +} + +/** + * Right panel component for displaying file, notion page, or website previews. + */ +function PreviewPanel({ + currentFile, + currentNotionPage, + currentWebsite, + notionCredentialId, + isShowPlanUpgradeModal, + hideFilePreview, + hideNotionPagePreview, + hideWebsitePreview, + hidePlanUpgradeModal, +}: PreviewPanelProps) { + const { t } = useTranslation() + + return ( +
+ {currentFile && } + {currentNotionPage && ( + + )} + {currentWebsite && } + {isShowPlanUpgradeModal && ( + + )} +
+ ) +} + +export default PreviewPanel diff --git a/web/app/components/datasets/create/step-one/hooks/index.ts b/web/app/components/datasets/create/step-one/hooks/index.ts new file mode 100644 index 0000000000..bae5ce4fce --- /dev/null +++ b/web/app/components/datasets/create/step-one/hooks/index.ts @@ -0,0 +1,2 @@ +export { default as usePreviewState } from './use-preview-state' +export type { PreviewActions, PreviewState, UsePreviewStateReturn } from './use-preview-state' diff --git a/web/app/components/datasets/create/step-one/hooks/use-preview-state.ts b/web/app/components/datasets/create/step-one/hooks/use-preview-state.ts new file mode 100644 index 0000000000..3984947ab1 --- /dev/null +++ b/web/app/components/datasets/create/step-one/hooks/use-preview-state.ts @@ -0,0 +1,70 @@ +'use client' + +import type { NotionPage } from '@/models/common' +import type { CrawlResultItem } from '@/models/datasets' +import { useCallback, useState } from 'react' + +export type PreviewState = { + currentFile: File | undefined + currentNotionPage: NotionPage | undefined + currentWebsite: CrawlResultItem | undefined +} + +export type PreviewActions = { + showFilePreview: (file: File) => void + hideFilePreview: () => void + showNotionPagePreview: (page: NotionPage) => void + hideNotionPagePreview: () => void + showWebsitePreview: (website: CrawlResultItem) => void + hideWebsitePreview: () => void +} + +export type UsePreviewStateReturn = PreviewState & PreviewActions + +/** + * Custom hook for managing preview state across different data source types. + * Handles file, notion page, and website preview visibility. + */ +function usePreviewState(): UsePreviewStateReturn { + const [currentFile, setCurrentFile] = useState() + const [currentNotionPage, setCurrentNotionPage] = useState() + const [currentWebsite, setCurrentWebsite] = useState() + + const showFilePreview = useCallback((file: File) => { + setCurrentFile(file) + }, []) + + const hideFilePreview = useCallback(() => { + setCurrentFile(undefined) + }, []) + + const showNotionPagePreview = useCallback((page: NotionPage) => { + setCurrentNotionPage(page) + }, []) + + const hideNotionPagePreview = useCallback(() => { + setCurrentNotionPage(undefined) + }, []) + + const showWebsitePreview = useCallback((website: CrawlResultItem) => { + setCurrentWebsite(website) + }, []) + + const hideWebsitePreview = useCallback(() => { + setCurrentWebsite(undefined) + }, []) + + return { + currentFile, + currentNotionPage, + currentWebsite, + showFilePreview, + hideFilePreview, + showNotionPagePreview, + hideNotionPagePreview, + showWebsitePreview, + hideWebsitePreview, + } +} + +export default usePreviewState diff --git a/web/app/components/datasets/create/step-one/index.spec.tsx b/web/app/components/datasets/create/step-one/index.spec.tsx new file mode 100644 index 0000000000..1ff77dc1f6 --- /dev/null +++ b/web/app/components/datasets/create/step-one/index.spec.tsx @@ -0,0 +1,1204 @@ +import type { DataSourceAuth } from '@/app/components/header/account-setting/data-source-page-new/types' +import type { NotionPage } from '@/models/common' +import type { CrawlOptions, CrawlResultItem, DataSet, FileItem } from '@/models/datasets' +import { act, fireEvent, render, renderHook, screen } from '@testing-library/react' +import { Plan } from '@/app/components/billing/type' +import { DataSourceType } from '@/models/datasets' +import { DataSourceTypeSelector, NextStepButton, PreviewPanel } from './components' +import { usePreviewState } from './hooks' +import StepOne from './index' + +// ========================================== +// Mock External Dependencies +// ========================================== + +// Mock config for website crawl features +vi.mock('@/config', () => ({ + ENABLE_WEBSITE_FIRECRAWL: true, + ENABLE_WEBSITE_JINAREADER: false, + ENABLE_WEBSITE_WATERCRAWL: false, +})) + +// Mock dataset detail context +let mockDatasetDetail: DataSet | undefined +vi.mock('@/context/dataset-detail', () => ({ + useDatasetDetailContextWithSelector: (selector: (state: { dataset: DataSet | undefined }) => DataSet | undefined) => { + return selector({ dataset: mockDatasetDetail }) + }, +})) + +// Mock provider context +let mockPlan = { + type: Plan.professional, + usage: { vectorSpace: 50, buildApps: 0, documentsUploadQuota: 0, vectorStorageQuota: 0 }, + total: { vectorSpace: 100, buildApps: 0, documentsUploadQuota: 0, vectorStorageQuota: 0 }, +} +let mockEnableBilling = false + +vi.mock('@/context/provider-context', () => ({ + useProviderContext: () => ({ + plan: mockPlan, + enableBilling: mockEnableBilling, + }), +})) + +// Mock child components +vi.mock('../file-uploader', () => ({ + default: ({ onPreview, fileList }: { onPreview: (file: File) => void, fileList: FileItem[] }) => ( +
+ {fileList.length} + +
+ ), +})) + +vi.mock('../website', () => ({ + default: ({ onPreview }: { onPreview: (item: CrawlResultItem) => void }) => ( +
+ +
+ ), +})) + +vi.mock('../empty-dataset-creation-modal', () => ({ + default: ({ show, onHide }: { show: boolean, onHide: () => void }) => ( + show + ? ( +
+ +
+ ) + : null + ), +})) + +// NotionConnector is a base component - imported directly without mock +// It only depends on i18n which is globally mocked + +vi.mock('@/app/components/base/notion-page-selector', () => ({ + NotionPageSelector: ({ onPreview }: { onPreview: (page: NotionPage) => void }) => ( +
+ +
+ ), +})) + +vi.mock('@/app/components/billing/vector-space-full', () => ({ + default: () =>
Vector Space Full
, +})) + +vi.mock('@/app/components/billing/plan-upgrade-modal', () => ({ + default: ({ show, onClose }: { show: boolean, onClose: () => void }) => ( + show + ? ( +
+ +
+ ) + : null + ), +})) + +vi.mock('../file-preview', () => ({ + default: ({ file, hidePreview }: { file: File, hidePreview: () => void }) => ( +
+ {file.name} + +
+ ), +})) + +vi.mock('../notion-page-preview', () => ({ + default: ({ currentPage, hidePreview }: { currentPage: NotionPage, hidePreview: () => void }) => ( +
+ {currentPage.page_id} + +
+ ), +})) + +// WebsitePreview is a sibling component without API dependencies - imported directly +// It only depends on i18n which is globally mocked + +vi.mock('./upgrade-card', () => ({ + default: () =>
Upgrade Card
, +})) + +// ========================================== +// Test Data Builders +// ========================================== + +const createMockCustomFile = (overrides: { id?: string, name?: string } = {}) => { + const file = new File(['test content'], overrides.name ?? 'test.txt', { type: 'text/plain' }) + return Object.assign(file, { + id: overrides.id ?? 'uploaded-id', + extension: 'txt', + mime_type: 'text/plain', + created_by: 'user-1', + created_at: Date.now(), + }) +} + +const createMockFileItem = (overrides: Partial = {}): FileItem => ({ + fileID: `file-${Date.now()}`, + file: createMockCustomFile(overrides.file as { id?: string, name?: string }), + progress: 100, + ...overrides, +}) + +const createMockNotionPage = (overrides: Partial = {}): NotionPage => ({ + page_id: `page-${Date.now()}`, + type: 'page', + ...overrides, +} as NotionPage) + +const createMockCrawlResult = (overrides: Partial = {}): CrawlResultItem => ({ + title: 'Test Page', + markdown: 'Test content', + description: 'Test description', + source_url: 'https://example.com', + ...overrides, +}) + +const createMockDataSourceAuth = (overrides: Partial = {}): DataSourceAuth => ({ + credential_id: 'cred-1', + provider: 'notion_datasource', + plugin_id: 'plugin-1', + credentials_list: [{ id: 'cred-1', name: 'Workspace 1' }], + ...overrides, +} as DataSourceAuth) + +const defaultProps = { + dataSourceType: DataSourceType.FILE, + dataSourceTypeDisable: false, + onSetting: vi.fn(), + files: [] as FileItem[], + updateFileList: vi.fn(), + updateFile: vi.fn(), + notionPages: [] as NotionPage[], + notionCredentialId: '', + updateNotionPages: vi.fn(), + updateNotionCredentialId: vi.fn(), + onStepChange: vi.fn(), + changeType: vi.fn(), + websitePages: [] as CrawlResultItem[], + updateWebsitePages: vi.fn(), + onWebsiteCrawlProviderChange: vi.fn(), + onWebsiteCrawlJobIdChange: vi.fn(), + crawlOptions: { + crawl_sub_pages: true, + only_main_content: true, + includes: '', + excludes: '', + limit: 10, + max_depth: '', + use_sitemap: true, + } as CrawlOptions, + onCrawlOptionsChange: vi.fn(), + authedDataSourceList: [] as DataSourceAuth[], +} + +// ========================================== +// usePreviewState Hook Tests +// ========================================== +describe('usePreviewState Hook', () => { + // -------------------------------------------------------------------------- + // Initial State Tests + // -------------------------------------------------------------------------- + describe('Initial State', () => { + it('should initialize with all preview states undefined', () => { + // Arrange & Act + const { result } = renderHook(() => usePreviewState()) + + // Assert + expect(result.current.currentFile).toBeUndefined() + expect(result.current.currentNotionPage).toBeUndefined() + expect(result.current.currentWebsite).toBeUndefined() + }) + }) + + // -------------------------------------------------------------------------- + // File Preview Tests + // -------------------------------------------------------------------------- + describe('File Preview', () => { + it('should show file preview when showFilePreview is called', () => { + // Arrange + const { result } = renderHook(() => usePreviewState()) + const mockFile = new File(['test'], 'test.txt') + + // Act + act(() => { + result.current.showFilePreview(mockFile) + }) + + // Assert + expect(result.current.currentFile).toBe(mockFile) + }) + + it('should hide file preview when hideFilePreview is called', () => { + // Arrange + const { result } = renderHook(() => usePreviewState()) + const mockFile = new File(['test'], 'test.txt') + + act(() => { + result.current.showFilePreview(mockFile) + }) + + // Act + act(() => { + result.current.hideFilePreview() + }) + + // Assert + expect(result.current.currentFile).toBeUndefined() + }) + }) + + // -------------------------------------------------------------------------- + // Notion Page Preview Tests + // -------------------------------------------------------------------------- + describe('Notion Page Preview', () => { + it('should show notion page preview when showNotionPagePreview is called', () => { + // Arrange + const { result } = renderHook(() => usePreviewState()) + const mockPage = createMockNotionPage() + + // Act + act(() => { + result.current.showNotionPagePreview(mockPage) + }) + + // Assert + expect(result.current.currentNotionPage).toBe(mockPage) + }) + + it('should hide notion page preview when hideNotionPagePreview is called', () => { + // Arrange + const { result } = renderHook(() => usePreviewState()) + const mockPage = createMockNotionPage() + + act(() => { + result.current.showNotionPagePreview(mockPage) + }) + + // Act + act(() => { + result.current.hideNotionPagePreview() + }) + + // Assert + expect(result.current.currentNotionPage).toBeUndefined() + }) + }) + + // -------------------------------------------------------------------------- + // Website Preview Tests + // -------------------------------------------------------------------------- + describe('Website Preview', () => { + it('should show website preview when showWebsitePreview is called', () => { + // Arrange + const { result } = renderHook(() => usePreviewState()) + const mockWebsite = createMockCrawlResult() + + // Act + act(() => { + result.current.showWebsitePreview(mockWebsite) + }) + + // Assert + expect(result.current.currentWebsite).toBe(mockWebsite) + }) + + it('should hide website preview when hideWebsitePreview is called', () => { + // Arrange + const { result } = renderHook(() => usePreviewState()) + const mockWebsite = createMockCrawlResult() + + act(() => { + result.current.showWebsitePreview(mockWebsite) + }) + + // Act + act(() => { + result.current.hideWebsitePreview() + }) + + // Assert + expect(result.current.currentWebsite).toBeUndefined() + }) + }) + + // -------------------------------------------------------------------------- + // Callback Stability Tests (Memoization) + // -------------------------------------------------------------------------- + describe('Callback Stability', () => { + it('should maintain stable showFilePreview callback reference', () => { + // Arrange + const { result, rerender } = renderHook(() => usePreviewState()) + const initialCallback = result.current.showFilePreview + + // Act + rerender() + + // Assert + expect(result.current.showFilePreview).toBe(initialCallback) + }) + + it('should maintain stable hideFilePreview callback reference', () => { + // Arrange + const { result, rerender } = renderHook(() => usePreviewState()) + const initialCallback = result.current.hideFilePreview + + // Act + rerender() + + // Assert + expect(result.current.hideFilePreview).toBe(initialCallback) + }) + + it('should maintain stable showNotionPagePreview callback reference', () => { + // Arrange + const { result, rerender } = renderHook(() => usePreviewState()) + const initialCallback = result.current.showNotionPagePreview + + // Act + rerender() + + // Assert + expect(result.current.showNotionPagePreview).toBe(initialCallback) + }) + + it('should maintain stable hideNotionPagePreview callback reference', () => { + // Arrange + const { result, rerender } = renderHook(() => usePreviewState()) + const initialCallback = result.current.hideNotionPagePreview + + // Act + rerender() + + // Assert + expect(result.current.hideNotionPagePreview).toBe(initialCallback) + }) + + it('should maintain stable showWebsitePreview callback reference', () => { + // Arrange + const { result, rerender } = renderHook(() => usePreviewState()) + const initialCallback = result.current.showWebsitePreview + + // Act + rerender() + + // Assert + expect(result.current.showWebsitePreview).toBe(initialCallback) + }) + + it('should maintain stable hideWebsitePreview callback reference', () => { + // Arrange + const { result, rerender } = renderHook(() => usePreviewState()) + const initialCallback = result.current.hideWebsitePreview + + // Act + rerender() + + // Assert + expect(result.current.hideWebsitePreview).toBe(initialCallback) + }) + }) +}) + +// ========================================== +// DataSourceTypeSelector Component Tests +// ========================================== +describe('DataSourceTypeSelector', () => { + const defaultSelectorProps = { + currentType: DataSourceType.FILE, + disabled: false, + onChange: vi.fn(), + onClearPreviews: vi.fn(), + } + + beforeEach(() => { + vi.clearAllMocks() + }) + + // -------------------------------------------------------------------------- + // Rendering Tests + // -------------------------------------------------------------------------- + describe('Rendering', () => { + it('should render all data source options when web is enabled', () => { + // Arrange & Act + render() + + // Assert + expect(screen.getByText('datasetCreation.stepOne.dataSourceType.file')).toBeInTheDocument() + expect(screen.getByText('datasetCreation.stepOne.dataSourceType.notion')).toBeInTheDocument() + expect(screen.getByText('datasetCreation.stepOne.dataSourceType.web')).toBeInTheDocument() + }) + + it('should highlight active type', () => { + // Arrange & Act + const { container } = render( + , + ) + + // Assert - The active item should have the active class + const items = container.querySelectorAll('[class*="dataSourceItem"]') + expect(items.length).toBeGreaterThan(0) + }) + }) + + // -------------------------------------------------------------------------- + // User Interactions Tests + // -------------------------------------------------------------------------- + describe('User Interactions', () => { + it('should call onChange when a type is clicked', () => { + // Arrange + const onChange = vi.fn() + render() + + // Act + fireEvent.click(screen.getByText('datasetCreation.stepOne.dataSourceType.notion')) + + // Assert + expect(onChange).toHaveBeenCalledWith(DataSourceType.NOTION) + }) + + it('should call onClearPreviews when a type is clicked', () => { + // Arrange + const onClearPreviews = vi.fn() + render() + + // Act + fireEvent.click(screen.getByText('datasetCreation.stepOne.dataSourceType.web')) + + // Assert + expect(onClearPreviews).toHaveBeenCalledWith(DataSourceType.WEB) + }) + + it('should not call onChange when disabled', () => { + // Arrange + const onChange = vi.fn() + render() + + // Act + fireEvent.click(screen.getByText('datasetCreation.stepOne.dataSourceType.notion')) + + // Assert + expect(onChange).not.toHaveBeenCalled() + }) + + it('should not call onClearPreviews when disabled', () => { + // Arrange + const onClearPreviews = vi.fn() + render() + + // Act + fireEvent.click(screen.getByText('datasetCreation.stepOne.dataSourceType.notion')) + + // Assert + expect(onClearPreviews).not.toHaveBeenCalled() + }) + }) +}) + +// ========================================== +// NextStepButton Component Tests +// ========================================== +describe('NextStepButton', () => { + beforeEach(() => { + vi.clearAllMocks() + }) + + // -------------------------------------------------------------------------- + // Rendering Tests + // -------------------------------------------------------------------------- + describe('Rendering', () => { + it('should render with correct label', () => { + // Arrange & Act + render() + + // Assert + expect(screen.getByText('datasetCreation.stepOne.button')).toBeInTheDocument() + }) + + it('should render with arrow icon', () => { + // Arrange & Act + const { container } = render() + + // Assert + const svgIcon = container.querySelector('svg') + expect(svgIcon).toBeInTheDocument() + }) + }) + + // -------------------------------------------------------------------------- + // Props Tests + // -------------------------------------------------------------------------- + describe('Props', () => { + it('should be disabled when disabled prop is true', () => { + // Arrange & Act + render() + + // Assert + expect(screen.getByRole('button')).toBeDisabled() + }) + + it('should be enabled when disabled prop is false', () => { + // Arrange & Act + render() + + // Assert + expect(screen.getByRole('button')).not.toBeDisabled() + }) + + it('should call onClick when clicked and not disabled', () => { + // Arrange + const onClick = vi.fn() + render() + + // Act + fireEvent.click(screen.getByRole('button')) + + // Assert + expect(onClick).toHaveBeenCalledTimes(1) + }) + + it('should not call onClick when clicked and disabled', () => { + // Arrange + const onClick = vi.fn() + render() + + // Act + fireEvent.click(screen.getByRole('button')) + + // Assert + expect(onClick).not.toHaveBeenCalled() + }) + }) +}) + +// ========================================== +// PreviewPanel Component Tests +// ========================================== +describe('PreviewPanel', () => { + const defaultPreviewProps = { + currentFile: undefined as File | undefined, + currentNotionPage: undefined as NotionPage | undefined, + currentWebsite: undefined as CrawlResultItem | undefined, + notionCredentialId: 'cred-1', + isShowPlanUpgradeModal: false, + hideFilePreview: vi.fn(), + hideNotionPagePreview: vi.fn(), + hideWebsitePreview: vi.fn(), + hidePlanUpgradeModal: vi.fn(), + } + + beforeEach(() => { + vi.clearAllMocks() + }) + + // -------------------------------------------------------------------------- + // Conditional Rendering Tests + // -------------------------------------------------------------------------- + describe('Conditional Rendering', () => { + it('should not render FilePreview when currentFile is undefined', () => { + // Arrange & Act + render() + + // Assert + expect(screen.queryByTestId('file-preview')).not.toBeInTheDocument() + }) + + it('should render FilePreview when currentFile is defined', () => { + // Arrange + const file = new File(['test'], 'test.txt') + + // Act + render() + + // Assert + expect(screen.getByTestId('file-preview')).toBeInTheDocument() + }) + + it('should not render NotionPagePreview when currentNotionPage is undefined', () => { + // Arrange & Act + render() + + // Assert + expect(screen.queryByTestId('notion-page-preview')).not.toBeInTheDocument() + }) + + it('should render NotionPagePreview when currentNotionPage is defined', () => { + // Arrange + const page = createMockNotionPage() + + // Act + render() + + // Assert + expect(screen.getByTestId('notion-page-preview')).toBeInTheDocument() + }) + + it('should not render WebsitePreview when currentWebsite is undefined', () => { + // Arrange & Act + render() + + // Assert - pagePreview is the title shown in WebsitePreview + expect(screen.queryByText('datasetCreation.stepOne.pagePreview')).not.toBeInTheDocument() + }) + + it('should render WebsitePreview when currentWebsite is defined', () => { + // Arrange + const website = createMockCrawlResult() + + // Act + render() + + // Assert - Check for the preview title and source URL + expect(screen.getByText('datasetCreation.stepOne.pagePreview')).toBeInTheDocument() + expect(screen.getByText(website.source_url)).toBeInTheDocument() + }) + + it('should not render PlanUpgradeModal when isShowPlanUpgradeModal is false', () => { + // Arrange & Act + render() + + // Assert + expect(screen.queryByTestId('plan-upgrade-modal')).not.toBeInTheDocument() + }) + + it('should render PlanUpgradeModal when isShowPlanUpgradeModal is true', () => { + // Arrange & Act + render() + + // Assert + expect(screen.getByTestId('plan-upgrade-modal')).toBeInTheDocument() + }) + }) + + // -------------------------------------------------------------------------- + // Event Handler Tests + // -------------------------------------------------------------------------- + describe('Event Handlers', () => { + it('should call hideFilePreview when file preview close is clicked', () => { + // Arrange + const hideFilePreview = vi.fn() + const file = new File(['test'], 'test.txt') + render() + + // Act + fireEvent.click(screen.getByTestId('hide-file-preview')) + + // Assert + expect(hideFilePreview).toHaveBeenCalledTimes(1) + }) + + it('should call hideNotionPagePreview when notion preview close is clicked', () => { + // Arrange + const hideNotionPagePreview = vi.fn() + const page = createMockNotionPage() + render() + + // Act + fireEvent.click(screen.getByTestId('hide-notion-preview')) + + // Assert + expect(hideNotionPagePreview).toHaveBeenCalledTimes(1) + }) + + it('should call hideWebsitePreview when website preview close is clicked', () => { + // Arrange + const hideWebsitePreview = vi.fn() + const website = createMockCrawlResult() + const { container } = render() + + // Act - Find the close button (div with cursor-pointer class containing the XMarkIcon) + const closeButton = container.querySelector('.cursor-pointer') + expect(closeButton).toBeInTheDocument() + fireEvent.click(closeButton!) + + // Assert + expect(hideWebsitePreview).toHaveBeenCalledTimes(1) + }) + + it('should call hidePlanUpgradeModal when modal close is clicked', () => { + // Arrange + const hidePlanUpgradeModal = vi.fn() + render() + + // Act + fireEvent.click(screen.getByTestId('close-upgrade-modal')) + + // Assert + expect(hidePlanUpgradeModal).toHaveBeenCalledTimes(1) + }) + }) +}) + +// ========================================== +// StepOne Component Tests +// ========================================== +describe('StepOne', () => { + beforeEach(() => { + vi.clearAllMocks() + mockDatasetDetail = undefined + mockPlan = { + type: Plan.professional, + usage: { vectorSpace: 50, buildApps: 0, documentsUploadQuota: 0, vectorStorageQuota: 0 }, + total: { vectorSpace: 100, buildApps: 0, documentsUploadQuota: 0, vectorStorageQuota: 0 }, + } + mockEnableBilling = false + }) + + // -------------------------------------------------------------------------- + // Rendering Tests + // -------------------------------------------------------------------------- + describe('Rendering', () => { + it('should render without crashing', () => { + // Arrange & Act + render() + + // Assert + expect(screen.getByText('datasetCreation.steps.one')).toBeInTheDocument() + }) + + it('should render DataSourceTypeSelector when not editing existing dataset', () => { + // Arrange & Act + render() + + // Assert + expect(screen.getByText('datasetCreation.stepOne.dataSourceType.file')).toBeInTheDocument() + }) + + it('should render FileUploader when dataSourceType is FILE', () => { + // Arrange & Act + render() + + // Assert + expect(screen.getByTestId('file-uploader')).toBeInTheDocument() + }) + + it('should render NotionConnector when dataSourceType is NOTION and not authenticated', () => { + // Arrange & Act + render() + + // Assert - NotionConnector shows sync title and connect button + expect(screen.getByText('datasetCreation.stepOne.notionSyncTitle')).toBeInTheDocument() + expect(screen.getByRole('button', { name: /datasetCreation.stepOne.connect/i })).toBeInTheDocument() + }) + + it('should render NotionPageSelector when dataSourceType is NOTION and authenticated', () => { + // Arrange + const authedDataSourceList = [createMockDataSourceAuth()] + + // Act + render() + + // Assert + expect(screen.getByTestId('notion-page-selector')).toBeInTheDocument() + }) + + it('should render Website when dataSourceType is WEB', () => { + // Arrange & Act + render() + + // Assert + expect(screen.getByTestId('website')).toBeInTheDocument() + }) + + it('should render empty dataset creation link when no datasetId', () => { + // Arrange & Act + render() + + // Assert + expect(screen.getByText('datasetCreation.stepOne.emptyDatasetCreation')).toBeInTheDocument() + }) + + it('should not render empty dataset creation link when datasetId exists', () => { + // Arrange & Act + render() + + // Assert + expect(screen.queryByText('datasetCreation.stepOne.emptyDatasetCreation')).not.toBeInTheDocument() + }) + }) + + // -------------------------------------------------------------------------- + // Props Tests + // -------------------------------------------------------------------------- + describe('Props', () => { + it('should pass files to FileUploader', () => { + // Arrange + const files = [createMockFileItem()] + + // Act + render() + + // Assert + expect(screen.getByTestId('file-count')).toHaveTextContent('1') + }) + + it('should call onSetting when NotionConnector connect button is clicked', () => { + // Arrange + const onSetting = vi.fn() + render() + + // Act - The NotionConnector's button calls onSetting + fireEvent.click(screen.getByRole('button', { name: /datasetCreation.stepOne.connect/i })) + + // Assert + expect(onSetting).toHaveBeenCalledTimes(1) + }) + + it('should call changeType when data source type is changed', () => { + // Arrange + const changeType = vi.fn() + render() + + // Act + fireEvent.click(screen.getByText('datasetCreation.stepOne.dataSourceType.notion')) + + // Assert + expect(changeType).toHaveBeenCalledWith(DataSourceType.NOTION) + }) + }) + + // -------------------------------------------------------------------------- + // State Management Tests + // -------------------------------------------------------------------------- + describe('State Management', () => { + it('should open empty dataset modal when link is clicked', () => { + // Arrange + render() + + // Act + fireEvent.click(screen.getByText('datasetCreation.stepOne.emptyDatasetCreation')) + + // Assert + expect(screen.getByTestId('empty-dataset-modal')).toBeInTheDocument() + }) + + it('should close empty dataset modal when close is clicked', () => { + // Arrange + render() + fireEvent.click(screen.getByText('datasetCreation.stepOne.emptyDatasetCreation')) + + // Act + fireEvent.click(screen.getByTestId('close-modal')) + + // Assert + expect(screen.queryByTestId('empty-dataset-modal')).not.toBeInTheDocument() + }) + }) + + // -------------------------------------------------------------------------- + // Memoization Tests + // -------------------------------------------------------------------------- + describe('Memoization', () => { + it('should correctly compute isNotionAuthed based on authedDataSourceList', () => { + // Arrange - No auth + const { rerender } = render() + // NotionConnector shows the sync title when not authenticated + expect(screen.getByText('datasetCreation.stepOne.notionSyncTitle')).toBeInTheDocument() + + // Act - Add auth + const authedDataSourceList = [createMockDataSourceAuth()] + rerender() + + // Assert + expect(screen.getByTestId('notion-page-selector')).toBeInTheDocument() + }) + + it('should correctly compute fileNextDisabled when files are empty', () => { + // Arrange & Act + render() + + // Assert - Button should be disabled + expect(screen.getByRole('button', { name: /datasetCreation.stepOne.button/i })).toBeDisabled() + }) + + it('should correctly compute fileNextDisabled when files are loaded', () => { + // Arrange + const files = [createMockFileItem()] + + // Act + render() + + // Assert - Button should be enabled + expect(screen.getByRole('button', { name: /datasetCreation.stepOne.button/i })).not.toBeDisabled() + }) + + it('should correctly compute fileNextDisabled when some files are not uploaded', () => { + // Arrange - Create a file item without id (not yet uploaded) + const file = new File(['test'], 'test.txt', { type: 'text/plain' }) + const fileItem: FileItem = { + fileID: 'temp-id', + file: Object.assign(file, { id: undefined, extension: 'txt', mime_type: 'text/plain' }), + progress: 0, + } + + // Act + render() + + // Assert - Button should be disabled + expect(screen.getByRole('button', { name: /datasetCreation.stepOne.button/i })).toBeDisabled() + }) + }) + + // -------------------------------------------------------------------------- + // Callback Tests + // -------------------------------------------------------------------------- + describe('Callbacks', () => { + it('should call onStepChange when next button is clicked with valid files', () => { + // Arrange + const onStepChange = vi.fn() + const files = [createMockFileItem()] + render() + + // Act + fireEvent.click(screen.getByRole('button', { name: /datasetCreation.stepOne.button/i })) + + // Assert + expect(onStepChange).toHaveBeenCalledTimes(1) + }) + + it('should show plan upgrade modal when batch upload not supported and multiple files', () => { + // Arrange + mockEnableBilling = true + mockPlan.type = Plan.sandbox + const files = [createMockFileItem(), createMockFileItem()] + render() + + // Act + fireEvent.click(screen.getByRole('button', { name: /datasetCreation.stepOne.button/i })) + + // Assert + expect(screen.getByTestId('plan-upgrade-modal')).toBeInTheDocument() + }) + + it('should show upgrade card when in sandbox plan with files', () => { + // Arrange + mockEnableBilling = true + mockPlan.type = Plan.sandbox + const files = [createMockFileItem()] + + // Act + render() + + // Assert + expect(screen.getByTestId('upgrade-card')).toBeInTheDocument() + }) + }) + + // -------------------------------------------------------------------------- + // Vector Space Full Tests + // -------------------------------------------------------------------------- + describe('Vector Space Full', () => { + it('should show VectorSpaceFull when vector space is full and billing is enabled', () => { + // Arrange + mockEnableBilling = true + mockPlan.usage.vectorSpace = 100 + mockPlan.total.vectorSpace = 100 + const files = [createMockFileItem()] + + // Act + render() + + // Assert + expect(screen.getByTestId('vector-space-full')).toBeInTheDocument() + }) + + it('should disable next button when vector space is full', () => { + // Arrange + mockEnableBilling = true + mockPlan.usage.vectorSpace = 100 + mockPlan.total.vectorSpace = 100 + const files = [createMockFileItem()] + + // Act + render() + + // Assert + expect(screen.getByRole('button', { name: /datasetCreation.stepOne.button/i })).toBeDisabled() + }) + }) + + // -------------------------------------------------------------------------- + // Preview Integration Tests + // -------------------------------------------------------------------------- + describe('Preview Integration', () => { + it('should show file preview when file preview button is clicked', () => { + // Arrange + render() + + // Act + fireEvent.click(screen.getByTestId('preview-file')) + + // Assert + expect(screen.getByTestId('file-preview')).toBeInTheDocument() + }) + + it('should hide file preview when hide button is clicked', () => { + // Arrange + render() + fireEvent.click(screen.getByTestId('preview-file')) + + // Act + fireEvent.click(screen.getByTestId('hide-file-preview')) + + // Assert + expect(screen.queryByTestId('file-preview')).not.toBeInTheDocument() + }) + + it('should show notion page preview when preview button is clicked', () => { + // Arrange + const authedDataSourceList = [createMockDataSourceAuth()] + render() + + // Act + fireEvent.click(screen.getByTestId('preview-notion')) + + // Assert + expect(screen.getByTestId('notion-page-preview')).toBeInTheDocument() + }) + + it('should show website preview when preview button is clicked', () => { + // Arrange + render() + + // Act + fireEvent.click(screen.getByTestId('preview-website')) + + // Assert - Check for pagePreview title which is shown by WebsitePreview + expect(screen.getByText('datasetCreation.stepOne.pagePreview')).toBeInTheDocument() + }) + }) + + // -------------------------------------------------------------------------- + // Edge Cases + // -------------------------------------------------------------------------- + describe('Edge Cases', () => { + it('should handle empty notionPages array', () => { + // Arrange + const authedDataSourceList = [createMockDataSourceAuth()] + + // Act + render() + + // Assert - Button should be disabled when no pages selected + expect(screen.getByRole('button', { name: /datasetCreation.stepOne.button/i })).toBeDisabled() + }) + + it('should handle empty websitePages array', () => { + // Arrange & Act + render() + + // Assert - Button should be disabled when no pages crawled + expect(screen.getByRole('button', { name: /datasetCreation.stepOne.button/i })).toBeDisabled() + }) + + it('should handle empty authedDataSourceList', () => { + // Arrange & Act + render() + + // Assert - Should show NotionConnector with connect button + expect(screen.getByText('datasetCreation.stepOne.notionSyncTitle')).toBeInTheDocument() + }) + + it('should handle authedDataSourceList without notion credentials', () => { + // Arrange + const authedDataSourceList = [createMockDataSourceAuth({ credentials_list: [] })] + + // Act + render() + + // Assert - Should show NotionConnector with connect button + expect(screen.getByText('datasetCreation.stepOne.notionSyncTitle')).toBeInTheDocument() + }) + + it('should clear previews when switching data source types', () => { + // Arrange + render() + fireEvent.click(screen.getByTestId('preview-file')) + expect(screen.getByTestId('file-preview')).toBeInTheDocument() + + // Act - Change to NOTION + fireEvent.click(screen.getByText('datasetCreation.stepOne.dataSourceType.notion')) + + // Assert - File preview should be cleared + expect(screen.queryByTestId('file-preview')).not.toBeInTheDocument() + }) + }) + + // -------------------------------------------------------------------------- + // Integration Tests + // -------------------------------------------------------------------------- + describe('Integration', () => { + it('should complete file upload flow', () => { + // Arrange + const onStepChange = vi.fn() + const files = [createMockFileItem()] + + // Act + render() + fireEvent.click(screen.getByRole('button', { name: /datasetCreation.stepOne.button/i })) + + // Assert + expect(onStepChange).toHaveBeenCalled() + }) + + it('should complete notion page selection flow', () => { + // Arrange + const onStepChange = vi.fn() + const authedDataSourceList = [createMockDataSourceAuth()] + const notionPages = [createMockNotionPage()] + + // Act + render( + , + ) + fireEvent.click(screen.getByRole('button', { name: /datasetCreation.stepOne.button/i })) + + // Assert + expect(onStepChange).toHaveBeenCalled() + }) + + it('should complete website crawl flow', () => { + // Arrange + const onStepChange = vi.fn() + const websitePages = [createMockCrawlResult()] + + // Act + render( + , + ) + fireEvent.click(screen.getByRole('button', { name: /datasetCreation.stepOne.button/i })) + + // Assert + expect(onStepChange).toHaveBeenCalled() + }) + }) +}) diff --git a/web/app/components/datasets/create/step-one/index.tsx b/web/app/components/datasets/create/step-one/index.tsx index 5c74e69e7e..a86c9d86c2 100644 --- a/web/app/components/datasets/create/step-one/index.tsx +++ b/web/app/components/datasets/create/step-one/index.tsx @@ -1,29 +1,25 @@ 'use client' + import type { DataSourceAuth } from '@/app/components/header/account-setting/data-source-page-new/types' import type { DataSourceProvider, NotionPage } from '@/models/common' import type { CrawlOptions, CrawlResultItem, FileItem } from '@/models/datasets' -import { RiArrowRightLine, RiFolder6Line } from '@remixicon/react' +import { RiFolder6Line } from '@remixicon/react' import { useBoolean } from 'ahooks' -import * as React from 'react' -import { useCallback, useMemo, useState } from 'react' +import { useCallback, useMemo } from 'react' import { useTranslation } from 'react-i18next' -import Button from '@/app/components/base/button' import NotionConnector from '@/app/components/base/notion-connector' import { NotionPageSelector } from '@/app/components/base/notion-page-selector' -import PlanUpgradeModal from '@/app/components/billing/plan-upgrade-modal' import { Plan } from '@/app/components/billing/type' import VectorSpaceFull from '@/app/components/billing/vector-space-full' -import { ENABLE_WEBSITE_FIRECRAWL, ENABLE_WEBSITE_JINAREADER, ENABLE_WEBSITE_WATERCRAWL } from '@/config' import { useDatasetDetailContextWithSelector } from '@/context/dataset-detail' import { useProviderContext } from '@/context/provider-context' import { DataSourceType } from '@/models/datasets' import { cn } from '@/utils/classnames' import EmptyDatasetCreationModal from '../empty-dataset-creation-modal' -import FilePreview from '../file-preview' import FileUploader from '../file-uploader' -import NotionPagePreview from '../notion-page-preview' import Website from '../website' -import WebsitePreview from '../website/preview' +import { DataSourceTypeSelector, NextStepButton, PreviewPanel } from './components' +import { usePreviewState } from './hooks' import s from './index.module.css' import UpgradeCard from './upgrade-card' @@ -50,6 +46,24 @@ type IStepOneProps = { authedDataSourceList: DataSourceAuth[] } +// Helper function to check if notion is authenticated +function checkNotionAuth(authedDataSourceList: DataSourceAuth[]): boolean { + const notionSource = authedDataSourceList.find(item => item.provider === 'notion_datasource') + return Boolean(notionSource && notionSource.credentials_list.length > 0) +} + +// Helper function to get notion credential list +function getNotionCredentialList(authedDataSourceList: DataSourceAuth[]) { + return authedDataSourceList.find(item => item.provider === 'notion_datasource')?.credentials_list || [] +} + +// Lookup table for checking multiple items by data source type +const MULTIPLE_ITEMS_CHECK: Record boolean> = { + [DataSourceType.FILE]: ({ files }) => files.length > 1, + [DataSourceType.NOTION]: ({ notionPages }) => notionPages.length > 1, + [DataSourceType.WEB]: ({ websitePages }) => websitePages.length > 1, +} + const StepOne = ({ datasetId, dataSourceType: inCreatePageDataSourceType, @@ -72,76 +86,47 @@ const StepOne = ({ onCrawlOptionsChange, authedDataSourceList, }: IStepOneProps) => { - const dataset = useDatasetDetailContextWithSelector(state => state.dataset) - const [showModal, setShowModal] = useState(false) - const [currentFile, setCurrentFile] = useState() - const [currentNotionPage, setCurrentNotionPage] = useState() - const [currentWebsite, setCurrentWebsite] = useState() const { t } = useTranslation() + const dataset = useDatasetDetailContextWithSelector(state => state.dataset) + const { plan, enableBilling } = useProviderContext() - const modalShowHandle = () => setShowModal(true) - const modalCloseHandle = () => setShowModal(false) + // Preview state management + const { + currentFile, + currentNotionPage, + currentWebsite, + showFilePreview, + hideFilePreview, + showNotionPagePreview, + hideNotionPagePreview, + showWebsitePreview, + hideWebsitePreview, + } = usePreviewState() - const updateCurrentFile = useCallback((file: File) => { - setCurrentFile(file) - }, []) + // Empty dataset modal state + const [showModal, { setTrue: openModal, setFalse: closeModal }] = useBoolean(false) - const hideFilePreview = useCallback(() => { - setCurrentFile(undefined) - }, []) - - const updateCurrentPage = useCallback((page: NotionPage) => { - setCurrentNotionPage(page) - }, []) - - const hideNotionPagePreview = useCallback(() => { - setCurrentNotionPage(undefined) - }, []) - - const updateWebsite = useCallback((website: CrawlResultItem) => { - setCurrentWebsite(website) - }, []) - - const hideWebsitePreview = useCallback(() => { - setCurrentWebsite(undefined) - }, []) + // Plan upgrade modal state + const [isShowPlanUpgradeModal, { setTrue: showPlanUpgradeModal, setFalse: hidePlanUpgradeModal }] = useBoolean(false) + // Computed values const shouldShowDataSourceTypeList = !datasetId || (datasetId && !dataset?.data_source_type) const isInCreatePage = shouldShowDataSourceTypeList - const dataSourceType = isInCreatePage ? inCreatePageDataSourceType : dataset?.data_source_type - const { plan, enableBilling } = useProviderContext() - const allFileLoaded = (files.length > 0 && files.every(file => file.file.id)) - const hasNotin = notionPages.length > 0 + // Default to FILE type when no type is provided from either source + const dataSourceType = isInCreatePage + ? (inCreatePageDataSourceType ?? DataSourceType.FILE) + : (dataset?.data_source_type ?? DataSourceType.FILE) + + const allFileLoaded = files.length > 0 && files.every(file => file.file.id) + const hasNotion = notionPages.length > 0 const isVectorSpaceFull = plan.usage.vectorSpace >= plan.total.vectorSpace - const isShowVectorSpaceFull = (allFileLoaded || hasNotin) && isVectorSpaceFull && enableBilling + const isShowVectorSpaceFull = (allFileLoaded || hasNotion) && isVectorSpaceFull && enableBilling const supportBatchUpload = !enableBilling || plan.type !== Plan.sandbox - const notSupportBatchUpload = !supportBatchUpload - const [isShowPlanUpgradeModal, { - setTrue: showPlanUpgradeModal, - setFalse: hidePlanUpgradeModal, - }] = useBoolean(false) - const onStepChange = useCallback(() => { - if (notSupportBatchUpload) { - let isMultiple = false - if (dataSourceType === DataSourceType.FILE && files.length > 1) - isMultiple = true + const isNotionAuthed = useMemo(() => checkNotionAuth(authedDataSourceList), [authedDataSourceList]) + const notionCredentialList = useMemo(() => getNotionCredentialList(authedDataSourceList), [authedDataSourceList]) - if (dataSourceType === DataSourceType.NOTION && notionPages.length > 1) - isMultiple = true - - if (dataSourceType === DataSourceType.WEB && websitePages.length > 1) - isMultiple = true - - if (isMultiple) { - showPlanUpgradeModal() - return - } - } - doOnStepChange() - }, [dataSourceType, doOnStepChange, files.length, notSupportBatchUpload, notionPages.length, showPlanUpgradeModal, websitePages.length]) - - const nextDisabled = useMemo(() => { + const fileNextDisabled = useMemo(() => { if (!files.length) return true if (files.some(file => !file.file.id)) @@ -149,109 +134,50 @@ const StepOne = ({ return isShowVectorSpaceFull }, [files, isShowVectorSpaceFull]) - const isNotionAuthed = useMemo(() => { - if (!authedDataSourceList) - return false - const notionSource = authedDataSourceList.find(item => item.provider === 'notion_datasource') - if (!notionSource) - return false - return notionSource.credentials_list.length > 0 - }, [authedDataSourceList]) + // Clear previews when switching data source type + const handleClearPreviews = useCallback((newType: DataSourceType) => { + if (newType !== DataSourceType.FILE) + hideFilePreview() + if (newType !== DataSourceType.NOTION) + hideNotionPagePreview() + if (newType !== DataSourceType.WEB) + hideWebsitePreview() + }, [hideFilePreview, hideNotionPagePreview, hideWebsitePreview]) - const notionCredentialList = useMemo(() => { - return authedDataSourceList.find(item => item.provider === 'notion_datasource')?.credentials_list || [] - }, [authedDataSourceList]) + // Handle step change with batch upload check + const onStepChange = useCallback(() => { + if (!supportBatchUpload && dataSourceType) { + const checkFn = MULTIPLE_ITEMS_CHECK[dataSourceType] + if (checkFn?.({ files, notionPages, websitePages })) { + showPlanUpgradeModal() + return + } + } + doOnStepChange() + }, [dataSourceType, doOnStepChange, files, supportBatchUpload, notionPages, showPlanUpgradeModal, websitePages]) return (
+ {/* Left Panel - Form */}
- { - shouldShowDataSourceTypeList && ( + {shouldShowDataSourceTypeList && ( + <>
{t('steps.one', { ns: 'datasetCreation' })}
- ) - } - { - shouldShowDataSourceTypeList && ( -
-
{ - if (dataSourceTypeDisable) - return - changeType(DataSourceType.FILE) - hideNotionPagePreview() - hideWebsitePreview() - }} - > - - - {t('stepOne.dataSourceType.file', { ns: 'datasetCreation' })} - -
-
{ - if (dataSourceTypeDisable) - return - changeType(DataSourceType.NOTION) - hideFilePreview() - hideWebsitePreview() - }} - > - - - {t('stepOne.dataSourceType.notion', { ns: 'datasetCreation' })} - -
- {(ENABLE_WEBSITE_FIRECRAWL || ENABLE_WEBSITE_JINAREADER || ENABLE_WEBSITE_WATERCRAWL) && ( -
{ - if (dataSourceTypeDisable) - return - changeType(DataSourceType.WEB) - hideFilePreview() - hideNotionPagePreview() - }} - > - - - {t('stepOne.dataSourceType.web', { ns: 'datasetCreation' })} - -
- )} -
