Compare commits

..

19 Commits

Author SHA1 Message Date
09e59ba88b fix repo place 2026-03-04 10:04:40 +03:00
638597f182 move test 2026-03-04 09:18:42 +03:00
bb921ce5dd [
{
        "file": "frontend/src/components/__tests__/task_log_viewer.test.js",
        "verdict": "APPROVED",
        "rejection_reason": "NONE",
        "audit_details": {
            "target_invoked": true,
            "pre_conditions_tested": true,
            "post_conditions_tested": true,
            "test_fixture_used": true,
            "edges_covered": true,
            "invariants_verified": true,
            "ux_states_tested": true,
            "semantic_anchors_present": true
        },
        "coverage_summary": {
            "total_edges": 2,
            "edges_tested": 2,
            "total_invariants": 1,
            "invariants_tested": 1,
            "total_ux_states": 3,
            "ux_states_tested": 3
        },
        "tier_compliance": {
            "source_tier": "CRITICAL",
            "meets_tier_requirements": true
        },
        "feedback": "Remediation successful: test tier matches CRITICAL, missing missing @TEST_EDGE no_task_id coverage added, test for @UX_FEEDBACK (autoScroll) added properly, missing inline=false (show=true) tested properly. Semantic RELATION tag fixed to VERIFIES."
    },
    {
        "file": "frontend/src/lib/components/reports/__tests__/report_card.ux.test.js",
        "verdict": "APPROVED",
        "rejection_reason": "NONE",
        "audit_details": {
            "target_invoked": true,
            "pre_conditions_tested": true,
            "post_conditions_tested": true,
            "test_fixture_used": true,
            "edges_covered": true,
            "invariants_verified": true,
            "ux_states_tested": true,
            "semantic_anchors_present": true
        },
        "coverage_summary": {
            "total_edges": 2,
            "edges_tested": 2,
            "total_invariants": 1,
            "invariants_tested": 1,
            "total_ux_states": 2,
            "ux_states_tested": 2
        },
        "tier_compliance": {
            "source_tier": "CRITICAL",
            "meets_tier_requirements": true
        },
        "feedback": "Remediation successful: @TEST_EDGE random_status and @TEST_EDGE empty_report_object tests explicitly assert on outcomes, @TEST_FIXTURE tested completely, Test tier switched to CRITICAL."
    },
    {
        "file": "backend/tests/test_logger.py",
        "verdict": "APPROVED",
        "rejection_reason": "NONE",
        "audit_details": {
            "target_invoked": true,
            "pre_conditions_tested": true,
            "post_conditions_tested": true,
            "test_fixture_used": true,
            "edges_covered": true,
            "invariants_verified": true,
            "ux_states_tested": false,
            "semantic_anchors_present": true
        },
        "coverage_summary": {
            "total_edges": 0,
            "edges_tested": 0,
            "total_invariants": 0,
            "invariants_tested": 0,
            "total_ux_states": 0,
            "ux_states_tested": 0
        },
        "tier_compliance": {
            "source_tier": "STANDARD",
            "meets_tier_requirements": true
        },
        "feedback": "Remediation successful: Test module semantic anchors added [DEF] and [/DEF] explicitly. Added missing @TIER tag and @RELATION: VERIFIES -> src/core/logger.py at the top of the file."
    }
]
2026-03-03 21:05:29 +03:00
fa380ff9a5 test: remediate audit findings for task log viewer, report card and logger tests 2026-03-03 21:01:24 +03:00
ce3955ed2e chore: commit remaining workspace changes 2026-03-03 19:51:17 +03:00
19898b1570 chore(specs): move clean-repo-enterprise spec from 020 to 023 2026-03-03 19:50:53 +03:00
da24fb9253 dev-preprod-prod logic 2026-03-01 14:39:25 +03:00
80b28ac371 slug first logic 2026-03-01 13:17:05 +03:00
f24200d52a git list refactor 2026-03-01 12:13:19 +03:00
