julee 0.1.0__py3-none-any.whl

julee/fixtures/assembly_specifications.yaml

@@ -0,0 +1,70 @@
+assembly_specifications:
+  - assembly_specification_id: "meeting-minutes-assembly"
+    name: "Meeting Minutes Assembly"
+    applicability: "Meeting transcripts from video conferences or in-person meetings that need to be structured into formal meeting minutes"
+    status: "active"
+    version: "1.0"
+    jsonschema:
+      $schema: "http://json-schema.org/draft-07/schema#"
+      title: "Meeting Minutes"
+      type: "object"
+      properties:
+        meeting_info:
+          type: "object"
+          properties:
+            title:
+              type: "string"
+            date:
+              type: "string"
+              format: "date"
+            start_time:
+              type: "string"
+            end_time:
+              type: "string"
+            attendees:
+              type: "array"
+              items:
+                type: "object"
+                properties:
+                  name:
+                    type: "string"
+                  role:
+                    type: "string"
+                required: ["name", "role"]
+          required: ["title", "date", "attendees"]
+        agenda_items:
+          type: "array"
+          items:
+            type: "object"
+            properties:
+              topic:
+                type: "string"
+              discussion_points:
+                type: "array"
+                items:
+                  type: "string"
+              decisions:
+                type: "array"
+                items:
+                  type: "string"
+            required: ["topic"]
+        action_items:
+          type: "array"
+          items:
+            type: "object"
+            properties:
+              task:
+                type: "string"
+              assignee:
+                type: "string"
+              due_date:
+                type: "string"
+              priority:
+                type: "string"
+                enum: ["low", "medium", "high"]
+            required: ["task", "assignee"]
+      required: ["meeting_info", "agenda_items"]
+    knowledge_service_queries:
+      "/properties/meeting_info": "extract-meeting-info-query"
+      "/properties/agenda_items": "extract-agenda-items-query"
+      "/properties/action_items": "extract-action-items-query"