- ) - } + + + )} + + {/* File Data Source */} {dataSourceType === DataSourceType.FILE && ( <> {isShowVectorSpaceFull && ( @@ -268,24 +194,17 @@ const StepOne = ({
)} -
- -
- { - enableBilling && plan.type === Plan.sandbox && files.length > 0 && ( -
-
- -
- ) - } + + {enableBilling && plan.type === Plan.sandbox && files.length > 0 && ( +
+
+ +
+ )} )} + + {/* Notion Data Source */} {dataSourceType === DataSourceType.NOTION && ( <> {!isNotionAuthed && } @@ -295,7 +214,7 @@ const StepOne = ({ page.page_id)} onSelect={updateNotionPages} - onPreview={updateCurrentPage} + onPreview={showNotionPagePreview} credentialList={notionCredentialList} onSelectCredential={updateNotionCredentialId} datasetId={datasetId} @@ -306,23 +225,21 @@ const StepOne = ({
)} -
- -
+ )} )} + + {/* Web Data Source */} {dataSourceType === DataSourceType.WEB && ( <>
)} -
- -
+ )} + + {/* Empty Dataset Creation Link */} {!datasetId && ( <>
- + {t('stepOne.emptyDatasetCreation', { ns: 'datasetCreation' })} )}
- +
-
- {currentFile && } - {currentNotionPage && ( - - )} - {currentWebsite && } - {isShowPlanUpgradeModal && ( - - )} -
+ + {/* Right Panel - Preview */} +
) diff --git a/web/app/components/datasets/list/dataset-card/components/corner-labels.tsx b/web/app/components/datasets/list/dataset-card/components/corner-labels.tsx new file mode 100644 index 0000000000..03ca543ee7 --- /dev/null +++ b/web/app/components/datasets/list/dataset-card/components/corner-labels.tsx @@ -0,0 +1,36 @@ +import type { DataSet } from '@/models/datasets' +import * as React from 'react' +import { useTranslation } from 'react-i18next' +import CornerLabel from '@/app/components/base/corner-label' + +type CornerLabelsProps = { + dataset: DataSet +} + +const CornerLabels = ({ dataset }: CornerLabelsProps) => { + const { t } = useTranslation() + + if (!dataset.embedding_available) { + return ( + + ) + } + + if (dataset.runtime_mode === 'rag_pipeline') { + return ( + + ) + } + + return null +} + +export default React.memo(CornerLabels) diff --git a/web/app/components/datasets/list/dataset-card/components/dataset-card-footer.tsx b/web/app/components/datasets/list/dataset-card/components/dataset-card-footer.tsx new file mode 100644 index 0000000000..854f34f49c --- /dev/null +++ b/web/app/components/datasets/list/dataset-card/components/dataset-card-footer.tsx @@ -0,0 +1,62 @@ +import type { DataSet } from '@/models/datasets' +import { RiFileTextFill, RiRobot2Fill } from '@remixicon/react' +import * as React from 'react' +import { useMemo } from 'react' +import { useTranslation } from 'react-i18next' +import Tooltip from '@/app/components/base/tooltip' +import { useFormatTimeFromNow } from '@/hooks/use-format-time-from-now' +import { cn } from '@/utils/classnames' + +const EXTERNAL_PROVIDER = 'external' + +type DatasetCardFooterProps = { + dataset: DataSet +} + +const DatasetCardFooter = ({ dataset }: DatasetCardFooterProps) => { + const { t } = useTranslation() + const { formatTimeFromNow } = useFormatTimeFromNow() + const isExternalProvider = dataset.provider === EXTERNAL_PROVIDER + + const documentCount = useMemo(() => { + const availableDocCount = dataset.total_available_documents ?? 0 + if (availableDocCount < dataset.document_count) + return `${availableDocCount} / ${dataset.document_count}` + return `${dataset.document_count}` + }, [dataset.document_count, dataset.total_available_documents]) + + const documentCountTooltip = useMemo(() => { + const availableDocCount = dataset.total_available_documents ?? 0 + if (availableDocCount < dataset.document_count) + return t('partialEnabled', { ns: 'dataset', count: dataset.document_count, num: availableDocCount }) + return t('docAllEnabled', { ns: 'dataset', count: availableDocCount }) + }, [t, dataset.document_count, dataset.total_available_documents]) + + return ( +
+ +
+ + {documentCount} +
+ + {!isExternalProvider && ( + +
+ + {dataset.app_count} +
+ + )} + / + {`${t('updated', { ns: 'dataset' })} ${formatTimeFromNow(dataset.updated_at * 1000)}`} +
+ ) +} + +export default React.memo(DatasetCardFooter) diff --git a/web/app/components/datasets/list/dataset-card/components/dataset-card-header.tsx b/web/app/components/datasets/list/dataset-card/components/dataset-card-header.tsx new file mode 100644 index 0000000000..abe7595e14 --- /dev/null +++ b/web/app/components/datasets/list/dataset-card/components/dataset-card-header.tsx @@ -0,0 +1,148 @@ +import type { DataSet } from '@/models/datasets' +import * as React from 'react' +import { useMemo } from 'react' +import { useTranslation } from 'react-i18next' +import AppIcon from '@/app/components/base/app-icon' +import { useFormatTimeFromNow } from '@/hooks/use-format-time-from-now' +import { useKnowledge } from '@/hooks/use-knowledge' +import { DOC_FORM_ICON_WITH_BG, DOC_FORM_TEXT } from '@/models/datasets' +import { cn } from '@/utils/classnames' + +const EXTERNAL_PROVIDER = 'external' + +type DatasetCardHeaderProps = { + dataset: DataSet +} + +// DocModeInfo component - placed before usage +type DocModeInfoProps = { + dataset: DataSet + isExternalProvider: boolean + isShowDocModeInfo: boolean +} + +const DocModeInfo = ({ + dataset, + isExternalProvider, + isShowDocModeInfo, +}: DocModeInfoProps) => { + const { t } = useTranslation() + const { formatIndexingTechniqueAndMethod } = useKnowledge() + + if (isExternalProvider) { + return ( +
+ {t('externalKnowledgeBase', { ns: 'dataset' })} +
+ ) + } + + if (!isShowDocModeInfo) + return null + + const indexingText = dataset.indexing_technique + ? formatIndexingTechniqueAndMethod( + dataset.indexing_technique as 'economy' | 'high_quality', + dataset.retrieval_model_dict?.search_method as Parameters[1], + ) + : '' + + return ( +
+ {dataset.doc_form && ( + + {t(`chunkingMode.${DOC_FORM_TEXT[dataset.doc_form]}`, { ns: 'dataset' })} + + )} + {dataset.indexing_technique && indexingText && ( + + {indexingText} + + )} + {dataset.is_multimodal && ( + + {t('multimodal', { ns: 'dataset' })} + + )} +
+ ) +} + +// Main DatasetCardHeader component +const DatasetCardHeader = ({ dataset }: DatasetCardHeaderProps) => { + const { t } = useTranslation() + const { formatTimeFromNow } = useFormatTimeFromNow() + + const isExternalProvider = dataset.provider === EXTERNAL_PROVIDER + + const isShowChunkingModeIcon = dataset.doc_form && (dataset.runtime_mode !== 'rag_pipeline' || dataset.is_published) + const isShowDocModeInfo = Boolean( + dataset.doc_form + && dataset.indexing_technique + && dataset.retrieval_model_dict?.search_method + && (dataset.runtime_mode !== 'rag_pipeline' || dataset.is_published), + ) + + const chunkingModeIcon = dataset.doc_form ? DOC_FORM_ICON_WITH_BG[dataset.doc_form] : React.Fragment + const Icon = isExternalProvider ? DOC_FORM_ICON_WITH_BG.external : chunkingModeIcon + + const iconInfo = useMemo(() => dataset.icon_info || { + icon: '📙', + icon_type: 'emoji' as const, + icon_background: '#FFF4ED', + icon_url: '', + }, [dataset.icon_info]) + + const editTimeText = useMemo( + () => `${t('segment.editedAt', { ns: 'datasetDocuments' })} ${formatTimeFromNow(dataset.updated_at * 1000)}`, + [t, dataset.updated_at, formatTimeFromNow], + ) + + return ( +
+
+ + {(isShowChunkingModeIcon || isExternalProvider) && ( +
+ +
+ )} +
+
+
+ {dataset.name} +
+
+
{dataset.author_name}
+
·
+
{editTimeText}
+
+ +
+
+ ) +} + +export default React.memo(DatasetCardHeader) diff --git a/web/app/components/datasets/list/dataset-card/components/dataset-card-modals.tsx b/web/app/components/datasets/list/dataset-card/components/dataset-card-modals.tsx new file mode 100644 index 0000000000..8162bc94c4 --- /dev/null +++ b/web/app/components/datasets/list/dataset-card/components/dataset-card-modals.tsx @@ -0,0 +1,55 @@ +import type { DataSet } from '@/models/datasets' +import * as React from 'react' +import { useTranslation } from 'react-i18next' +import Confirm from '@/app/components/base/confirm' +import RenameDatasetModal from '../../../rename-modal' + +type ModalState = { + showRenameModal: boolean + showConfirmDelete: boolean + confirmMessage: string +} + +type DatasetCardModalsProps = { + dataset: DataSet + modalState: ModalState + onCloseRename: () => void + onCloseConfirm: () => void + onConfirmDelete: () => void + onSuccess?: () => void +} + +const DatasetCardModals = ({ + dataset, + modalState, + onCloseRename, + onCloseConfirm, + onConfirmDelete, + onSuccess, +}: DatasetCardModalsProps) => { + const { t } = useTranslation() + + return ( + <> + {modalState.showRenameModal && ( + + )} + {modalState.showConfirmDelete && ( + + )} + + ) +} + +export default React.memo(DatasetCardModals) diff --git a/web/app/components/datasets/list/dataset-card/components/description.tsx b/web/app/components/datasets/list/dataset-card/components/description.tsx new file mode 100644 index 0000000000..79604e92ab --- /dev/null +++ b/web/app/components/datasets/list/dataset-card/components/description.tsx @@ -0,0 +1,18 @@ +import type { DataSet } from '@/models/datasets' +import * as React from 'react' +import { cn } from '@/utils/classnames' + +type DescriptionProps = { + dataset: DataSet +} + +const Description = ({ dataset }: DescriptionProps) => ( +
+ {dataset.description} +
+) + +export default React.memo(Description) diff --git a/web/app/components/datasets/list/dataset-card/components/operations-popover.tsx b/web/app/components/datasets/list/dataset-card/components/operations-popover.tsx new file mode 100644 index 0000000000..80ae2fb7a1 --- /dev/null +++ b/web/app/components/datasets/list/dataset-card/components/operations-popover.tsx @@ -0,0 +1,52 @@ +import type { DataSet } from '@/models/datasets' +import { RiMoreFill } from '@remixicon/react' +import * as React from 'react' +import CustomPopover from '@/app/components/base/popover' +import { cn } from '@/utils/classnames' +import Operations from '../operations' + +type OperationsPopoverProps = { + dataset: DataSet + isCurrentWorkspaceDatasetOperator: boolean + openRenameModal: () => void + handleExportPipeline: (include?: boolean) => void + detectIsUsedByApp: () => void +} + +const OperationsPopover = ({ + dataset, + isCurrentWorkspaceDatasetOperator, + openRenameModal, + handleExportPipeline, + detectIsUsedByApp, +}: OperationsPopoverProps) => ( +
+ + )} + className="z-20 min-w-[186px]" + popupClassName="rounded-xl bg-none shadow-none ring-0 min-w-[186px]" + position="br" + trigger="click" + btnElement={( +
+ +
+ )} + btnClassName={open => + cn( + 'size-9 cursor-pointer justify-center rounded-[10px] border-[0.5px] border-components-actionbar-border bg-components-actionbar-bg p-0 shadow-lg shadow-shadow-shadow-5 ring-[2px] ring-inset ring-components-actionbar-bg hover:border-components-actionbar-border', + open ? 'border-components-actionbar-border bg-state-base-hover' : '', + )} + /> +
+) + +export default React.memo(OperationsPopover) diff --git a/web/app/components/datasets/list/dataset-card/components/tag-area.tsx b/web/app/components/datasets/list/dataset-card/components/tag-area.tsx new file mode 100644 index 0000000000..f55a064387 --- /dev/null +++ b/web/app/components/datasets/list/dataset-card/components/tag-area.tsx @@ -0,0 +1,55 @@ +import type { Tag } from '@/app/components/base/tag-management/constant' +import type { DataSet } from '@/models/datasets' +import * as React from 'react' +import TagSelector from '@/app/components/base/tag-management/selector' +import { cn } from '@/utils/classnames' + +type TagAreaProps = { + dataset: DataSet + tags: Tag[] + setTags: (tags: Tag[]) => void + onSuccess?: () => void + isHoveringTagSelector: boolean + onClick: (e: React.MouseEvent) => void +} + +const TagArea = React.forwardRef(({ + dataset, + tags, + setTags, + onSuccess, + isHoveringTagSelector, + onClick, +}, ref) => ( +
+
0 && 'visible', + )} + > + tag.id)} + selectedTags={tags} + onCacheUpdate={setTags} + onChange={onSuccess} + /> +
+
+
+)) +TagArea.displayName = 'TagArea' + +export default TagArea diff --git a/web/app/components/datasets/list/dataset-card/hooks/use-dataset-card-state.ts b/web/app/components/datasets/list/dataset-card/hooks/use-dataset-card-state.ts new file mode 100644 index 0000000000..ad68a1df1c --- /dev/null +++ b/web/app/components/datasets/list/dataset-card/hooks/use-dataset-card-state.ts @@ -0,0 +1,138 @@ +import type { Tag } from '@/app/components/base/tag-management/constant' +import type { DataSet } from '@/models/datasets' +import { useCallback, useEffect, useState } from 'react' +import { useTranslation } from 'react-i18next' +import Toast from '@/app/components/base/toast' +import { useCheckDatasetUsage, useDeleteDataset } from '@/service/use-dataset-card' +import { useExportPipelineDSL } from '@/service/use-pipeline' + +type ModalState = { + showRenameModal: boolean + showConfirmDelete: boolean + confirmMessage: string +} + +type UseDatasetCardStateOptions = { + dataset: DataSet + onSuccess?: () => void +} + +export const useDatasetCardState = ({ dataset, onSuccess }: UseDatasetCardStateOptions) => { + const { t } = useTranslation() + const [tags, setTags] = useState(dataset.tags) + + useEffect(() => { + setTags(dataset.tags) + }, [dataset.tags]) + + // Modal state + const [modalState, setModalState] = useState({ + showRenameModal: false, + showConfirmDelete: false, + confirmMessage: '', + }) + + // Export state + const [exporting, setExporting] = useState(false) + + // Modal handlers + const openRenameModal = useCallback(() => { + setModalState(prev => ({ ...prev, showRenameModal: true })) + }, []) + + const closeRenameModal = useCallback(() => { + setModalState(prev => ({ ...prev, showRenameModal: false })) + }, []) + + const closeConfirmDelete = useCallback(() => { + setModalState(prev => ({ ...prev, showConfirmDelete: false })) + }, []) + + // API mutations + const { mutateAsync: checkUsage } = useCheckDatasetUsage() + const { mutateAsync: deleteDatasetMutation } = useDeleteDataset() + const { mutateAsync: exportPipelineConfig } = useExportPipelineDSL() + + // Export pipeline handler + const handleExportPipeline = useCallback(async (include: boolean = false) => { + const { pipeline_id, name } = dataset + if (!pipeline_id || exporting) + return + + try { + setExporting(true) + const { data } = await exportPipelineConfig({ + pipelineId: pipeline_id, + include, + }) + const a = document.createElement('a') + const file = new Blob([data], { type: 'application/yaml' }) + const url = URL.createObjectURL(file) + a.href = url + a.download = `${name}.pipeline` + a.click() + URL.revokeObjectURL(url) + } + catch { + Toast.notify({ type: 'error', message: t('exportFailed', { ns: 'app' }) }) + } + finally { + setExporting(false) + } + }, [dataset, exportPipelineConfig, exporting, t]) + + // Delete flow handlers + const detectIsUsedByApp = useCallback(async () => { + try { + const { is_using: isUsedByApp } = await checkUsage(dataset.id) + const message = isUsedByApp + ? t('datasetUsedByApp', { ns: 'dataset' })! + : t('deleteDatasetConfirmContent', { ns: 'dataset' })! + setModalState(prev => ({ + ...prev, + confirmMessage: message, + showConfirmDelete: true, + })) + } + catch (e: unknown) { + if (e instanceof Response) { + const res = await e.json() + Toast.notify({ type: 'error', message: res?.message || 'Unknown error' }) + } + else { + Toast.notify({ type: 'error', message: (e as Error)?.message || 'Unknown error' }) + } + } + }, [dataset.id, checkUsage, t]) + + const onConfirmDelete = useCallback(async () => { + try { + await deleteDatasetMutation(dataset.id) + Toast.notify({ type: 'success', message: t('datasetDeleted', { ns: 'dataset' }) }) + onSuccess?.