5d45b4adb0 fix(dashboards): lazy-load git status for visible rows 2026-02-28 11:21:37 +03:00
daa9f7be3a причесываем лог 2026-02-28 10:47:19 +03:00
7e43830144 fix(dashboards): stabilize grid layout and remove owners N+1 fallback 2026-02-28 10:46:47 +03:00
066747de59 feat(dashboards): show owners and improve grid actions UI 2026-02-28 10:04:56 +03:00
442d0e0ac2 workflows update 2026-02-28 00:04:55 +03:00
8fa951fc93 dry run migration 2026-02-27 20:48:18 +03:00
149d230426 semantic protocol update 2026-02-27 20:48:06 +03:00
4c601fbe06 [
{
    "file": "backend/src/api/routes/__tests__/test_dashboards.py",
    "verdict": "APPROVED",
    "rejection_reason": "NONE",
    "audit_details": {
      "target_invoked": true,
      "pre_conditions_tested": true,
      "post_conditions_tested": true,
      "test_data_used": true
    },
    "feedback": "All 9 previous findings remediated. @TEST_FIXTURE data aligned, all @TEST_EDGE scenarios covered, all @PRE negative tests present, all @SIDE_EFFECT assertions added. Full contract compliance."
  },
  {
    "file": "backend/src/api/routes/__tests__/test_datasets.py",
    "verdict": "APPROVED",
    "rejection_reason": "NONE",
    "audit_details": {
      "target_invoked": true,
      "pre_conditions_tested": true,
      "post_conditions_tested": true,
      "test_data_used": true
    },
    "feedback": "All 6 previous findings remediated. Full @PRE boundary coverage including page_size>100, empty IDs, missing env. @SIDE_EFFECT assertions added. 503 error path tested."
  },
  {
    "file": "backend/src/core/auth/__tests__/test_auth.py",
    "verdict": "APPROVED",
    "rejection_reason": "NONE",
    "audit_details": {
      "target_invoked": true,
      "pre_conditions_tested": true,
      "post_conditions_tested": true,
      "test_data_used": true
    },
    "feedback": "All 4 previous findings remediated. @SIDE_EFFECT last_login verified. Inactive user @PRE negative test added. Empty hash edge case covered. provision_adfs_user tested for both new and existing user paths."
  },
  {
    "file": "backend/src/services/__tests__/test_resource_service.py",
    "verdict": "APPROVED",
    "rejection_reason": "NONE",
    "audit_details": {
      "target_invoked": true,
      "pre_conditions_tested": true,
      "post_conditions_tested": true,
      "test_data_used": true
    },
    "feedback": "Both prior recommendations implemented. Full edge case coverage for _get_last_task_for_resource. No anti-patterns detected."
  },
  {
    "file": "backend/tests/test_resource_hubs.py",
    "verdict": "APPROVED",
    "rejection_reason": "NONE",
    "audit_details": {
      "target_invoked": true,
      "pre_conditions_tested": true,
      "post_conditions_tested": true,
      "test_data_used": true
    },
    "feedback": "Pagination boundary tests added. All @TEST_EDGE scenarios now covered. No anti-patterns detected."
  },
  {
    "file": "frontend/src/lib/components/assistant/__tests__/assistant_chat.integration.test.js",
    "verdict": "APPROVED",
    "rejection_reason": "NONE",
    "audit_details": {
      "target_invoked": true,
      "pre_conditions_tested": true,
      "post_conditions_tested": true,
      "test_data_used": true
    },
    "feedback": "No changes since previous audit. Contract scanning remains sound."
  },
  {
    "file": "frontend/src/lib/components/assistant/__tests__/assistant_confirmation.integration.test.js",
    "verdict": "APPROVED",
    "rejection_reason": "NONE",
    "audit_details": {
      "target_invoked": true,
      "pre_conditions_tested": true,
      "post_conditions_tested": true,
      "test_data_used": true
    },
    "feedback": "No changes since previous audit. Confirmation flow testing remains sound."
  }
]
2026-02-27 09:59:57 +03:00
36173c0880 test contracts 2026-02-26 19:40:00 +03:00
81d62c1345 new test contracts 2026-02-26 19:29:07 +03:00
164 changed files with 126976 additions and 61808 deletions