julee/fixtures/documents.yaml

@@ -0,0 +1,178 @@
+# Documents Fixture Configuration
+#
+# This file defines the documents that should be created during system
+# initialization for testing and demonstration purposes. Each document
+# represents a sample file with content and metadata that can be used
+# in the CEAP workflow.
+#
+# The documents are loaded during application startup and stored in the
+# repository if they don't already exist (idempotent loading).
+
+documents:
+  - document_id: "meeting-transcript-q1-planning"
+    original_filename: "q1_planning_meeting.txt"
+    content_type: "text/plain"
+    status: "captured"
+    additional_metadata:
+      meeting_type: "planning_session"
+      quarter: "Q1 2024"
+      attendee_count: 3
+      duration_minutes: 90
+      department: "product"
+    content: |
+      Meeting Transcript - Q1 Planning Session
+      Date: March 15, 2024
+      Time: 2:00 PM - 3:30 PM
+      Attendees: Sarah Chen (Product Manager), Mike Rodriguez (Engineering Lead),
+      Lisa Wang (Designer)
+
+      Sarah: Thanks everyone for joining. Let's kick off our Q1 planning. Mike,
+      can you give us an update on the current sprint?
+
+      Mike: Sure, we're about 80% through sprint 23. We've completed the user
+      authentication module and are working on the data migration tool. Should be
+      done by Friday.
+
+      Lisa: Great! I've finished the mockups for the dashboard redesign. Sarah,
+      have you had a chance to review them?
+
+      Sarah: Yes, they look fantastic. I especially like the new navigation
+      structure. When can we start implementation?
+
+      Mike: I'd estimate 2 weeks for the frontend work, plus another week for
+      backend API changes.
+
+      Lisa: I can start on the component library updates while Mike works on the
+      APIs.
+
+      Sarah: Perfect. Let's also discuss the customer feedback integration. We had
+      47 responses to our survey.
+
+      Mike: The main requests were for better reporting and mobile optimization.
+
+      Sarah: Those should be our next priorities then. Lisa, can you start
+      sketching mobile designs?
+
+      Lisa: Absolutely. I'll have initial concepts by next Tuesday.
+
+      Sarah: Excellent. Any other items?
+
+      Mike: Just a heads up that we'll need to schedule downtime for the database
+      migration, probably next weekend.
+
+      Sarah: Noted. I'll coordinate with support. Meeting adjourned at 3:30 PM.
+
+  - document_id: "customer-feedback-survey-q4"
+    original_filename: "customer_survey_results_q4_2023.txt"
+    content_type: "text/plain"
+    status: "captured"
+    additional_metadata:
+      survey_type: "customer_satisfaction"
+      quarter: "Q4 2023"
+      response_count: 47
+      department: "product"
+      collection_method: "email_survey"
+    content: |
+      Customer Feedback Survey Results - Q4 2023
+      Survey Period: October 1 - December 31, 2023
+      Total Responses: 47
+      Response Rate: 23.5%
+
+      === SUMMARY ===
+      Overall Satisfaction: 4.2/5.0 (up from 3.9 in Q3)
+      Net Promoter Score: +15 (up from +8 in Q3)
+
+      === TOP REQUESTED FEATURES ===
+      1. Better reporting dashboard (mentioned by 78% of respondents)
+      2. Mobile application/optimization (mentioned by 65% of respondents)
+      3. Advanced filtering options (mentioned by 52% of respondents)
+      4. Real-time collaboration features (mentioned by 43% of respondents)
+      5. API access for integrations (mentioned by 39% of respondents)
+
+      === KEY FEEDBACK THEMES ===
+
+      Positive Feedback:
+      - "Love the recent performance improvements" - Customer #23
+      - "Interface is much cleaner than competitors" - Customer #41
+      - "Support team is very responsive" - Customer #15
+
+      Areas for Improvement:
+      - "Mobile experience feels like an afterthought" - Customer #7
+      - "Reports are too basic for our needs" - Customer #31
+      - "Would love more customization options" - Customer #18
+
+      === DETAILED METRICS ===
+      Feature Usage:
+      - Dashboard: 95% of users
+      - Reports: 73% of users
+      - Collaboration: 45% of users
+      - API: 12% of users
+
+      Support Satisfaction: 4.5/5.0
+      Performance Rating: 4.1/5.0
+      Ease of Use: 4.0/5.0
+
+  - document_id: "project-requirements-doc"
+    original_filename: "mobile_optimization_requirements.md"
+    content_type: "text/markdown"
+    status: "registered"
+    knowledge_service_id: "anthropic-4.5-as-a-knowledge-service"
+    assembly_types: ["technical_specification"]
+    additional_metadata:
+      document_type: "requirements"
+      project: "mobile_optimization"
+      priority: "high"
+      department: "engineering"
+      version: "1.2"
+    content: |
+      # Mobile Optimization Project Requirements
+
+      ## Overview
+      Based on Q4 customer feedback indicating 65% of users want better mobile experience,
+      this document outlines requirements for mobile optimization across our platform.
+
+      ## Stakeholders
+      - **Product Owner**: Sarah Chen
+      - **Tech Lead**: Mike Rodriguez
+      - **UX Designer**: Lisa Wang
+      - **QA Lead**: James Kim
+
+      ## Success Criteria
+      - Mobile page load time < 3 seconds
+      - 95%+ responsive design coverage
+      - Touch-friendly interface elements
+      - Offline capability for core features
+      - App store rating > 4.0
+
+      ## Technical Requirements
+
+      ### Performance
+      - Implement lazy loading for images and components
+      - Optimize bundle size (target: <2MB initial load)
+      - Add service worker for caching
+      - Implement progressive web app (PWA) features
+
+      ### User Experience
+      - Responsive breakpoints: 320px, 768px, 1024px, 1440px
+      - Touch targets minimum 44px x 44px
+      - Swipe gestures for navigation
+      - Pull-to-refresh functionality
+      - Bottom navigation for primary actions
+
+      ### Browser Support
+      - iOS Safari (last 2 versions)
+      - Android Chrome (last 2 versions)
+      - Samsung Internet (latest)
+      - Firefox Mobile (latest)
+
+      ## Timeline
+      - **Phase 1 (2 weeks)**: Core responsive layouts
+      - **Phase 2 (1 week)**: Performance optimizations
+      - **Phase 3 (1 week)**: PWA features and testing
+
+      ## Definition of Done
+      - [ ] All pages responsive on target devices
+      - [ ] Performance metrics meet targets
+      - [ ] Accessibility audit passes (WCAG 2.1 AA)
+      - [ ] Cross-browser testing complete
+      - [ ] QA sign-off received