() + } + finally { + closeConfirmDelete() + } + }, [dataset.id, deleteDatasetMutation, onSuccess, t, closeConfirmDelete]) + + return { + // Tag state + tags, + setTags, + + // Modal state + modalState, + openRenameModal, + closeRenameModal, + closeConfirmDelete, + + // Export state + exporting, + + // Handlers + handleExportPipeline, + detectIsUsedByApp, + onConfirmDelete, + } +} diff --git a/web/app/components/datasets/list/dataset-card/index.tsx b/web/app/components/datasets/list/dataset-card/index.tsx index 99404b0454..85dba7e8ff 100644 --- a/web/app/components/datasets/list/dataset-card/index.tsx +++ b/web/app/components/datasets/list/dataset-card/index.tsx @@ -1,28 +1,17 @@ 'use client' -import type { Tag } from '@/app/components/base/tag-management/constant' import type { DataSet } from '@/models/datasets' -import { RiFileTextFill, RiMoreFill, RiRobot2Fill } from '@remixicon/react' import { useHover } from 'ahooks' import { useRouter } from 'next/navigation' -import * as React from 'react' -import { useCallback, useEffect, useMemo, useRef, useState } from 'react' -import { useTranslation } from 'react-i18next' -import AppIcon from '@/app/components/base/app-icon' -import Confirm from '@/app/components/base/confirm' -import CornerLabel from '@/app/components/base/corner-label' -import CustomPopover from '@/app/components/base/popover' -import TagSelector from '@/app/components/base/tag-management/selector' -import Toast from '@/app/components/base/toast' -import Tooltip from '@/app/components/base/tooltip' +import { useMemo, useRef } from 'react' import { useSelector as useAppContextWithSelector } from '@/context/app-context' -import { useFormatTimeFromNow } from '@/hooks/use-format-time-from-now' -import { useKnowledge } from '@/hooks/use-knowledge' -import { DOC_FORM_ICON_WITH_BG, DOC_FORM_TEXT } from '@/models/datasets' -import { checkIsUsedInApp, deleteDataset } from '@/service/datasets' -import { useExportPipelineDSL } from '@/service/use-pipeline' -import { cn } from '@/utils/classnames' -import RenameDatasetModal from '../../rename-modal' -import Operations from './operations' +import CornerLabels from './components/corner-labels' +import DatasetCardFooter from './components/dataset-card-footer' +import DatasetCardHeader from './components/dataset-card-header' +import DatasetCardModals from './components/dataset-card-modals' +import Description from './components/description' +import OperationsPopover from './components/operations-popover' +import TagArea from './components/tag-area' +import { useDatasetCardState } from './hooks/use-dataset-card-state' const EXTERNAL_PROVIDER = 'external' @@ -35,320 +24,80 @@ const DatasetCard = ({ dataset, onSuccess, }: DatasetCardProps) => { - const { t } = useTranslation() const { push } = useRouter() const isCurrentWorkspaceDatasetOperator = useAppContextWithSelector(state => state.isCurrentWorkspaceDatasetOperator) - const [tags, setTags] = useState(dataset.tags) const tagSelectorRef = useRef(null) const isHoveringTagSelector = useHover(tagSelectorRef) - const [showRenameModal, setShowRenameModal] = useState(false) - const [showConfirmDelete, setShowConfirmDelete] = useState(false) - const [confirmMessage, setConfirmMessage] = useState('') - const [exporting, setExporting] = useState(false) + const { + tags, + setTags, + modalState, + openRenameModal, + closeRenameModal, + closeConfirmDelete, + handleExportPipeline, + detectIsUsedByApp, + onConfirmDelete, + } = useDatasetCardState({ dataset, onSuccess }) - const isExternalProvider = useMemo(() => { - return dataset.provider === EXTERNAL_PROVIDER - }, [dataset.provider]) + const isExternalProvider = dataset.provider === EXTERNAL_PROVIDER const isPipelineUnpublished = useMemo(() => { return dataset.runtime_mode === 'rag_pipeline' && !dataset.is_published }, [dataset.runtime_mode, dataset.is_published]) - const isShowChunkingModeIcon = useMemo(() => { - return dataset.doc_form && (dataset.runtime_mode !== 'rag_pipeline' || dataset.is_published) - }, [dataset.doc_form, dataset.runtime_mode, dataset.is_published]) - const isShowDocModeInfo = useMemo(() => { - return dataset.doc_form && dataset.indexing_technique && dataset.retrieval_model_dict?.search_method && (dataset.runtime_mode !== 'rag_pipeline' || dataset.is_published) - }, [dataset.doc_form, dataset.indexing_technique, dataset.retrieval_model_dict?.search_method, dataset.runtime_mode, dataset.is_published]) - const chunkingModeIcon = dataset.doc_form ? DOC_FORM_ICON_WITH_BG[dataset.doc_form] : React.Fragment - const Icon = isExternalProvider ? DOC_FORM_ICON_WITH_BG.external : chunkingModeIcon - const iconInfo = dataset.icon_info || { - icon: '📙', - icon_type: 'emoji', - icon_background: '#FFF4ED', - icon_url: '', + const handleCardClick = (e: React.MouseEvent) => { + e.preventDefault() + if (isExternalProvider) + push(`/datasets/${dataset.id}/hitTesting`) + else if (isPipelineUnpublished) + push(`/datasets/${dataset.id}/pipeline`) + else + push(`/datasets/${dataset.id}/documents`) } - const { formatIndexingTechniqueAndMethod } = useKnowledge() - const documentCount = useMemo(() => { - const availableDocCount = dataset.total_available_documents ?? 0 - if (availableDocCount === dataset.document_count) - return `${dataset.document_count}` - if (availableDocCount < dataset.document_count) - return `${availableDocCount} / ${dataset.document_count}` - }, [dataset.document_count, dataset.total_available_documents]) - const documentCountTooltip = useMemo(() => { - const availableDocCount = dataset.total_available_documents ?? 0 - if (availableDocCount === dataset.document_count) - return t('docAllEnabled', { ns: 'dataset', count: availableDocCount }) - if (availableDocCount < dataset.document_count) - return t('partialEnabled', { ns: 'dataset', count: dataset.document_count, num: availableDocCount }) - }, [t, dataset.document_count, dataset.total_available_documents]) - const { formatTimeFromNow } = useFormatTimeFromNow() - const editTimeText = useMemo(() => { - return `${t('segment.editedAt', { ns: 'datasetDocuments' })} ${formatTimeFromNow(dataset.updated_at * 1000)}` - }, [t, dataset.updated_at, formatTimeFromNow]) - - const openRenameModal = useCallback(() => { - setShowRenameModal(true) - }, []) - - const { mutateAsync: exportPipelineConfig } = useExportPipelineDSL() - - const handleExportPipeline = useCallback(async (include = false) => { - const { pipeline_id, name } = dataset - if (!pipeline_id) - return - - if (exporting) - return - - try { - setExporting(true) - const { data } = await exportPipelineConfig({ - pipelineId: pipeline_id, - include, - }) - const a = document.createElement('a') - const file = new Blob([data], { type: 'application/yaml' }) - const url = URL.createObjectURL(file) - a.href = url - a.download = `${name}.pipeline` - a.click() - URL.revokeObjectURL(url) - } - catch { - Toast.notify({ type: 'error', message: t('exportFailed', { ns: 'app' }) }) - } - finally { - setExporting(false) - } - }, [dataset, exportPipelineConfig, exporting, t]) - - const detectIsUsedByApp = useCallback(async () => { - try { - const { is_using: isUsedByApp } = await checkIsUsedInApp(dataset.id) - setConfirmMessage(isUsedByApp ? t('datasetUsedByApp', { ns: 'dataset' })! : t('deleteDatasetConfirmContent', { ns: 'dataset' })!) - setShowConfirmDelete(true) - } - catch (e: any) { - const res = await e.json() - Toast.notify({ type: 'error', message: res?.message || 'Unknown error' }) - } - }, [dataset.id, t]) - - const onConfirmDelete = useCallback(async () => { - try { - await deleteDataset(dataset.id) - Toast.notify({ type: 'success', message: t('datasetDeleted', { ns: 'dataset' }) }) - if (onSuccess) - onSuccess() - } - finally { - setShowConfirmDelete(false) - } - }, [dataset.id, onSuccess, t]) - - useEffect(() => { - setTags(dataset.tags) - }, [dataset]) + const handleTagAreaClick = (e: React.MouseEvent) => { + e.stopPropagation() + e.preventDefault() + } return ( <>
{ - e.preventDefault() - if (isExternalProvider) - push(`/datasets/${dataset.id}/hitTesting`) - else if (isPipelineUnpublished) - push(`/datasets/${dataset.id}/pipeline`) - else - push(`/datasets/${dataset.id}/documents`) - }} + onClick={handleCardClick} > - {!dataset.embedding_available && ( - - )} - {dataset.embedding_available && dataset.runtime_mode === 'rag_pipeline' && ( - - )} -
-
- - {(isShowChunkingModeIcon || isExternalProvider) && ( -
- -
- )} -
-
-
- {dataset.name} -
-
-
{dataset.author_name}
-
·
-
{editTimeText}
-
-
- {isExternalProvider && {t('externalKnowledgeBase', { ns: 'dataset' })}} - {!isExternalProvider && isShowDocModeInfo && ( - <> - {dataset.doc_form && ( - - {t(`chunkingMode.${DOC_FORM_TEXT[dataset.doc_form]}`, { ns: 'dataset' })} - - )} - {dataset.indexing_technique && ( - - {formatIndexingTechniqueAndMethod(dataset.indexing_technique, dataset.retrieval_model_dict?.search_method) as any} - - )} - {dataset.is_multimodal && ( - - {t('multimodal', { ns: 'dataset' })} - - )} - - )} -
-
-
-
- {dataset.description} -
-
{ - e.stopPropagation() - e.preventDefault() - }} - > -
0 && 'visible', - )} - > - tag.id)} - selectedTags={tags} - onCacheUpdate={setTags} - onChange={onSuccess} - /> -
- {/* Tag Mask */} -
-
-
- -
- - {documentCount} -
- - {!isExternalProvider && ( - -
- - {dataset.app_count} -
- - )} - / - {`${t('updated', { ns: 'dataset' })} ${formatTimeFromNow(dataset.updated_at * 1000)}`} -
-
- - )} - className="z-20 min-w-[186px]" - popupClassName="rounded-xl bg-none shadow-none ring-0 min-w-[186px]" - position="br" - trigger="click" - btnElement={( -
- -
- )} - btnClassName={open => - cn( - 'size-9 cursor-pointer justify-center rounded-[10px] border-[0.5px] border-components-actionbar-border bg-components-actionbar-bg p-0 shadow-lg shadow-shadow-shadow-5 ring-[2px] ring-inset ring-components-actionbar-bg hover:border-components-actionbar-border', - open ? 'border-components-actionbar-border bg-state-base-hover' : '', - )} - /> -
-
- {showRenameModal && ( - + + + setShowRenameModal(false)} + tags={tags} + setTags={setTags} onSuccess={onSuccess} + isHoveringTagSelector={isHoveringTagSelector} + onClick={handleTagAreaClick} /> - )} - {showConfirmDelete && ( - setShowConfirmDelete(false)} + + - )} +
+ ) } diff --git a/web/app/components/plugins/marketplace/description/index.spec.tsx b/web/app/components/plugins/marketplace/description/index.spec.tsx index b5c8cb716b..054949ee1f 100644 --- a/web/app/components/plugins/marketplace/description/index.spec.tsx +++ b/web/app/components/plugins/marketplace/description/index.spec.tsx @@ -1,7 +1,5 @@ import { render, screen } from '@testing-library/react' import { beforeEach, describe, expect, it, vi } from 'vitest' - -// Import component after mocks are set up import Description from './index' // ================================ @@ -30,20 +28,18 @@ const commonTranslations: Record = { 'operation.in': 'in', } -// Mock getLocaleOnServer and translate -vi.mock('@/i18n-config/server', () => ({ - getLocaleOnServer: vi.fn(() => Promise.resolve(mockDefaultLocale)), - getTranslation: vi.fn((locale: string, ns: string) => { - return Promise.resolve({ - t: (key: string) => { - if (ns === 'plugin') - return pluginTranslations[key] || key - if (ns === 'common') - return commonTranslations[key] || key - return key - }, - }) - }), +// Mock i18n hooks +vi.mock('#i18n', () => ({ + useLocale: vi.fn(() => mockDefaultLocale), + useTranslation: vi.fn((ns: string) => ({ + t: (key: string) => { + if (ns === 'plugin') + return pluginTranslations[key] || key + if (ns === 'common') + return commonTranslations[key] || key + return key + }, + })), })) // ================================ @@ -59,29 +55,29 @@ describe('Description', () => { // Rendering Tests // ================================ describe('Rendering', () => { - it('should render without crashing', async () => { - const { container } = render(await Description({})) + it('should render without crashing', () => { + const { container } = render() expect(container.firstChild).toBeInTheDocument() }) - it('should render h1 heading with empower text', async () => { - render(await Description({})) + it('should render h1 heading with empower text', () => { + render() const heading = screen.getByRole('heading', { level: 1 }) expect(heading).toBeInTheDocument() expect(heading).toHaveTextContent('Empower your AI development') }) - it('should render h2 subheading', async () => { - render(await Description({})) + it('should render h2 subheading', () => { + render() const subheading = screen.getByRole('heading', { level: 2 }) expect(subheading).toBeInTheDocument() }) - it('should apply correct CSS classes to h1', async () => { - render(await Description({})) + it('should apply correct CSS classes to h1', () => { + render() const heading = screen.getByRole('heading', { level: 1 }) expect(heading).toHaveClass('title-4xl-semi-bold') @@ -90,8 +86,8 @@ describe('Description', () => { expect(heading).toHaveClass('text-text-primary') }) - it('should apply correct CSS classes to h2', async () => { - render(await Description({})) + it('should apply correct CSS classes to h2', () => { + render() const subheading = screen.getByRole('heading', { level: 2 }) expect(subheading).toHaveClass('body-md-regular') @@ -104,14 +100,18 @@ describe('Description', () => { // Non-Chinese Locale Rendering Tests // ================================ describe('Non-Chinese Locale Rendering', () => { - it('should render discover text for en-US locale', async () => { - render(await Description({ locale: 'en-US' })) + beforeEach(() => { + mockDefaultLocale = 'en-US' + }) + + it('should render discover text for en-US locale', () => { + render() expect(screen.getByText(/Discover/)).toBeInTheDocument() }) - it('should render all category names', async () => { - render(await Description({ locale: 'en-US' })) + it('should render all category names', () => { + render() expect(screen.getByText('Models')).toBeInTheDocument() expect(screen.getByText('Tools')).toBeInTheDocument() @@ -122,36 +122,36 @@ describe('Description', () => { expect(screen.getByText('Bundles')).toBeInTheDocument() }) - it('should render "and" conjunction text', async () => { - render(await Description({ locale: 'en-US' })) + it('should render "and" conjunction text', () => { + render() const subheading = screen.getByRole('heading', { level: 2 }) expect(subheading.textContent).toContain('and') }) - it('should render "in" preposition at the end for non-Chinese locales', async () => { - render(await Description({ locale: 'en-US' })) + it('should render "in" preposition at the end for non-Chinese locales', () => { + render() expect(screen.getByText('in')).toBeInTheDocument() }) - it('should render Dify Marketplace text at the end for non-Chinese locales', async () => { - render(await Description({ locale: 'en-US' })) + it('should render Dify Marketplace text at the end for non-Chinese locales', () => { + render() const subheading = screen.getByRole('heading', { level: 2 }) expect(subheading.textContent).toContain('Dify Marketplace') }) - it('should render category spans with styled underline effect', async () => { - const { container } = render(await Description({ locale: 'en-US' })) + it('should render category spans with styled underline effect', () => { + const { container } = render() const styledSpans = container.querySelectorAll('.body-md-medium.relative.z-\\[1\\]') // 7 category spans (models, tools, datasources, triggers, agents, extensions, bundles) expect(styledSpans.length).toBe(7) }) - it('should apply text-text-secondary class to category spans', async () => { - const { container } = render(await Description({ locale: 'en-US' })) + it('should apply text-text-secondary class to category spans', () => { + const { container } = render() const styledSpans = container.querySelectorAll('.text-text-secondary') expect(styledSpans.length).toBeGreaterThanOrEqual(7) @@ -162,29 +162,33 @@ describe('Description', () => { // Chinese (zh-Hans) Locale Rendering Tests // ================================ describe('Chinese (zh-Hans) Locale Rendering', () => { - it('should render "in" text at the beginning for zh-Hans locale', async () => { - render(await Description({ locale: 'zh-Hans' })) + beforeEach(() => { + mockDefaultLocale = 'zh-Hans' + }) + + it('should render "in" text at the beginning for zh-Hans locale', () => { + render() // In zh-Hans mode, "in" appears at the beginning const inElements = screen.getAllByText('in') expect(inElements.length).toBeGreaterThanOrEqual(1) }) - it('should render Dify Marketplace text for zh-Hans locale', async () => { - render(await Description({ locale: 'zh-Hans' })) + it('should render Dify Marketplace text for zh-Hans locale', () => { + render() const subheading = screen.getByRole('heading', { level: 2 }) expect(subheading.textContent).toContain('Dify Marketplace') }) - it('should render discover text for zh-Hans locale', async () => { - render(await Description({ locale: 'zh-Hans' })) + it('should render discover text for zh-Hans locale', () => { + render() expect(screen.getByText(/Discover/)).toBeInTheDocument() }) - it('should render all categories for zh-Hans locale', async () => { - render(await Description({ locale: 'zh-Hans' })) + it('should render all categories for zh-Hans locale', () => { + render() expect(screen.getByText('Models')).toBeInTheDocument() expect(screen.getByText('Tools')).toBeInTheDocument() @@ -195,8 +199,8 @@ describe('Description', () => { expect(screen.getByText('Bundles')).toBeInTheDocument() }) - it('should render both zh-Hans specific elements and shared elements', async () => { - render(await Description({ locale: 'zh-Hans' })) + it('should render both zh-Hans specific elements and shared elements', () => { + render() // zh-Hans has specific element order: "in" -> Dify Marketplace -> Discover // then the same category list with "and" -> Bundles @@ -206,61 +210,57 @@ describe('Description', () => { }) // ================================ - // Locale Prop Variations Tests + // Locale Variations Tests // ================================ - describe('Locale Prop Variations', () => { - it('should use default locale when locale prop is undefined', async () => { + describe('Locale Variations', () => { + it('should use en-US locale by default', () => { mockDefaultLocale = 'en-US' - render(await Description({})) + render() - // Should use the default locale from getLocaleOnServer expect(screen.getByText('Empower your AI development')).toBeInTheDocument() }) - it('should use provided locale prop instead of default', async () => { + it('should handle ja-JP locale as non-Chinese', () => { mockDefaultLocale = 'ja-JP' - render(await Description({ locale: 'en-US' })) - - // The locale prop should be used, triggering non-Chinese rendering - const subheading = screen.getByRole('heading', { level: 2 }) - expect(subheading).toBeInTheDocument() - }) - - it('should handle ja-JP locale as non-Chinese', async () => { - render(await Description({ locale: 'ja-JP' })) + render() // Should render in non-Chinese format (discover first, then "in Dify Marketplace" at end) const subheading = screen.getByRole('heading', { level: 2 }) expect(subheading.textContent).toContain('Dify Marketplace') }) - it('should handle ko-KR locale as non-Chinese', async () => { - render(await Description({ locale: 'ko-KR' })) + it('should handle ko-KR locale as non-Chinese', () => { + mockDefaultLocale = 'ko-KR' + render() // Should render in non-Chinese format expect(screen.getByText('Empower your AI development')).toBeInTheDocument() }) - it('should handle de-DE locale as non-Chinese', async () => { - render(await Description({ locale: 'de-DE' })) + it('should handle de-DE locale as non-Chinese', () => { + mockDefaultLocale = 'de-DE' + render() expect(screen.getByText('Empower your AI development')).toBeInTheDocument() }) - it('should handle fr-FR locale as non-Chinese', async () => { - render(await Description({ locale: 'fr-FR' })) + it('should handle fr-FR locale as non-Chinese', () => { + mockDefaultLocale = 'fr-FR' + render() expect(screen.getByText('Empower your AI development')).toBeInTheDocument() }) - it('should handle pt-BR locale as non-Chinese', async () => { - render(await Description({ locale: 'pt-BR' })) + it('should handle pt-BR locale as non-Chinese', () => { + mockDefaultLocale = 'pt-BR' + render() expect(screen.getByText('Empower your AI development')).toBeInTheDocument() }) - it('should handle es-ES locale as non-Chinese', async () => { - render(await Description({ locale: 'es-ES' })) + it('should handle es-ES locale as non-Chinese', () => { + mockDefaultLocale = 'es-ES' + render() expect(screen.getByText('Empower your AI development')).toBeInTheDocument() }) @@ -270,24 +270,27 @@ describe('Description', () => { // Conditional Rendering Tests // ================================ describe('Conditional Rendering', () => { - it('should render zh-Hans specific content when locale is zh-Hans', async () => { - const { container } = render(await Description({ locale: 'zh-Hans' })) + it('should render zh-Hans specific content when locale is zh-Hans', () => { + mockDefaultLocale = 'zh-Hans' + const { container } = render() // zh-Hans has additional span with mr-1 before "in" text at the start const mrSpan = container.querySelector('span.mr-1') expect(mrSpan).toBeInTheDocument() }) - it('should render non-Chinese specific content when locale is not zh-Hans', async () => { - render(await Description({ locale: 'en-US' })) + it('should render non-Chinese specific content when locale is not zh-Hans', () => { + mockDefaultLocale = 'en-US' + render() // Non-Chinese has "in" and "Dify Marketplace" at the end const subheading = screen.getByRole('heading', { level: 2 }) expect(subheading.textContent).toContain('Dify Marketplace') }) - it('should not render zh-Hans intro content for non-Chinese locales', async () => { - render(await Description({ locale: 'en-US' })) + it('should not render zh-Hans intro content for non-Chinese locales', () => { + mockDefaultLocale = 'en-US' + render() // For en-US, the order should be Discover ... in Dify Marketplace // The "in" text should only appear once at the end @@ -303,8 +306,9 @@ describe('Description', () => { expect(inIndex).toBeLessThan(marketplaceIndex) }) - it('should render zh-Hans with proper word order', async () => { - render(await Description({ locale: 'zh-Hans' })) + it('should render zh-Hans with proper word order', () => { + mockDefaultLocale = 'zh-Hans' + render() const subheading = screen.getByRole('heading', { level: 2 }) const content = subheading.textContent || '' @@ -323,58 +327,58 @@ describe('Description', () => { // Category Styling Tests // ================================ describe('Category Styling', () => { - it('should apply underline effect with after pseudo-element styling', async () => { - const { container } = render(await Description({})) + it('should apply underline effect with after pseudo-element styling', () => { + const { container } = render() const categorySpan = container.querySelector('.after\\:absolute') expect(categorySpan).toBeInTheDocument() }) - it('should apply correct after pseudo-element classes', async () => { - const { container } = render(await Description({})) + it('should apply correct after pseudo-element classes', () => { + const { container } = render() // Check for the specific after pseudo-element classes const categorySpans = container.querySelectorAll('.after\\:bottom-\\[1\\.5px\\]') expect(categorySpans.length).toBe(7) }) - it('should apply full width to after element', async () => { - const { container } = render(await Description({})) + it('should apply full width to after element', () => { + const { container } = render() const categorySpans = container.querySelectorAll('.after\\:w-full') expect(categorySpans.length).toBe(7) }) - it('should apply correct height to after element', async () => { - const { container } = render(await Description({})) + it('should apply correct height to after element', () => { + const { container } = render() const categorySpans = container.querySelectorAll('.after\\:h-2') expect(categorySpans.length).toBe(7) }) - it('should apply bg-text-text-selected to after element', async () => { - const { container } = render(await Description({})) + it('should apply bg-text-text-selected to after element', () => { + const { container } = render() const categorySpans = container.querySelectorAll('.after\\:bg-text-text-selected') expect(categorySpans.length).toBe(7) }) - it('should have z-index 1 on category spans', async () => { - const { container } = render(await Description({})) + it('should have z-index 1 on category spans', () => { + const { container } = render() const categorySpans = container.querySelectorAll('.z-\\[1\\]') expect(categorySpans.length).toBe(7) }) - it('should apply left margin to category spans', async () => { - const { container } = render(await Description({})) + it('should apply left margin to category spans', () => { + const { container } = render() const categorySpans = container.querySelectorAll('.ml-1') expect(categorySpans.length).toBeGreaterThanOrEqual(7) }) - it('should apply both left and right margin to specific spans', async () => { - const { container } = render(await Description({})) + it('should apply both left and right margin to specific spans', () => { + const { container } = render() // Extensions and Bundles spans have both ml-1 and mr-1 const extensionsBundlesSpans = container.querySelectorAll('.ml-1.mr-1') @@ -386,28 +390,17 @@ describe('Description', () => { // Edge Cases Tests // ================================ describe('Edge Cases', () => { - it('should handle empty props object', async () => { - const { container } = render(await Description({})) - - expect(container.firstChild).toBeInTheDocument() - }) - - it('should render fragment as root element', async () => { - const { container } = render(await Description({})) + it('should render fragment as root element', () => { + const { container } = render() // Fragment renders h1 and h2 as direct children expect(container.querySelector('h1')).toBeInTheDocument() expect(container.querySelector('h2')).toBeInTheDocument() }) - it('should handle locale prop with undefined value', async () => { - render(await Description({ locale: undefined })) - - expect(screen.getByRole('heading', { level: 1 })).toBeInTheDocument() - }) - - it('should handle zh-Hant as non-Chinese simplified', async () => { - render(await Description({ locale: 'zh-Hant' })) + it('should handle zh-Hant as non-Chinese simplified', () => { + mockDefaultLocale = 'zh-Hant' + render() // zh-Hant is different from zh-Hans, should use non-Chinese format const subheading = screen.getByRole('heading', { level: 2 }) @@ -426,8 +419,8 @@ describe('Description', () => { // Content Structure Tests // ================================ describe('Content Structure', () => { - it('should have comma separators between categories', async () => { - render(await Description({})) + it('should have comma separators between categories', () => { + render() const subheading = screen.getByRole('heading', { level: 2 }) const content = subheading.textContent || '' @@ -436,8 +429,8 @@ describe('Description', () => { expect(content).toMatch(/Models[^\n\r,\u2028\u2029]*,.*Tools[^\n\r,\u2028\u2029]*,.*Data Sources[^\n\r,\u2028\u2029]*,.*Triggers[^\n\r,\u2028\u2029]*,.*Agent Strategies[^\n\r,\u2028\u2029]*,.*Extensions/) }) - it('should have "and" before last category (Bundles)', async () => { - render(await Description({})) + it('should have "and" before last category (Bundles)', () => { + render() const subheading = screen.getByRole('heading', { level: 2 }) const content = subheading.textContent || '' @@ -449,8 +442,9 @@ describe('Description', () => { expect(andIndex).toBeLessThan(bundlesIndex) }) - it('should render all text elements in correct order for en-US', async () => { - render(await Description({ locale: 'en-US' })) + it('should render all text elements in correct order for en-US', () => { + mockDefaultLocale = 'en-US' + render() const subheading = screen.getByRole('heading', { level: 2 }) const content = subheading.textContent || '' @@ -477,8 +471,9 @@ describe('Description', () => { } }) - it('should render all text elements in correct order for zh-Hans', async () => { - render(await Description({ locale: 'zh-Hans' })) + it('should render all text elements in correct order for zh-Hans', () => { + mockDefaultLocale = 'zh-Hans' + render() const subheading = screen.getByRole('heading', { level: 2 }) const content = subheading.textContent || '' @@ -499,82 +494,48 @@ describe('Description', () => { // Layout Tests // ================================ describe('Layout', () => { - it('should have shrink-0 on h1 heading', async () => { - render(await Description({})) + it('should have shrink-0 on h1 heading', () => { + render() const heading = screen.getByRole('heading', { level: 1 }) expect(heading).toHaveClass('shrink-0') }) - it('should have shrink-0 on h2 subheading', async () => { - render(await Description({})) + it('should have shrink-0 on h2 subheading', () => { + render() const subheading = screen.getByRole('heading', { level: 2 }) expect(subheading).toHaveClass('shrink-0') }) - it('should have flex layout on h2', async () => { - render(await Description({})) + it('should have flex layout on h2', () => { + render() const subheading = screen.getByRole('heading', { level: 2 }) expect(subheading).toHaveClass('flex') }) - it('should have items-center on h2', async () => { - render(await Description({})) + it('should have items-center on h2', () => { + render() const subheading = screen.getByRole('heading', { level: 2 }) expect(subheading).toHaveClass('items-center') }) - it('should have justify-center on h2', async () => { - render(await Description({})) + it('should have justify-center on h2', () => { + render() const subheading = screen.getByRole('heading', { level: 2 }) expect(subheading).toHaveClass('justify-center') }) }) - // ================================ - // Translation Function Tests - // ================================ - describe('Translation Functions', () => { - it('should call getTranslation for plugin namespace', async () => { - const { getTranslation } = await import('@/i18n-config/server') - render(await Description({ locale: 'en-US' })) - - expect(getTranslation).toHaveBeenCalledWith('en-US', 'plugin') - }) - - it('should call getTranslation for common namespace', async () => { - const { getTranslation } = await import('@/i18n-config/server') - render(await Description({ locale: 'en-US' })) - - expect(getTranslation).toHaveBeenCalledWith('en-US', 'common') - }) - - it('should call getLocaleOnServer when locale prop is undefined', async () => { - const { getLocaleOnServer } = await import('@/i18n-config/server') - render(await Description({})) - - expect(getLocaleOnServer).toHaveBeenCalled() - }) - - it('should use locale prop