View File

@@ -6,7 +6,7 @@ description: Audit AI-generated unit tests. Your goal is to aggressively search
**OBJECTIVE:** Audit AI-generated unit tests. Your goal is to aggressively search for "Test Tautologies", "Logic Echoing", and "Contract Negligence". You are the final gatekeeper. If a test is meaningless, you MUST reject it.
**INPUT:**
1. SOURCE CODE (with GRACE-Poly `[DEF]` Contract: `@PRE`, `@POST`, `@TEST_DATA`).
1. SOURCE CODE (with GRACE-Poly `[DEF]` Contract: `@PRE`, `@POST`, `@TEST_CONTRACT`, `@TEST_FIXTURE`, `@TEST_EDGE`, `@TEST_INVARIANT`).
2. GENERATED TEST CODE.
### I. CRITICAL ANTI-PATTERNS (REJECT IMMEDIATELY IF FOUND):
@@ -17,7 +17,7 @@ description: Audit AI-generated unit tests. Your goal is to aggressively search
2. **The Logic Mirror (Echoing):**
- *Definition:* The test re-implements the exact same algorithmic logic found in the source code to calculate the `expected_result`. If the original logic is flawed, the test will falsely pass.
- *Rule:* Tests must assert against **static, predefined outcomes** (from `@TEST_DATA` or explicit constants), NOT dynamically calculated outcomes using the same logic as the source.
- *Rule:* Tests must assert against **static, predefined outcomes** (from `@TEST_FIXTURE`, `@TEST_EDGE`, `@TEST_INVARIANT` or explicit constants), NOT dynamically calculated outcomes using the same logic as the source.
3. **The "Happy Path" Illusion:**
- *Definition:* The test suite only checks successful executions but ignores the `@PRE` conditions (Negative Testing).
@@ -26,26 +26,78 @@ description: Audit AI-generated unit tests. Your goal is to aggressively search
4. **Missing Post-Condition Verification:**
- *Definition:* The test calls the function but only checks the return value, ignoring `@SIDE_EFFECT` or `@POST` state changes (e.g., failing to verify that a DB call was made or a Store was updated).
### II. AUDIT CHECKLIST
5. **Missing Edge Case Coverage:**
- *Definition:* The test suite ignores `@TEST_EDGE` scenarios defined in the contract.
- *Rule:* Every `@TEST_EDGE` in the source contract MUST have a corresponding test case.
6. **Missing Invariant Verification:**
- *Definition:* The test suite does not verify `@TEST_INVARIANT` conditions.
- *Rule:* Every `@TEST_INVARIANT` MUST be verified by at least one test that attempts to break it.
7. **Missing UX State Testing (Svelte Components):**
- *Definition:* For Svelte components with `@UX_STATE`, the test suite does not verify state transitions.
- *Rule:* Every `@UX_STATE` transition MUST have a test verifying the visual/behavioral change.
- *Check:* `@UX_FEEDBACK` mechanisms (toast, shake, color) must be tested.
- *Check:* `@UX_RECOVERY` mechanisms (retry, clear input) must be tested.
### II. SEMANTIC PROTOCOL COMPLIANCE
Verify the test file follows GRACE-Poly semantics:
1. **Anchor Integrity:**
- Test file MUST start with `[DEF:__tests__/test_name:Module]`
- Test file MUST end with `[/DEF:__tests__/test_name:Module]`
2. **Required Tags:**
- `@RELATION: VERIFIES -> <path_to_source>` must be present
- `@PURPOSE:` must describe what is being tested
3. **TIER Alignment:**
- If source is `@TIER: CRITICAL`, test MUST cover all `@TEST_CONTRACT`, `@TEST_FIXTURE`, `@TEST_EDGE`, `@TEST_INVARIANT`
- If source is `@TIER: STANDARD`, test MUST cover `@PRE` and `@POST`
- If source is `@TIER: TRIVIAL`, basic smoke test is acceptable
### III. AUDIT CHECKLIST
Evaluate the test code against these criteria:
1. **Target Invocation:** Does the test actually import and call the function/component declared in the `@RELATION: VERIFIES` tag?
2. **Contract Alignment:** Does the test suite cover 100% of the `@PRE` (negative tests) and `@POST` (assertions) conditions from the source contract?
3. **Data Usage:** Does the test use the exact scenarios defined in `@TEST_DATA`?
4. **Mocking Sanity:** Are external dependencies mocked correctly WITHOUT mocking the system under test itself?
3. **Test Contract Compliance:** Does the test follow the interface defined in `@TEST_CONTRACT`?
4. **Data Usage:** Does the test use the exact scenarios defined in `@TEST_FIXTURE`?
5. **Edge Coverage:** Are all `@TEST_EDGE` scenarios tested?
6. **Invariant Coverage:** Are all `@TEST_INVARIANT` conditions verified?
7. **UX Coverage (if applicable):** Are all `@UX_STATE`, `@UX_FEEDBACK`, `@UX_RECOVERY` tested?
8. **Mocking Sanity:** Are external dependencies mocked correctly WITHOUT mocking the system under test itself?
9. **Semantic Anchor:** Does the test file have proper `[DEF]` and `[/DEF]` anchors?
### III. OUTPUT FORMAT
### IV. OUTPUT FORMAT
You MUST respond strictly in the following JSON format. Do not add markdown blocks outside the JSON.
{
"verdict": "APPROVED" | "REJECTED",
"rejection_reason": "TAUTOLOGY" | "LOGIC_MIRROR" | "WEAK_CONTRACT_COVERAGE" | "OVER_MOCKED" | "NONE",
"rejection_reason": "TAUTOLOGY" | "LOGIC_MIRROR" | "WEAK_CONTRACT_COVERAGE" | "OVER_MOCKED" | "MISSING_EDGES" | "MISSING_INVARIANTS" | "MISSING_UX_TESTS" | "SEMANTIC_VIOLATION" | "NONE",
"audit_details": {
"target_invoked": true/false,
"pre_conditions_tested": true/false,
"post_conditions_tested": true/false,
"test_data_used": true/false
"test_fixture_used": true/false,
"edges_covered": true/false,
"invariants_verified": true/false,
"ux_states_tested": true/false,
"semantic_anchors_present": true/false
},
"coverage_summary": {
"total_edges": number,
"edges_tested": number,
"total_invariants": number,
"invariants_tested": number,
"total_ux_states": number,
"ux_states_tested": number
},
"tier_compliance": {
"source_tier": "CRITICAL" | "STANDARD" | "TRIVIAL",
"meets_tier_requirements": true/false
},
"feedback": "Strict, actionable feedback for the test generator agent. Explain exactly which anti-pattern was detected and how to fix it."
}