julee/fixtures/knowledge_service_configs.yaml

@@ -0,0 +1,37 @@
+# Knowledge Services Fixture Configuration
+#
+# This file defines the knowledge service configurations that should be
+# created during system initialization. Each configuration represents
+# an external AI/ML service that can be used for document analysis
+# and data extraction in the CEAP workflow.
+#
+# The configurations are loaded during application startup and stored
+# in the repository if they don't already exist (idempotent loading).
+
+knowledge_services:
+  - knowledge_service_id: "anthropic-4.5-as-a-knowledge-service"
+    name: "Anthropic 4.5 sonnet as a Knowledge Service"
+    description: "Uses Anthropic's Claude Sonnet 4.5 with its beta file API as an initial knowledge service"
+    service_api: "anthropic"
+    metadata:
+      model: "claude-sonnet-4-5"
+      max_tokens: 4096
+      temperature: 0.2
+      capabilities:
+        - "text_analysis"
+        - "document_extraction"
+        - "summarization"
+        - "question_answering"
+
+  - knowledge_service_id: "anthropic-claude-haiku"
+    name: "Anthropic Claude Haiku 4.5 as a knowledge service"
+    description: "Uses Anthropic's Claude Haiku 4.5 for fast, lightweight text processing"
+    service_api: "anthropic"
+    metadata:
+      model: "claude-haiku-4-5"
+      max_tokens: 2048
+      temperature: 0.1
+      capabilities:
+        - "quick_analysis"
+        - "simple_extraction"
+        - "classification"

julee/fixtures/knowledge_service_queries.yaml

@@ -0,0 +1,27 @@
+knowledge_service_queries:
+  - query_id: "extract-meeting-info-query"
+    name: "Extract Meeting Information"
+    knowledge_service_id: "anthropic-4.5-as-a-knowledge-service"
+    prompt: "Extract the basic meeting information from this transcript including title, date, times, and attendees with their roles."
+    assistant_prompt: "Looking at the meeting transcript, here's the extracted meeting information that conforms to the provided schema, without surrounding ```json ... ``` markers:"
+    query_metadata:
+      max_tokens: 1000
+      temperature: 0.1
+
+  - query_id: "extract-agenda-items-query"
+    name: "Extract Agenda Items"
+    knowledge_service_id: "anthropic-4.5-as-a-knowledge-service"
+    prompt: "Analyze the meeting transcript and extract the main agenda items discussed, including the topic, key discussion points, and any decisions made for each item."
+    assistant_prompt: "Analyzing the meeting transcript, here are the agenda items with discussion points and decisions that conform to the provided schema, without surrounding ```json ... ``` markers:"
+    query_metadata:
+      max_tokens: 2000
+      temperature: 0.1
+
+  - query_id: "extract-action-items-query"
+    name: "Extract Action Items"
+    knowledge_service_id: "anthropic-4.5-as-a-knowledge-service"
+    prompt: "Identify and extract action items from the meeting transcript, including the specific task, who it's assigned to, any mentioned due dates, and the priority level."
+    assistant_prompt: "From the meeting transcript, here are the identified action items formatted according to the provided schema, without surrounding ```json ... ``` markers:"
+    query_metadata:
+      max_tokens: 1500
+      temperature: 0.1

julee/repositories/__init__.py

@@ -0,0 +1,17 @@
+"""
+Repository implementations and infrastructure.
+
+This package contains concrete implementations of the repository interfaces
+defined in julee.domain.repositories.
+
+Implementation packages:
+- memory: In-memory implementations for testing
+- minio: MinIO-based implementations for production
+- temporal: Temporal workflow proxy implementations
+
+Import implementations using their full module paths, e.g.:
+    from julee.repositories.memory import MemoryDocumentRepository
+    from julee.repositories.minio.document import (
+        MinioDocumentRepository,
+    )
+"""