when provided', async () => { - const { getTranslation } = await import('@/i18n-config/server') - render(await Description({ locale: 'ja-JP' })) - - expect(getTranslation).toHaveBeenCalledWith('ja-JP', 'plugin') - expect(getTranslation).toHaveBeenCalledWith('ja-JP', 'common') - }) - }) - // ================================ // Accessibility Tests // ================================ describe('Accessibility', () => { - it('should have proper heading hierarchy', async () => { - render(await Description({})) + it('should have proper heading hierarchy', () => { + render() const h1 = screen.getByRole('heading', { level: 1 }) const h2 = screen.getByRole('heading', { level: 2 }) @@ -583,22 +544,22 @@ describe('Description', () => { expect(h2).toBeInTheDocument() }) - it('should have readable text content', async () => { - render(await Description({})) + it('should have readable text content', () => { + render() const h1 = screen.getByRole('heading', { level: 1 }) expect(h1.textContent).not.toBe('') }) - it('should have visible h1 heading', async () => { - render(await Description({})) + it('should have visible h1 heading', () => { + render() const heading = screen.getByRole('heading', { level: 1 }) expect(heading).toBeVisible() }) - it('should have visible h2 heading', async () => { - render(await Description({})) + it('should have visible h2 heading', () => { + render() const subheading = screen.getByRole('heading', { level: 2 }) expect(subheading).toBeVisible() @@ -615,8 +576,8 @@ describe('Description Integration', () => { mockDefaultLocale = 'en-US' }) - it('should render complete component structure', async () => { - const { container } = render(await Description({ locale: 'en-US' })) + it('should render complete component structure', () => { + const { container } = render() // Main headings expect(container.querySelector('h1')).toBeInTheDocument() @@ -627,8 +588,9 @@ describe('Description Integration', () => { expect(categorySpans.length).toBe(7) }) - it('should render complete zh-Hans structure', async () => { - const { container } = render(await Description({ locale: 'zh-Hans' })) + it('should render complete zh-Hans structure', () => { + mockDefaultLocale = 'zh-Hans' + const { container } = render() // Main headings expect(container.querySelector('h1')).toBeInTheDocument() @@ -639,14 +601,16 @@ describe('Description Integration', () => { expect(categorySpans.length).toBe(7) }) - it('should correctly switch between zh-Hans and en-US layouts', async () => { + it('should correctly differentiate between zh-Hans and en-US layouts', () => { // Render en-US - const { container: enContainer, unmount: unmountEn } = render(await Description({ locale: 'en-US' })) + mockDefaultLocale = 'en-US' + const { container: enContainer, unmount: unmountEn } = render() const enContent = enContainer.querySelector('h2')?.textContent || '' unmountEn() // Render zh-Hans - const { container: zhContainer } = render(await Description({ locale: 'zh-Hans' })) + mockDefaultLocale = 'zh-Hans' + const { container: zhContainer } = render() const zhContent = zhContainer.querySelector('h2')?.textContent || '' // Both should have all categories @@ -666,14 +630,16 @@ describe('Description Integration', () => { expect(zhMarketplaceIndex).toBeLessThan(zhDiscoverIndex) }) - it('should maintain consistent styling across locales', async () => { + it('should maintain consistent styling across locales', () => { // Render en-US - const { container: enContainer, unmount: unmountEn } = render(await Description({ locale: 'en-US' })) + mockDefaultLocale = 'en-US' + const { container: enContainer, unmount: unmountEn } = render() const enCategoryCount = enContainer.querySelectorAll('.body-md-medium').length unmountEn() // Render zh-Hans - const { container: zhContainer } = render(await Description({ locale: 'zh-Hans' })) + mockDefaultLocale = 'zh-Hans' + const { container: zhContainer } = render() const zhCategoryCount = zhContainer.querySelectorAll('.body-md-medium').length // Both should have same number of styled category spans diff --git a/web/app/components/plugins/marketplace/description/index.tsx b/web/app/components/plugins/marketplace/description/index.tsx index d3ca964538..30ccbdb76e 100644 --- a/web/app/components/plugins/marketplace/description/index.tsx +++ b/web/app/components/plugins/marketplace/description/index.tsx @@ -1,17 +1,11 @@ -/* eslint-disable dify-i18n/require-ns-option */ -import type { Locale } from '@/i18n-config' -import { getLocaleOnServer, getTranslation } from '@/i18n-config/server' +import { useLocale, useTranslation } from '#i18n' -type DescriptionProps = { - locale?: Locale -} -const Description = async ({ - locale: localeFromProps, -}: DescriptionProps) => { - const localeDefault = await getLocaleOnServer() - const { t } = await getTranslation(localeFromProps || localeDefault, 'plugin') - const { t: tCommon } = await getTranslation(localeFromProps || localeDefault, 'common') - const isZhHans = localeFromProps === 'zh-Hans' +const Description = () => { + const { t } = useTranslation('plugin') + const { t: tCommon } = useTranslation('common') + const locale = useLocale() + + const isZhHans = locale === 'zh-Hans' return ( <> diff --git a/web/app/components/plugins/marketplace/index.tsx b/web/app/components/plugins/marketplace/index.tsx index ff9a4d60bc..f9f7e86b9a 100644 --- a/web/app/components/plugins/marketplace/index.tsx +++ b/web/app/components/plugins/marketplace/index.tsx @@ -42,7 +42,7 @@ const Marketplace = async ({ scrollContainerId={scrollContainerId} showSearchParams={showSearchParams} > - + ({ + useRouter: () => ({ push: mockPush }), +})) + +vi.mock('@/service/common', () => ({ + fetchSetupStatus: vi.fn(), + fetchInitValidateStatus: vi.fn(), + sendForgotPasswordEmail: vi.fn(), +})) + +const mockFetchSetupStatus = vi.mocked(fetchSetupStatus) +const mockFetchInitValidateStatus = vi.mocked(fetchInitValidateStatus) +const mockSendForgotPasswordEmail = vi.mocked(sendForgotPasswordEmail) + +const prepareLoadedState = () => { + mockFetchSetupStatus.mockResolvedValue({ step: 'not_started' } as SetupStatusResponse) + mockFetchInitValidateStatus.mockResolvedValue({ status: 'finished' } as InitValidateStatusResponse) +} + +describe('ForgotPasswordForm', () => { + beforeEach(() => { + vi.clearAllMocks() + prepareLoadedState() + }) + + it('should render form after loading', async () => { + render() + + expect(await screen.findByLabelText('login.email')).toBeInTheDocument() + }) + + it('should show validation error when email is empty', async () => { + render() + + await screen.findByLabelText('login.email') + + fireEvent.click(screen.getByRole('button', { name: /login\.sendResetLink/ })) + + await waitFor(() => { + expect(screen.getByText('login.error.emailInValid')).toBeInTheDocument() + }) + expect(mockSendForgotPasswordEmail).not.toHaveBeenCalled() + }) + + it('should send reset email and navigate after confirmation', async () => { + mockSendForgotPasswordEmail.mockResolvedValue({ result: 'success', data: 'ok' } as any) + + render() + + const emailInput = await screen.findByLabelText('login.email') + fireEvent.change(emailInput, { target: { value: 'test@example.com' } }) + + fireEvent.click(screen.getByRole('button', { name: /login\.sendResetLink/ })) + + await waitFor(() => { + expect(mockSendForgotPasswordEmail).toHaveBeenCalledWith({ + url: '/forgot-password', + body: { email: 'test@example.com' }, + }) + }) + + await waitFor(() => { + expect(screen.getByRole('button', { name: /login\.backToSignIn/ })).toBeInTheDocument() + }) + + fireEvent.click(screen.getByRole('button', { name: /login\.backToSignIn/ })) + expect(mockPush).toHaveBeenCalledWith('/signin') + }) + + it('should submit when form is submitted', async () => { + mockSendForgotPasswordEmail.mockResolvedValue({ result: 'success', data: 'ok' } as any) + + render() + + fireEvent.change(await screen.findByLabelText('login.email'), { target: { value: 'test@example.com' } }) + + const form = screen.getByRole('button', { name: /login\.sendResetLink/ }).closest('form') + expect(form).not.toBeNull() + + fireEvent.submit(form as HTMLFormElement) + + await waitFor(() => { + expect(mockSendForgotPasswordEmail).toHaveBeenCalledWith({ + url: '/forgot-password', + body: { email: 'test@example.com' }, + }) + }) + }) + + it('should disable submit while request is in flight', async () => { + let resolveRequest: ((value: any) => void) | undefined + const requestPromise = new Promise((resolve) => { + resolveRequest = resolve + }) + mockSendForgotPasswordEmail.mockReturnValue(requestPromise as any) + + render() + + fireEvent.change(await screen.findByLabelText('login.email'), { target: { value: 'test@example.com' } }) + + const button = screen.getByRole('button', { name: /login\.sendResetLink/ }) + fireEvent.click(button) + + await waitFor(() => { + expect(button).toBeDisabled() + }) + + fireEvent.click(button) + expect(mockSendForgotPasswordEmail).toHaveBeenCalledTimes(1) + + resolveRequest?.({ result: 'success', data: 'ok' }) + + await waitFor(() => { + expect(screen.getByRole('button', { name: /login\.backToSignIn/ })).toBeInTheDocument() + }) + }) + + it('should keep form state when request fails', async () => { + const consoleSpy = vi.spyOn(console, 'error').mockImplementation(() => {}) + mockSendForgotPasswordEmail.mockResolvedValue({ result: 'fail', data: 'error' } as any) + + render() + + fireEvent.change(await screen.findByLabelText('login.email'), { target: { value: 'test@example.com' } }) + fireEvent.click(screen.getByRole('button', { name: /login\.sendResetLink/ })) + + await waitFor(() => { + expect(mockSendForgotPasswordEmail).toHaveBeenCalledTimes(1) + }) + + expect(screen.getByRole('button', { name: /login\.sendResetLink/ })).toBeInTheDocument() + expect(mockPush).not.toHaveBeenCalled() + + consoleSpy.mockRestore() + }) + + it('should redirect to init when status is not started', async () => { + const originalLocation = window.location + Object.defineProperty(window, 'location', { + value: { href: '' }, + writable: true, + }) + mockFetchInitValidateStatus.mockResolvedValue({ status: 'not_started' } as InitValidateStatusResponse) + + render() + + await waitFor(() => { + expect(window.location.href).toBe('/init') + }) + + Object.defineProperty(window, 'location', { + value: originalLocation, + writable: true, + }) + }) +}) diff --git a/web/app/forgot-password/ForgotPasswordForm.tsx b/web/app/forgot-password/ForgotPasswordForm.tsx index 7299d24ebc..ff33cccc82 100644 --- a/web/app/forgot-password/ForgotPasswordForm.tsx +++ b/web/app/forgot-password/ForgotPasswordForm.tsx @@ -1,15 +1,16 @@ 'use client' import type { InitValidateStatusResponse } from '@/models/common' -import { zodResolver } from '@hookform/resolvers/zod' +import { useStore } from '@tanstack/react-form' import { useRouter } from 'next/navigation' import * as React from 'react' import { useEffect, useState } from 'react' -import { useForm } from 'react-hook-form' import { useTranslation } from 'react-i18next' import { z } from 'zod' import Button from '@/app/components/base/button' +import { formContext, useAppForm } from '@/app/components/base/form' +import { zodSubmitValidator } from '@/app/components/base/form/utils/zod-submit-validator' import { fetchInitValidateStatus, fetchSetupStatus, @@ -27,44 +28,45 @@ const accountFormSchema = z.object({ .email('error.emailInValid'), }) -type AccountFormValues = z.infer - const ForgotPasswordForm = () => { const { t } = useTranslation() const router = useRouter() const [loading, setLoading] = useState(true) const [isEmailSent, setIsEmailSent] = useState(false) - const { register, trigger, getValues, formState: { errors } } = useForm({ - resolver: zodResolver(accountFormSchema), + + const form = useAppForm({ defaultValues: { email: '' }, + validators: { + onSubmit: zodSubmitValidator(accountFormSchema), + }, + onSubmit: async ({ value }) => { + try { + const res = await sendForgotPasswordEmail({ + url: '/forgot-password', + body: { email: value.email }, + }) + if (res.result === 'success') + setIsEmailSent(true) + else console.error('Email verification failed') + } + catch (error) { + console.error('Request failed:', error) + } + }, }) - const handleSendResetPasswordEmail = async (email: string) => { - try { - const res = await sendForgotPasswordEmail({ - url: '/forgot-password', - body: { email }, - }) - if (res.result === 'success') - setIsEmailSent(true) - - else console.error('Email verification failed') - } - catch (error) { - console.error('Request failed:', error) - } - } + const isSubmitting = useStore(form.store, state => state.isSubmitting) + const emailErrors = useStore(form.store, state => state.fieldMeta.email?.errors) const handleSendResetPasswordClick = async () => { + if (isSubmitting) + return + if (isEmailSent) { router.push('/signin') } else { - const isValid = await trigger('email') - if (isValid) { - const email = getValues('email') - await handleSendResetPasswordEmail(email) - } + form.handleSubmit() } } @@ -94,30 +96,51 @@ const ForgotPasswordForm = () => {
-
- {!isEmailSent && ( -
- -
- - {errors.email && {t(`${errors.email?.message}` as 'error.emailInValid', { ns: 'login' })}} + + { + e.preventDefault() + e.stopPropagation() + form.handleSubmit() + }} + > + {!isEmailSent && ( +
+ +
+ + {field => ( + field.handleChange(e.target.value)} + onBlur={field.handleBlur} + placeholder={t('emailPlaceholder', { ns: 'login' }) || ''} + /> + )} + + {emailErrors && emailErrors.length > 0 && ( + + {t(`${emailErrors[0]}` as 'error.emailInValid', { ns: 'login' })} + + )} +
+ )} +
+
- )} -
- -
- + +