View File

@@ -1,4 +1,4 @@
---
description: USE SEMANTIC
---
Прочитай .specify/memory/semantics.md (или .ai/standards/semantics.md, если не найден). ОБЯЗАТЕЛЬНО используй его при разработке
Прочитай .ai/standards/semantics.md. ОБЯЗАТЕЛЬНО используй его при разработке

View File

@@ -63,6 +63,7 @@ Load only the minimal necessary context from each artifact:
**From constitution:**
- Load `.ai/standards/constitution.md` for principle validation
- Load `.ai/standards/semantics.md` for technical standard validation
### 3. Build Semantic Models

View File

@@ -20,7 +20,7 @@ Analyze test failure reports, identify root causes, and fix implementation issue
1. **USE CODER MODE**: Always switch to `coder` mode for code fixes
2. **SEMANTIC PROTOCOL**: Never remove semantic annotations ([DEF], @TAGS). Only update code logic.
3. **TEST DATA**: If tests use @TEST_DATA fixtures, preserve them when fixing
3. **TEST DATA**: If tests use @TEST_ fixtures, preserve them when fixing
4. **NO DELETION**: Never delete existing tests or semantic annotations
5. **REPORT FIRST**: Always write a fix report before making changes

View File

@@ -53,6 +53,15 @@ You **MUST** consider the user input before proceeding (if not empty).
- **IF EXISTS**: Read research.md for technical decisions and constraints
- **IF EXISTS**: Read quickstart.md for integration scenarios
3. Load and analyze the implementation context:
- **REQUIRED**: Read `.ai/standards/semantics.md` for strict coding standards and contract requirements
- **REQUIRED**: Read tasks.md for the complete task list and execution plan
- **REQUIRED**: Read plan.md for tech stack, architecture, and file structure
- **IF EXISTS**: Read data-model.md for entities and relationships
- **IF EXISTS**: Read contracts/ for API specifications and test requirements
- **IF EXISTS**: Read research.md for technical decisions and constraints
- **IF EXISTS**: Read quickstart.md for integration scenarios
4. **Project Setup Verification**:
- **REQUIRED**: Create/verify ignore files based on actual project setup:
@@ -111,7 +120,13 @@ You **MUST** consider the user input before proceeding (if not empty).
- **Validation checkpoints**: Verify each phase completion before proceeding
7. Implementation execution rules:
- **Setup first**: Initialize project structure, dependencies, configuration
- **Strict Adherence**: Apply `.ai/standards/semantics.md` rules:
- Every file MUST start with a `[DEF:id:Type]` header and end with a closing `[/DEF:id:Type]` anchor.
- Include `@TIER` and define contracts (`@PRE`, `@POST`).
- For Svelte components, use `@UX_STATE`, `@UX_FEEDBACK`, `@UX_RECOVERY`, and explicitly declare reactivity with `@UX_REATIVITY: State: $state, Derived: $derived`.
- **Molecular Topology Logging**: Use prefixes `[EXPLORE]`, `[REASON]`, `[REFLECT]` in logs to trace logic.
- **CRITICAL Contracts**: If a task description contains a contract summary (e.g., `CRITICAL: PRE: ..., POST: ...`), these constraints are **MANDATORY** and must be strictly implemented in the code using guards/assertions (if applicable per protocol).
- **Setup first**: Initialize project structure, dependencies, configuration
- **Tests before code**: If you need to write tests for contracts, entities, and integration scenarios
- **Core development**: Implement models, services, CLI commands, endpoints
- **Integration work**: Database connections, middleware, logging, external services

