704272644c
feat(prompts): implement Phase 7 - Quality & Validation (FR-9, FR-10)
...
Test Suite / unit-tests (3.11) (push) Has been cancelled
Test Suite / unit-tests (3.12) (push) Has been cancelled
Test Suite / integration-tests (push) Has been cancelled
Test Suite / e2e-tests (push) Has been cancelled
Test Suite / performance-tests (push) Has been cancelled
Test Suite / code-quality (push) Has been cancelled
Test Suite / security-scan (push) Has been cancelled
Test Suite / test-summary (push) Has been cancelled
Add quality gate framework with schema validation (JSON Schema via
jsonschema library), pattern validation (regex-based), multi-gate
QualityValidator with SQLite persistence, HaltingPolicyEngine with
budget/iteration/improvement checks, and RefinementLoop for iterative
execute-validate-halt cycles.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-09 13:31:37 +01:00
bd1d05ba79
feat(prompts): implement Phase 6 - Incremental Execution (FR-7, FR-8)
...
Add change detection, structural diff-based impact analysis,
configurable-depth incremental recomputation with circular suppression,
and impact debt tracking.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-09 13:18:27 +01:00
9ce157400e
feat(prompts): implement Phase 5 - Dependency Tracking (FR-6)
...
Add directed dependency graph with cycle detection, topological sort,
and query service for finding dependents/dependencies transitively.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-09 13:18:18 +01:00
c56c92c815
feat(prompts): implement Phase 4 - Execution Engine (FR-4, FR-5)
...
Test Suite / unit-tests (3.11) (push) Has been cancelled
Test Suite / security-scan (push) Has been cancelled
Test Suite / unit-tests (3.12) (push) Has been cancelled
Test Suite / integration-tests (push) Has been cancelled
Test Suite / e2e-tests (push) Has been cancelled
Test Suite / performance-tests (push) Has been cancelled
Test Suite / code-quality (push) Has been cancelled
Test Suite / test-summary (push) Has been cancelled
Implement three-stage execution lifecycle with idempotent runs and complete
provenance tracking via RunManifest.
Core Features:
- PromptRun model with execution lifecycle stages:
1. Analysis: Template analysis and macro extraction
2. Compilation: Macro resolution and context compilation
3. Processing: LLM execution and output generation
- InputBundleHash for deterministic idempotency (FR-4.3)
- RunManifest for complete execution provenance (FR-5)
- LLMAdapter interface for pluggable model providers
- MockLLMAdapter for testing without API calls
- PromptExecutionEngine orchestrating full lifecycle
Idempotent Execution (FR-4.4):
- Calculate SHA-256 hash of complete input context
- Skip execution if identical hash exists
- Cache successful runs by hash
- Support force re-execution via config flag
RunManifest Tracking (FR-5.2):
- Template metadata (id, name, digest)
- Resolved input artifacts and digests
- Compiled prompt digest
- Model configuration
- Output artifacts
- Dependency edges for graph construction
- Timing metadata for performance analysis
Tests (27 passing):
- 17 execution model tests (config, bundle, runs, stages)
- 10 engine tests (execution, idempotency, errors, caching)
Implements:
- FR-4.1: Three-stage execution lifecycle
- FR-4.2: CompiledPrompt during compilation
- FR-4.3: InputBundleHash calculation
- FR-4.4: Skip execution for identical hashes
- FR-5.1: RunManifest persistence
- FR-5.2: Complete manifest contents
- FR-5.3: Nested run linking (foundation)
Files Created:
- markitect/prompts/execution/models.py
- markitect/prompts/execution/manifest.py
- markitect/prompts/execution/llm_adapter.py
- markitect/prompts/execution/engine.py
- migrations/prompts/003_create_runs_and_manifests.sql
- tests/unit/prompts/test_execution_models.py
- tests/unit/prompts/test_execution_engine.py
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-08 23:15:33 +01:00
5f463e5b20
feat(prompts): implement Phase 3 - Resolver Engine (FR-3)
...
Implement deterministic multi-space resolution with configurable search order.
Core Features:
- ResolutionContext and ResolutionResult for tracking resolution state
- MultiSpaceResolutionStrategy implementing FR-3.1 search order:
1. Local InformationSpace
2. Explicitly included InformationSpaces
3. Default InformationSpace
4. Team/Shared InformationSpace
- PromptResolver with macro resolution logic
- ContextCompiler for assembling resolved prompts
- ResolutionConfig for configurable resolution behavior
Resolution Behavior:
- Required macros fail if not found (FR-3.2)
- Optional macros resolve to empty (FR-3.3)
- Generate macros detected for deferred execution (FR-3.4)
- Deterministic search order with duplicate removal
- Partial compilation support for debugging
Tests (31 passing):
- 14 strategy tests (search order, duplicates, priority)
- 9 resolver tests (required, optional, generate, multi-space)
- 8 compiler tests (substitution, dependencies, digests)
Implements:
- FR-3.1: Deterministic resolution order
- FR-3.2: Required macro validation
- FR-3.3: Optional macro fallback
- FR-3.4: Generate macro detection
- FR-3.5: Max generation depth configuration
Files Created:
- markitect/prompts/resolver/models.py
- markitect/prompts/resolver/strategy.py
- markitect/prompts/resolver/resolver.py
- markitect/prompts/resolver/compiler.py
- migrations/prompts/002_create_resolution_config.sql
- tests/unit/prompts/test_resolution_strategy.py
- tests/unit/prompts/test_prompt_resolver.py
- tests/unit/prompts/test_context_compiler.py
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-08 22:45:46 +01:00
945544880d
feat(prompts): implement Phase 1 - Foundation (FR-1)
...
Implement addressable artifacts with content-based identity and change detection.
Core Features:
- Artifact model with SHA-256 content digests
- ArtifactReference for cross-space addressing
- IArtifactRepository interface for pluggable storage
- SQLiteArtifactRepository implementation
- ArtifactService for high-level operations
- Content digest calculation utilities
Database:
- prompt_artifacts table with indexes
- Support for artifact metadata and types
- UNIQUE constraint on space_id+name
Tests (41 passing):
- 26 model tests (metadata, artifacts, references, digests)
- 15 repository tests (CRUD, queries, constraints)
Implements:
- FR-1.1: Unique addressability by name and ID
- FR-1.2: Content digest computation and storage
- FR-1.3: Cross-space artifact references
Files Created:
- markitect/prompts/models.py
- markitect/prompts/repositories/interfaces.py
- markitect/prompts/repositories/sqlite.py
- markitect/prompts/services/artifact_service.py
- migrations/prompts/001_create_artifacts_table.sql
- tests/unit/prompts/test_artifact_models.py
- tests/unit/prompts/test_artifact_repository.py
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-08 22:30:26 +01:00