julee/repositories/memory/__init__.py

@@ -0,0 +1,31 @@
+"""
+Memory repository implementations for julee domain.
+
+This module exports in-memory implementations of all repository protocols
+for the Capture, Extract, Assemble, Publish workflow. These implementations
+use Python dictionaries for storage and are ideal for testing scenarios
+where external dependencies should be avoided.
+
+All implementations maintain the same async interfaces as their production
+counterparts while providing lightweight, dependency-free alternatives.
+"""
+
+from .assembly import MemoryAssemblyRepository
+from .assembly_specification import MemoryAssemblySpecificationRepository
+from .document import MemoryDocumentRepository
+from .document_policy_validation import (
+    MemoryDocumentPolicyValidationRepository,
+)
+from .knowledge_service_config import MemoryKnowledgeServiceConfigRepository
+from .knowledge_service_query import MemoryKnowledgeServiceQueryRepository
+from .policy import MemoryPolicyRepository
+
+__all__ = [
+    "MemoryAssemblyRepository",
+    "MemoryAssemblySpecificationRepository",
+    "MemoryDocumentRepository",
+    "MemoryDocumentPolicyValidationRepository",
+    "MemoryKnowledgeServiceConfigRepository",
+    "MemoryKnowledgeServiceQueryRepository",
+    "MemoryPolicyRepository",
+]

julee/repositories/memory/assembly.py

@@ -0,0 +1,84 @@
+"""
+Memory implementation of AssemblyRepository.
+
+This module provides an in-memory implementation of the AssemblyRepository
+protocol that follows the Clean Architecture patterns defined in the
+Fun-Police Framework. It handles assembly storage in memory dictionaries,
+ensuring idempotency and proper error handling.
+
+The implementation uses Python dictionaries to store assembly data, making it
+ideal for testing scenarios where external dependencies should be avoided.
+All operations are still async to maintain interface compatibility.
+"""
+
+import logging
+from typing import Optional, Dict, Any, List
+
+from julee.domain.models.assembly import Assembly
+from julee.domain.repositories.assembly import AssemblyRepository
+from .base import MemoryRepositoryMixin
+
+logger = logging.getLogger(__name__)
+
+
+class MemoryAssemblyRepository(AssemblyRepository, MemoryRepositoryMixin[Assembly]):
+    """
+    Memory implementation of AssemblyRepository using Python dictionaries.
+
+    This implementation stores assembly data in memory using a dictionary
+    keyed by assembly_id. This provides a lightweight, dependency-free
+    option for testing.
+    """
+
+    def __init__(self) -> None:
+        """Initialize repository with empty in-memory storage."""
+        self.logger = logger
+        self.entity_name = "Assembly"
+        self.storage_dict: Dict[str, Assembly] = {}
+
+        logger.debug("Initializing MemoryAssemblyRepository")
+
+    async def get(self, assembly_id: str) -> Optional[Assembly]:
+        """Retrieve an assembly by ID.
+
+        Args:
+            assembly_id: Unique assembly identifier
+
+        Returns:
+            Assembly if found, None otherwise
+        """
+        return self.get_entity(assembly_id)
+
+    async def save(self, assembly: Assembly) -> None:
+        """Save assembly metadata (status, updated_at, etc.).
+
+        Args:
+            assembly: Assembly entity
+        """
+        self.save_entity(assembly, "assembly_id")
+
+    async def generate_id(self) -> str:
+        """Generate a unique assembly identifier.
+
+        Returns:
+            Unique assembly ID string
+        """
+        return self.generate_entity_id("assembly")
+
+    async def get_many(self, assembly_ids: List[str]) -> Dict[str, Optional[Assembly]]:
+        """Retrieve multiple assemblies by ID.
+
+        Args:
+            assembly_ids: List of unique assembly identifiers
+
+        Returns:
+            Dict mapping assembly_id to Assembly (or None if not found)
+        """
+        return self.get_many_entities(assembly_ids)
+
+    def _add_entity_specific_log_data(
+        self, entity: Assembly, log_data: Dict[str, Any]
+    ) -> None:
+        """Add assembly-specific data to log entries."""
+        super()._add_entity_specific_log_data(entity, log_data)
+        log_data["assembled_document_id"] = entity.assembled_document_id