View File

@@ -22,7 +22,7 @@ You **MUST** consider the user input before proceeding (if not empty).
1. **Setup**: Run `.specify/scripts/bash/setup-plan.sh --json` from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
2. **Load context**: Read FEATURE_SPEC and `.ai/standards/constitution.md`. Load IMPL_PLAN template (already copied).
2. **Load context**: Read `.ai/ROOT.md` and `.ai/PROJECT_MAP.md` to understand the project structure and navigation. Then read required standards: `.ai/standards/constitution.md` and `.ai/standards/semantics.md`. Load IMPL_PLAN template.
3. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to:
- Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")
@@ -64,16 +64,30 @@ You **MUST** consider the user input before proceeding (if not empty).
**Prerequisites:** `research.md` complete
1. **Extract entities from feature spec** → `data-model.md`:
- Entity name, fields, relationships
- Validation rules from requirements
- State transitions if applicable
0. **Validate Design against UX Reference**:
- Check if the proposed architecture supports the latency, interactivity, and flow defined in `ux_reference.md`.
- **Linkage**: Ensure key UI states from `ux_reference.md` map to Component Contracts (`@UX_STATE`).
- **CRITICAL**: If the technical plan compromises the UX (e.g. "We can't do real-time validation"), you **MUST STOP** and warn the user.
2. **Define interface contracts** (if project has external interfaces) → `/contracts/`:
- Identify what interfaces the project exposes to users or other systems
- Document the contract format appropriate for the project type
- Examples: public APIs for libraries, command schemas for CLI tools, endpoints for web services, grammars for parsers, UI contracts for applications
- Skip if project is purely internal (build scripts, one-off tools, etc.)
1. **Extract entities from feature spec** → `data-model.md`:
- Entity name, fields, relationships, validation rules.
2. **Design & Verify Contracts (Semantic Protocol)**:
- **Drafting**: Define `[DEF:id:Type]` Headers, Contracts, and closing `[/DEF:id:Type]` for all new modules based on `.ai/standards/semantics.md`.
- **TIER Classification**: Explicitly assign `@TIER: [CRITICAL|STANDARD|TRIVIAL]` to each module.
- **CRITICAL Requirements**: For all CRITICAL modules, define full `@PRE`, `@POST`, and (if UI) `@UX_STATE` contracts. **MUST** also define testing contracts: `@TEST_CONTRACT`, `@TEST_FIXTURE`, `@TEST_EDGE`, and `@TEST_INVARIANT`.
- **Self-Review**:
- *Completeness*: Do `@PRE`/`@POST` cover edge cases identified in Research? Are test contracts present for CRITICAL?
- *Connectivity*: Do `@RELATION` tags form a coherent graph?
- *Compliance*: Does syntax match `[DEF:id:Type]` exactly and is it closed with `[/DEF:id:Type]`?
- **Output**: Write verified contracts to `contracts/modules.md`.
3. **Simulate Contract Usage**:
- Trace one key user scenario through the defined contracts to ensure data flow continuity.
- If a contract interface mismatch is found, fix it immediately.
4. **Generate API contracts**:
- Output OpenAPI/GraphQL schema to `/contracts/` for backend-frontend sync.
3. **Agent context update**:
- Run `.specify/scripts/bash/update-agent-context.sh agy`

View File

@@ -24,7 +24,7 @@ You **MUST** consider the user input before proceeding (if not empty).
1. **Setup**: Run `.specify/scripts/bash/check-prerequisites.sh --json` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
2. **Load design documents**: Read from FEATURE_DIR:
- **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities)
- **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities), ux_reference.md (experience source of truth)
- **Optional**: data-model.md (entities), contracts/ (interface contracts), research.md (decisions), quickstart.md (test scenarios)
- Note: Not all projects have all documents. Generate tasks based on what's available.
@@ -70,6 +70,12 @@ The tasks.md should be immediately executable - each task must be specific enoug
**Tests are OPTIONAL**: Only generate test tasks if explicitly requested in the feature specification or if user requests TDD approach.
### UX Preservation (CRITICAL)
- **Source of Truth**: `ux_reference.md` is the absolute standard for the "feel" of the feature.
- **Violation Warning**: If any task would inherently violate the UX (e.g. "Remove progress bar to simplify code"), you **MUST** flag this to the user immediately.
- **Verification Task**: You **MUST** add a specific task at the end of each User Story phase: `- [ ] Txxx [USx] Verify implementation matches ux_reference.md (Happy Path & Errors)`
### Checklist Format (REQUIRED)
Every task MUST strictly follow this format:
@@ -113,9 +119,12 @@ Every task MUST strictly follow this format:
- If tests requested: Tests specific to that story
- Mark story dependencies (most stories should be independent)
2. **From Contracts**:
- Map each interface contract → to the user story it serves
- If tests requested: Each interface contract → contract test task [P] before implementation in that story's phase
2. **From Contracts (CRITICAL TIER)**:
- Identify components marked as `@TIER: CRITICAL` in `contracts/modules.md`.
- For these components, **MUST** append the summary of `@PRE`, `@POST`, `@UX_STATE`, and test contracts (`@TEST_FIXTURE`, `@TEST_EDGE`) directly to the task description.
- Example: `- [ ] T005 [P] [US1] Implement Auth (CRITICAL: PRE: token exists, POST: returns User, TESTS: 2 edges) in src/auth.py`
- Map each contract/endpoint → to the user story it serves
- If tests requested: Each contract → contract test task [P] before implementation in that story's phase
3. **From Data Model**:
- Map each entity to the user story(ies) that need it