diff --git a/web/app/install/installForm.spec.tsx b/web/app/install/installForm.spec.tsx new file mode 100644 index 0000000000..74602f916a --- /dev/null +++ b/web/app/install/installForm.spec.tsx @@ -0,0 +1,158 @@ +import type { InitValidateStatusResponse, SetupStatusResponse } from '@/models/common' +import { fireEvent, render, screen, waitFor } from '@testing-library/react' +import { fetchInitValidateStatus, fetchSetupStatus, login, setup } from '@/service/common' +import { encryptPassword } from '@/utils/encryption' +import InstallForm from './installForm' + +const mockPush = vi.fn() +const mockReplace = vi.fn() + +vi.mock('next/navigation', () => ({ + useRouter: () => ({ push: mockPush, replace: mockReplace }), +})) + +vi.mock('@/service/common', () => ({ + fetchSetupStatus: vi.fn(), + fetchInitValidateStatus: vi.fn(), + setup: vi.fn(), + login: vi.fn(), + getSystemFeatures: vi.fn(), +})) + +const mockFetchSetupStatus = vi.mocked(fetchSetupStatus) +const mockFetchInitValidateStatus = vi.mocked(fetchInitValidateStatus) +const mockSetup = vi.mocked(setup) +const mockLogin = vi.mocked(login) + +const prepareLoadedState = () => { + mockFetchSetupStatus.mockResolvedValue({ step: 'not_started' } as SetupStatusResponse) + mockFetchInitValidateStatus.mockResolvedValue({ status: 'finished' } as InitValidateStatusResponse) +} + +describe('InstallForm', () => { + beforeEach(() => { + vi.clearAllMocks() + prepareLoadedState() + }) + + it('should render form after loading', async () => { + render() + + expect(await screen.findByLabelText('login.email')).toBeInTheDocument() + expect(screen.getByRole('button', { name: /login\.installBtn/ })).toBeInTheDocument() + }) + + it('should show validation error when required fields are empty', async () => { + render() + + await screen.findByLabelText('login.email') + + fireEvent.click(screen.getByRole('button', { name: /login\.installBtn/ })) + + await waitFor(() => { + expect(screen.getByText('login.error.emailInValid')).toBeInTheDocument() + expect(screen.getByText('login.error.nameEmpty')).toBeInTheDocument() + }) + expect(mockSetup).not.toHaveBeenCalled() + }) + + it('should submit and redirect to apps on successful login', async () => { + mockSetup.mockResolvedValue({ result: 'success' } as any) + mockLogin.mockResolvedValue({ result: 'success', data: { access_token: 'token' } } as any) + + render() + + fireEvent.change(await screen.findByLabelText('login.email'), { target: { value: 'admin@example.com' } }) + fireEvent.change(screen.getByLabelText('login.name'), { target: { value: 'Admin' } }) + fireEvent.change(screen.getByLabelText('login.password'), { target: { value: 'Password123' } }) + + const form = screen.getByRole('button', { name: /login\.installBtn/ }).closest('form') + expect(form).not.toBeNull() + + fireEvent.submit(form as HTMLFormElement) + + await waitFor(() => { + expect(mockSetup).toHaveBeenCalledWith({ + body: { + email: 'admin@example.com', + name: 'Admin', + password: 'Password123', + language: 'en', + }, + }) + }) + + await waitFor(() => { + expect(mockLogin).toHaveBeenCalledWith({ + url: '/login', + body: { + email: 'admin@example.com', + password: encryptPassword('Password123'), + }, + }) + }) + + await waitFor(() => { + expect(mockReplace).toHaveBeenCalledWith('/apps') + }) + }) + + it('should redirect to sign in when login fails', async () => { + mockSetup.mockResolvedValue({ result: 'success' } as any) + mockLogin.mockResolvedValue({ result: 'fail', data: 'error', code: 'login_failed', message: 'login failed' } as any) + + render() + + fireEvent.change(await screen.findByLabelText('login.email'), { target: { value: 'admin@example.com' } }) + fireEvent.change(screen.getByLabelText('login.name'), { target: { value: 'Admin' } }) + fireEvent.change(screen.getByLabelText('login.password'), { target: { value: 'Password123' } }) + + fireEvent.click(screen.getByRole('button', { name: /login\.installBtn/ })) + + await waitFor(() => { + expect(mockReplace).toHaveBeenCalledWith('/signin') + }) + }) + + it('should disable submit while request is in flight', async () => { + let resolveSetup: ((value: any) => void) | undefined + const setupPromise = new Promise((resolve) => { + resolveSetup = resolve + }) + mockSetup.mockReturnValue(setupPromise as any) + mockLogin.mockResolvedValue({ result: 'success', data: { access_token: 'token' } } as any) + + render() + + fireEvent.change(await screen.findByLabelText('login.email'), { target: { value: 'admin@example.com' } }) + fireEvent.change(screen.getByLabelText('login.name'), { target: { value: 'Admin' } }) + fireEvent.change(screen.getByLabelText('login.password'), { target: { value: 'Password123' } }) + + const button = screen.getByRole('button', { name: /login\.installBtn/ }) + fireEvent.click(button) + + await waitFor(() => { + expect(button).toBeDisabled() + }) + + fireEvent.click(button) + expect(mockSetup).toHaveBeenCalledTimes(1) + + resolveSetup?.({ result: 'success' }) + + await waitFor(() => { + expect(mockLogin).toHaveBeenCalledTimes(1) + }) + }) + + it('should redirect to sign in when setup is finished', async () => { + mockFetchSetupStatus.mockResolvedValue({ step: 'finished' } as SetupStatusResponse) + + render() + + await waitFor(() => { + expect(localStorage.setItem).toHaveBeenCalledWith('setup_status', 'finished') + expect(mockPush).toHaveBeenCalledWith('/signin') + }) + }) +}) diff --git a/web/app/install/installForm.tsx b/web/app/install/installForm.tsx index c43fbb4251..de32f18bc7 100644 --- a/web/app/install/installForm.tsx +++ b/web/app/install/installForm.tsx @@ -1,18 +1,17 @@ 'use client' -import type { SubmitHandler } from 'react-hook-form' import type { InitValidateStatusResponse, SetupStatusResponse } from '@/models/common' -import { zodResolver } from '@hookform/resolvers/zod' - -import { useDebounceFn } from 'ahooks' +import { useStore } from '@tanstack/react-form' import Link from 'next/link' import { useRouter } from 'next/navigation' import * as React from 'react' -import { useCallback, useEffect } from 'react' -import { useForm } from 'react-hook-form' +import { useEffect } from 'react' import { useTranslation } from 'react-i18next' import { z } from 'zod' import Button from '@/app/components/base/button' +import { formContext, useAppForm } from '@/app/components/base/form' +import { zodSubmitValidator } from '@/app/components/base/form/utils/zod-submit-validator' +import Input from '@/app/components/base/input' import { validPassword } from '@/config' import { useDocLink } from '@/context/i18n' @@ -33,8 +32,6 @@ const accountFormSchema = z.object({ }).regex(validPassword, 'error.passwordInvalid'), }) -type AccountFormValues = z.infer - const InstallForm = () => { useDocumentTitle('') const { t, i18n } = useTranslation() @@ -42,64 +39,49 @@ const InstallForm = () => { const router = useRouter() const [showPassword, setShowPassword] = React.useState(false) const [loading, setLoading] = React.useState(true) - const { - register, - handleSubmit, - formState: { errors, isSubmitting }, - } = useForm({ - resolver: zodResolver(accountFormSchema), + + const form = useAppForm({ defaultValues: { name: '', password: '', email: '', }, - }) + validators: { + onSubmit: zodSubmitValidator(accountFormSchema), + }, + onSubmit: async ({ value }) => { + // First, setup the admin account + await setup({ + body: { + ...value, + language: i18n.language, + }, + }) - const onSubmit: SubmitHandler = async (data) => { - // First, setup the admin account - await setup({ - body: { - ...data, - language: i18n.language, - }, - }) + // Then, automatically login with the same credentials + const loginRes = await login({ + url: '/login', + body: { + email: value.email, + password: encodePassword(value.password), + }, + }) - // Then, automatically login with the same credentials - const loginRes = await login({ - url: '/login', - body: { - email: data.email, - password: encodePassword(data.password), - }, - }) - - // Store tokens and redirect to apps if login successful - if (loginRes.result === 'success') { - router.replace('/apps') - } - else { - // Fallback to signin page if auto-login fails - router.replace('/signin') - } - } - - const handleSetting = async () => { - if (isSubmitting) - return - handleSubmit(onSubmit)() - } - - const { run: debouncedHandleKeyDown } = useDebounceFn( - (e: React.KeyboardEvent) => { - if (e.key === 'Enter') { - e.preventDefault() - handleSetting() + // Store tokens and redirect to apps if login successful + if (loginRes.result === 'success') { + router.replace('/apps') + } + else { + // Fallback to signin page if auto-login fails + router.replace('/signin') } }, - { wait: 200 }, - ) + }) - const handleKeyDown = useCallback(debouncedHandleKeyDown, [debouncedHandleKeyDown]) + const isSubmitting = useStore(form.store, state => state.isSubmitting) + const emailErrors = useStore(form.store, state => state.fieldMeta.email?.errors) + const nameErrors = useStore(form.store, state => state.fieldMeta.name?.errors) + const passwordErrors = useStore(form.store, state => state.fieldMeta.password?.errors) useEffect(() => { fetchSetupStatus().then((res: SetupStatusResponse) => { @@ -128,76 +110,111 @@ const InstallForm = () => {
-
-
- -
- - {errors.email && {t(`${errors.email?.message}` as 'error.emailInValid', { ns: 'login' })}} -
- -
- -
- -
- -
- {errors.name && {t(`${errors.name.message}` as 'error.nameEmpty', { ns: 'login' })}} -
- -
- -
- - -
- + + { + e.preventDefault() + e.stopPropagation() + if (isSubmitting) + return + form.handleSubmit() + }} + > +
+ +
+ + {field => ( + field.handleChange(e.target.value)} + onBlur={field.handleBlur} + placeholder={t('emailPlaceholder', { ns: 'login' }) || ''} + /> + )} + + {emailErrors && emailErrors.length > 0 && ( + + {t(`${emailErrors[0]}` as 'error.emailInValid', { ns: 'login' })} + + )}
-
- {t('error.passwordInvalid', { ns: 'login' })} +
+ +
+ + {field => ( + field.handleChange(e.target.value)} + onBlur={field.handleBlur} + placeholder={t('namePlaceholder', { ns: 'login' }) || ''} + /> + )} + +
+ {nameErrors && nameErrors.length > 0 && ( + + {t(`${nameErrors[0]}` as 'error.nameEmpty', { ns: 'login' })} + + )}
-
-
- -
- +
+ +
+ + {field => ( + field.handleChange(e.target.value)} + onBlur={field.handleBlur} + placeholder={t('passwordPlaceholder', { ns: 'login' }) || ''} + /> + )} + + +
+ +
+
+ +
0, + })} + > + {t('error.passwordInvalid', { ns: 'login' })} +
+
+ +
+ +
+ +
{t('license.tip', { ns: 'login' })} -   +   (null) @@ -35,15 +35,14 @@ const getOrCreateI18next = async (lng: Locale) => { return instance } -export async function getTranslation(lng: Locale, ns: NamespaceKebabCase) { - const camelNs = camelCase(ns) as NamespaceCamelCase +export async function getTranslation(lng: Locale, ns?: NamespaceCamelCase) { const i18nextInstance = await getOrCreateI18next(lng) - if (!i18nextInstance.hasLoadedNamespace(camelNs)) - await i18nextInstance.loadNamespaces(camelNs) + if (ns && !i18nextInstance.hasLoadedNamespace(ns)) + await i18nextInstance.loadNamespaces(ns) return { - t: i18nextInstance.getFixedT(lng, camelNs), + t: i18nextInstance.getFixedT(lng, ns), i18n: i18nextInstance, } } diff --git a/web/package.json b/web/package.json index 05933c08f7..e94f2fd441 100644 --- a/web/package.json +++ b/web/package.json @@ -3,7 +3,13 @@ "type": "module", "version": "1.11.2", "private": true, - "packageManager": "pnpm@10.26.2+sha512.0e308ff2005fc7410366f154f625f6631ab2b16b1d2e70238444dd6ae9d630a8482d92a451144debc492416896ed16f7b114a86ec68b8404b2443869e68ffda6", + "packageManager": "pnpm@10.27.0+sha512.72d699da16b1179c14ba9e64dc71c9a40988cbdc65c264cb0e489db7de917f20dcf4d64d8723625f2969ba52d4b7e2a1170682d9ac2a5dcaeaab732b7e16f04a", + "imports": { + "#i18n": { + "react-server": "./i18n-config/lib.server.ts", + "default": "./i18n-config/lib.client.ts" + } + }, "engines": { "node": ">=v22.11.0" }, @@ -54,7 +60,6 @@ "@formatjs/intl-localematcher": "^0.5.10", "@headlessui/react": "2.2.1", "@heroicons/react": "^2.2.0", - "@hookform/resolvers": "^5.2.2", "@lexical/code": "^0.38.2", "@lexical/link": "^0.38.2", "@lexical/list": "^0.38.2", @@ -117,7 +122,6 @@ "react-18-input-autosize": "^3.0.0", "react-dom": "19.2.3", "react-easy-crop": "^5.5.3", - "react-hook-form": "^7.65.0", "react-hotkeys-hook": "^4.6.2", "react-i18next": "^16.5.0", "react-markdown": "^9.1.0", diff --git a/web/pnpm-lock.yaml b/web/pnpm-lock.yaml index d9f90b62f3..a2e95dadd7 100644 --- a/web/pnpm-lock.yaml +++ b/web/pnpm-lock.yaml @@ -78,9 +78,6 @@ importers: '@heroicons/react': specifier: ^2.2.0 version: 2.2.0(react@19.2.3) - '@hookform/resolvers': - specifier: ^5.2.2 - version: 5.2.2(react-hook-form@7.68.0(react@19.2.3)) '@lexical/code': specifier: ^0.38.2 version: 0.38.2 @@ -267,9 +264,6 @@ importers: react-easy-crop: specifier: ^5.5.3 version: 5.5.6(react-dom@19.2.3(react@19.2.3))(react@19.2.3) - react-hook-form: - specifier: ^7.65.0 - version: 7.68.0(react@19.2.3) react-hotkeys-hook: specifier: ^4.6.2 version: 4.6.2(react-dom@19.2.3(react@19.2.3))(react@19.2.3) @@ -1878,11 +1872,6 @@ packages: peerDependencies: react: '>= 16 || ^19.0.0-rc' - '@hookform/resolvers@5.2.2': - resolution: {integrity: sha512-A/IxlMLShx3KjV/HeTcTfaMxdwy690+L/ZADoeaTltLx+CVuzkeVIPuybK3jrRfw7YZnmdKsVVHAlEPIAEUNlA==} - peerDependencies: - react-hook-form: ^7.55.0 - '@humanfs/core@0.19.1': resolution: {integrity: sha512-5DyQ4+1JEUzejeK1JGICcideyfUbGixgS9jNgex5nqkW+cY7WZhxBigmieN5Qnw9ZosSNVC9KQKyb+GUaGyKUA==} engines: {node: '>=18.18.0'} @@ -3211,9 +3200,6 @@ packages: '@standard-schema/spec@1.1.0': resolution: {integrity: sha512-l2aFy5jALhniG5HgqrD6jXLi/rUWrKvqN/qJx6yoJsgKhblVd+iqqU4RCXavm/jPityDo5TCvKMnpjKnOriy0w==} - '@standard-schema/utils@0.3.0': - resolution: {integrity: sha512-e7Mew686owMaPJVNNLs55PUvgz371nKgwsc4vxE49zsODpJEnxgxRo2y/OKrqueavXgZNMDVj3DdHFlaSAeU8g==} - '@storybook/addon-docs@9.1.13': resolution: {integrity: sha512-V1nCo7bfC3kQ5VNVq0VDcHsIhQf507m+BxMA5SIYiwdJHljH2BXpW2fL3FFn9gv9Wp57AEEzhm+wh4zANaJgkg==} peerDependencies: @@ -7436,12 +7422,6 @@ packages: react-fast-compare@3.2.2: resolution: {integrity: sha512-nsO+KSNgo1SbJqJEYRE9ERzo7YtYbou/OqjSQKxV7jcKox7+usiUVZOAC+XnDOABXggQTno0Y1CpVnuWEc1boQ==} - react-hook-form@7.68.0: - resolution: {integrity: sha512-oNN3fjrZ/Xo40SWlHf1yCjlMK417JxoSJVUXQjGdvdRCU07NTFei1i1f8ApUAts+IVh14e4EdakeLEA+BEAs/Q==} - engines: {node: '>=18.0.0'} - peerDependencies: - react: ^16.8.0 || ^17 || ^18 || ^19 - react-hotkeys-hook@4.6.2: resolution: {integrity: sha512-FmP+ZriY3EG59Ug/lxNfrObCnW9xQShgk7Nb83+CkpfkcCpfS95ydv+E9JuXA5cp8KtskU7LGlIARpkc92X22Q==} peerDependencies: @@ -10516,11 +10496,6 @@ snapshots: dependencies: react: 19.2.3 - '@hookform/resolvers@5.2.2(react-hook-form@7.68.0(react@19.2.3))': - dependencies: - '@standard-schema/utils': 0.3.0 - react-hook-form: 7.68.0(react@19.2.3) - '@humanfs/core@0.19.1': {} '@humanfs/node@0.16.7': @@ -11782,8 +11757,6 @@ snapshots: '@standard-schema/spec@1.1.0': {} - '@standard-schema/utils@0.3.0': {} - '@storybook/addon-docs@9.1.13(@types/react@19.2.7)(storybook@9.1.17(@testing-library/dom@10.4.1)(vite@7.3.0(@types/node@18.15.0)(jiti@1.21.7)(sass@1.95.0)(terser@5.44.1)(tsx@4.21.0)(yaml@2.8.2)))': dependencies: '@mdx-js/react': 3.1.1(@types/react@19.2.7)(react@19.2.3) @@ -16931,10 +16904,6 @@ snapshots: react-fast-compare@3.2.2: {} - react-hook-form@7.68.0(react@19.2.3): - dependencies: - react: 19.2.3 - react-hotkeys-hook@4.6.2(react-dom@19.2.3(react@19.2.3))(react@19.2.3): dependencies: react: 19.2.3 diff --git a/web/service/use-apps.ts b/web/service/use-apps.ts index 0f6c4a64ac..d16d44af20 100644 --- a/web/service/use-apps.ts +++ b/web/service/use-apps.ts @@ -12,6 +12,7 @@ import type { } from '@/models/app' import type { App, AppModeEnum } from '@/types/app' import { + keepPreviousData, useInfiniteQuery, useQuery, useQueryClient, @@ -107,6 +108,7 @@ export const useInfiniteAppList = (params: AppListParams, options?: { enabled?: queryFn: ({ pageParam = normalizedParams.page }) => get('/apps', { params: { ...normalizedParams, page: pageParam } }), getNextPageParam: lastPage => lastPage.has_more ? lastPage.page + 1 : undefined, initialPageParam: normalizedParams.page, + placeholderData: keepPreviousData, ...options, }) } diff --git a/web/service/use-dataset-card.ts b/web/service/use-dataset-card.ts new file mode 100644 index 0000000000..05365479dc --- /dev/null +++ b/web/service/use-dataset-card.ts @@ -0,0 +1,18 @@ +import { useMutation } from '@tanstack/react-query' +import { checkIsUsedInApp, deleteDataset } from './datasets' + +const NAME_SPACE = 'dataset-card' + +export const useCheckDatasetUsage = () => { + return useMutation({ + mutationKey: [NAME_SPACE, 'check-usage'], + mutationFn: (datasetId: string) => checkIsUsedInApp(datasetId), + }) +} + +export const useDeleteDataset = () => { + return useMutation({ + mutationKey: [NAME_SPACE, 'delete'], + mutationFn: (datasetId: string) => deleteDataset(datasetId), + }) +} diff --git a/web/utils/server-only-context.ts b/web/utils/server-only-context.ts index e58dbfe98b..43fe743811 100644 --- a/web/utils/server-only-context.ts +++ b/web/utils/server-only-context.ts @@ -2,7 +2,7 @@ import { cache } from 'react' -export default (defaultValue: T): [() => T, (v: T) => void] => { +export function serverOnlyContext(defaultValue: T): [() => T, (v: T) => void] { const getRef = cache(() => ({ current: defaultValue })) const getValue = (): T => getRef().current