julee/repositories/memory/assembly_specification.py

@@ -0,0 +1,125 @@
+"""
+Memory implementation of AssemblySpecificationRepository.
+
+This module provides an in-memory implementation of the
+AssemblySpecificationRepository protocol that follows the Clean Architecture
+patterns defined in the Fun-Police Framework. It handles assembly
+specification storage with JSON schemas and knowledge service query
+configurations in memory dictionaries, ensuring idempotency and proper
+error handling.
+
+The implementation uses Python dictionaries to store specification data,
+making it ideal for testing scenarios where external dependencies should be
+avoided. All operations are still async to maintain interface compatibility.
+"""
+
+import logging
+from typing import Optional, Dict, Any, List
+
+from julee.domain.models.assembly_specification import (
+    AssemblySpecification,
+)
+from julee.domain.repositories.assembly_specification import (
+    AssemblySpecificationRepository,
+)
+from .base import MemoryRepositoryMixin
+
+logger = logging.getLogger(__name__)
+
+
+class MemoryAssemblySpecificationRepository(
+    AssemblySpecificationRepository,
+    MemoryRepositoryMixin[AssemblySpecification],
+):
+    """
+    Memory implementation of AssemblySpecificationRepository using Python
+    dictionaries.
+
+    This implementation stores assembly specifications in memory:
+    - Specifications: Dictionary keyed by assembly_specification_id containing
+      AssemblySpecification objects
+
+    This provides a lightweight, dependency-free option for testing while
+    maintaining the same interface as other implementations.
+    """
+
+    def __init__(self) -> None:
+        """Initialize repository with empty in-memory storage."""
+        self.logger = logger
+        self.entity_name = "AssemblySpecification"
+        self.storage_dict: Dict[str, AssemblySpecification] = {}
+
+        logger.debug("Initializing MemoryAssemblySpecificationRepository")
+
+    async def get(
+        self, assembly_specification_id: str
+    ) -> Optional[AssemblySpecification]:
+        """Retrieve an assembly specification by ID.
+
+        Args:
+            assembly_specification_id: Unique specification identifier
+
+        Returns:
+            AssemblySpecification if found, None otherwise
+        """
+        return self.get_entity(assembly_specification_id)
+
+    async def save(self, assembly_specification: AssemblySpecification) -> None:
+        """Save an assembly specification.
+
+        Args:
+            assembly_specification: Complete AssemblySpecification to save
+        """
+        self.save_entity(assembly_specification, "assembly_specification_id")
+
+    async def generate_id(self) -> str:
+        """Generate a unique assembly specification identifier.
+
+        Returns:
+            Unique assembly specification ID string
+        """
+        return self.generate_entity_id("spec")
+
+    async def get_many(
+        self, assembly_specification_ids: List[str]
+    ) -> Dict[str, Optional[AssemblySpecification]]:
+        """Retrieve multiple assembly specifications by ID.
+
+        Args:
+            assembly_specification_ids: List of unique specification
+            identifiers
+
+        Returns:
+            Dict mapping specification_id to AssemblySpecification (or None if
+            not found)
+        """
+        return self.get_many_entities(assembly_specification_ids)
+
+    async def list_all(self) -> List[AssemblySpecification]:
+        """List all assembly specifications.
+
+        Returns:
+            List of all AssemblySpecification entities in the repository
+        """
+        self.logger.debug(
+            f"Memory{self.entity_name}Repository: Listing all "
+            f"{self.entity_name.lower()}s"
+        )
+
+        specifications = list(self.storage_dict.values())
+
+        self.logger.info(
+            f"Memory{self.entity_name}Repository: Listed all "
+            f"{self.entity_name.lower()}s",
+            extra={"count": len(specifications)},
+        )
+
+        return specifications
+
+    def _add_entity_specific_log_data(
+        self, entity: AssemblySpecification, log_data: Dict[str, Any]
+    ) -> None:
+        """Add assembly specification-specific data to log entries."""
+        super()._add_entity_specific_log_data(entity, log_data)
+        log_data["spec_name"] = entity.name
+        log_data["version"] = entity.version