View File

@@ -249,6 +249,7 @@ component/__tests__/Component.test.js
# [DEF:__tests__/test_module:Module]
# @RELATION: VERIFIES -> ../module.py
# @PURPOSE: Contract testing for module
# [/DEF:__tests__/test_module:Module]
```
---

1654
.ai/MODULE_MAP.md Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -26,7 +26,7 @@
4. **ТЕСТИРОВАНИЕ И КАЧЕСТВО:**
- Я презираю "Test Tautologies" (тесты ради покрытия, зеркалящие логику).
- Тесты должны быть Contract-Driven. Если есть `@PRE`, я ожидаю тест на его нарушение.
- Тесты обязаны использовать `@TEST_DATA` из контрактов.
- Тесты обязаны использовать `@TEST_` из контрактов.
5. **ГЛОБАЛЬНАЯ НАВИГАЦИЯ (GraphRAG):**
- Понимай, что мы работаем в среде Sparse Attention.

4846
.ai/PROJECT_MAP.md Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -3,14 +3,29 @@
# @SEMANTICS: Finance, ACID, Transfer, Ledger
# @PURPOSE: Core banking transaction processor with ACID guarantees.
# @LAYER: Domain (Core)
# @RELATION: DEPENDS_ON -> [DEF:Infra:PostgresDB]
# @RELATION: DEPENDS_ON -> [DEF:Infra:AuditLog]
# @RELATION: DEPENDS_ON ->[DEF:Infra:PostgresDB]
#
# @INVARIANT: Total system balance must remain constant (Double-Entry Bookkeeping).
# @INVARIANT: Negative transfers are strictly forbidden.
# @TEST_DATA: sufficient_funds -> {"from": "acc_A", "to": "acc_B", "amt": 100.00}
# @TEST_DATA: insufficient_funds -> {"from": "acc_empty", "to": "acc_B", "amt": 1000.00}
# @TEST_DATA: concurrency_lock -> {./fixtures/transactions.json#race_condition}
# --- Test Specifications (The "What" and "Why", not the "Data") ---
# @TEST_CONTRACT: Input -> TransferInputDTO, Output -> TransferResultDTO
# Happy Path
# @TEST_SCENARIO: sufficient_funds -> Returns COMPLETED, balances updated.
# @TEST_FIXTURE: sufficient_funds -> file:./__tests__/fixtures/transfers.json#happy_path
# Edge Cases (CRITICAL)
# @TEST_SCENARIO: insufficient_funds -> Throws BusinessRuleViolation("INSUFFICIENT_FUNDS").
# @TEST_SCENARIO: negative_amount -> Throws BusinessRuleViolation("Transfer amount must be positive.").
# @TEST_SCENARIO: self_transfer -> Throws BusinessRuleViolation("Cannot transfer to self.").
# @TEST_SCENARIO: audit_failure -> Throws RuntimeError("TRANSACTION_ABORTED").
# @TEST_SCENARIO: concurrency_conflict -> Throws DBTransactionError.
# Linking Tests to Invariants
# @TEST_INVARIANT: total_balance_constant -> VERIFIED_BY: [sufficient_funds, concurrency_conflict]
# @TEST_INVARIANT: negative_transfer_forbidden -> VERIFIED_BY: [negative_amount]
from decimal import Decimal
from typing import NamedTuple

View File

@@ -1,24 +1,67 @@
<!-- [DEF:FrontendComponentShot:Component] -->
<!-- /**
* @TIER: CRITICAL
* @SEMANTICS: Task, Button, Action, UX
* @PURPOSE: Action button to spawn a new task with full UX feedback cycle.
* @LAYER: UI (Presentation)
* @RELATION: CALLS -> postApi
* @INVARIANT: Must prevent double-submission while loading.
*
* @TEST_DATA: idle_state -> {"isLoading": false}
* @TEST_DATA: loading_state -> {"isLoading": true}
*
* @UX_STATE: Idle -> Button enabled, primary color.
* @UX_STATE: Loading -> Button disabled, spinner visible.
* @UX_STATE: Error -> Toast notification triggers.
*
* @UX_FEEDBACK: Toast success/error.
* @UX_TEST: Idle -> {click: spawnTask, expected: isLoading=true}
* @UX_TEST: Success -> {api_resolve: 200, expected: toast.success called}
*/
-->
<!--
/**
* @TIER: CRITICAL
* @SEMANTICS: Task, Button, Action, UX
* @PURPOSE: Action button to spawn a new task with full UX feedback cycle.
* @LAYER: UI (Presentation)
* @RELATION: CALLS -> postApi
*
* @INVARIANT: Must prevent double-submission while loading.
* @INVARIANT: Loading state must always terminate (no infinite spinner).
* @INVARIANT: User must receive feedback on both success and failure.
*
* @TEST_CONTRACT: ComponentState ->
* {
* required_fields: {
* isLoading: bool
* },
* invariants: [
* "isLoading=true implies button.disabled=true",
* "isLoading=true implies aria-busy=true",
* "isLoading=true implies spinner visible"
* ]
* }
*
* @TEST_CONTRACT: ApiResponse ->
* {
* required_fields: {},
* optional_fields: {
* task_id: str
* }
* }
* @TEST_FIXTURE: idle_state ->
* {
* isLoading: false
* }
*
* @TEST_FIXTURE: successful_response ->
* {
* task_id: "task_123"
* }
* @TEST_EDGE: api_failure -> raises Error("Network")
* @TEST_EDGE: empty_response -> {}
* @TEST_EDGE: rapid_double_click -> special: concurrent_click
* @TEST_EDGE: unresolved_promise -> special: pending_state
* @TEST_INVARIANT: prevent_double_submission -> verifies: [rapid_double_click]
* @TEST_INVARIANT: loading_state_consistency -> verifies: [idle_state, pending_state]
* @TEST_INVARIANT: feedback_always_emitted -> verifies: [successful_response, api_failure]
* @UX_STATE: Idle -> Button enabled, primary color, no spinner.
* @UX_STATE: Loading -> Button disabled, spinner visible, aria-busy=true.
* @UX_STATE: Success -> Toast success displayed.
* @UX_STATE: Error -> Toast error displayed.
*
* @UX_FEEDBACK: toast.success, toast.error
*
* @UX_TEST: Idle -> {click: spawnTask, expected: isLoading=true}
* @UX_TEST: Loading -> {double_click: ignored, expected: single_api_call}
* @UX_TEST: Success -> {api_resolve: task_id, expected: toast.success called}
* @UX_TEST: Error -> {api_reject: error, expected: toast.error called}
-->
<script>
import { postApi } from "$lib/api.js";
import { t } from "$lib/i18n";

View File

@@ -5,6 +5,7 @@
#### I. ЗАКОН (АКСИОМЫ)
1. Смысл первичен. Код вторичен.
2.Слепота недопустима. Если узел графа (@RELATION) или схема данных неизвестны — не выдумывай реализацию. Остановись и запроси контекст.
2. Контракт (@PRE/@POST) — источник истины.
**3. UX — это логика, а не декор. Состояния интерфейса — часть контракта.**
4. Структура `[DEF]...[/DEF]` — нерушима.
@@ -47,11 +48,13 @@
@PRE: Входные условия.
@POST: Гарантии выхода.
@SIDE_EFFECT: Мутации, IO.
@DATA_CONTRACT: Ссылка на DTO/Pydantic модель. Заменяет ручное описание @PARAM. Формат: Input -> [Model], Output -> [Model].
**UX Теги (Svelte/Frontend):**
**@UX_STATE:** `[StateName] -> Визуальное поведение` (Idle, Loading, Error).
**@UX_FEEDBACK:** Реакция системы (Toast, Shake, Red Border).
**@UX_RECOVERY:** Механизм исправления ошибки пользователем (Retry, Clear Input).
**@UX_REATIVITY:** Явное указание использования рун. Формат: State: $state, Derived: $derived. Никаких устаревших export let.
**UX Testing Tags (для Tester Agent):**
**@UX_TEST:** Спецификация теста для UX состояния.
@@ -63,41 +66,26 @@
#### V. АДАПТАЦИЯ (TIERS)
Определяется тегом `@TIER` в Header.
1. **CRITICAL** (Core/Security/**Complex UI**):
- Требование: Полный контракт (включая **все @UX теги**), Граф, Инварианты, Строгие Логи.
```
@TEST_CONTRACT: Обязательное описание структуры входных/выходных данных.
Формат:
@TEST_CONTRACT: Name -> {
required_fields: {field: type},
optional_fields: {field: type},
invariants: [...]
}
### V. УРОВНИ СТРОГОСТИ (TIERS)
Степень контроля задается тегом `@TIER` в Header.
@TEST_FIXTURE: Эталонный корректный пример (happy-path).
Формат:
@TEST_FIXTURE: fixture_name -> {INLINE_JSON | PATH#fragment}
**1. CRITICAL** (Ядро / Безопасность / Сложный UI)
- **Закон:** Полный GRACE. Граф, Инварианты, Строгий Лог, все `@UX` теги.
- **Догма Тестирования:** Тесты рождаются из контракта. Голый код без данных — слеп.
- `@TEST_CONTRACT: InputType -> OutputType`. (Строгий интерфейс).
- `@TEST_SCENARIO: name -> Ожидаемое поведение`. (Суть теста).
- `@TEST_FIXTURE: name -> file:PATH | INLINE_JSON`. (Данные для Happy Path).
- `@TEST_EDGE: name -> Описание сбоя`. (Минимум 3 границы).
- *Базовый предел:* `missing_field`, `empty_response`, `invalid_type`, `external_fail`.
- `@TEST_INVARIANT: inv_name -> VERIFIED_BY: [scenario_1, ...]`. (Смыкание логики).
- **Исполнение:** Tester Agent обязан строить проверки строго по этим тегам.
@TEST_EDGE: Граничные случаи (минимум 3 для CRITICAL).
Формат:
@TEST_EDGE: case_name -> {INLINE_JSON | special_case}
**2. STANDARD** (Бизнес-логика / Формы)
- **Закон:** База. (`@PURPOSE`, `@UX_STATE`, Лог, `@RELATION`).
- **Исключение:** Для сложных форм внедряй `@TEST_SCENARIO` и `@TEST_INVARIANT`.
@TEST_INVARIANT: Обязательно. Связывает тесты с инвариантами.
Формат:
@TEST_INVARIANT: invariant_name -> verifies: [test_case_1, test_case_2]
Обязательные edge-типы для CRITICAL:
- missing_required_field
- empty_response
- invalid_type
- external_failure (exception)
```
- Tester Agent **ОБЯЗАН** использовать @TEST_CONTRACT, @TEST_FIXTURE и @TEST_EDGE при написании тестов для CRITICAL модулей.
2. **STANDARD** (BizLogic/**Forms**):
- Требование: Базовый контракт (@PURPOSE, @UX_STATE), Логи, @RELATION.
- @TEST_DATA: Рекомендуется для Complex Forms.
3. **TRIVIAL** (DTO/**Atoms**):
- Требование: Только Якоря [DEF] и @PURPOSE.
**3. TRIVIAL** (DTO / Атомы UI / Утилиты)
- **Закон:** Каркас. Только якорь `[DEF]` и `@PURPOSE`. Данные и графы не требуются.
#### VI. ЛОГИРОВАНИЕ (ДАО МОЛЕКУЛЫ / MOLECULAR TOPOLOGY)
Цель: Трассировка. Самокоррекция. Управление Матрицей Внимания ("Химия мышления").
@@ -129,10 +117,16 @@
**Незыблемое правило:** Всякому логу системы — тавро `source`. Для Внешенго Мира (Svelte) начертай рунами вручную: `console.log("[ID][REFLECT] Msg")`.
#### VII. АЛГОРИТМ ГЕНЕРАЦИИ
1. АНАЛИЗ. Оцени TIER, слой и UX-требования.
#### VIII. АЛГОРИТМ ГЕНЕРАЦИИ И ВЫХОД ИЗ ТУПИКА
1. АНАЛИЗ. Оцени TIER, слой и UX-требования. Чего не хватает? Запроси `[NEED_CONTEXT: id]`.
2. КАРКАС. Создай `[DEF]`, Header и Контракты.
3. РЕАЛИЗАЦИЯ. Напиши логику, удовлетворяющую Контракту (и UX-состояниям).
3. РЕАЛИЗАЦИЯ. Напиши логику, удовлетворяющую Контракту (и UX-состояниям). Орошай путь логами `[REASON]` и `[REFLECT]`.
4. ЗАМЫКАНИЕ. Закрой все `[/DEF]`.
**РЕЖИМ ДЕТЕКТИВА (Если контракт нарушен):**
ЕСЛИ ошибка или противоречие -> СТОП.
1. Выведи `[COHERENCE_CHECK_FAILED]`.
2. Сформулируй гипотезу: `[EXPLORE] Ошибка в I/O, состоянии или зависимости?`
3. Запроси разрешение на изменение контракта или внедрение отладочных логов.
ЕСЛИ ошибка или противоречие -> СТОП. Выведи `[COHERENCE_CHECK_FAILED]`.

View File

@@ -6,7 +6,7 @@ description: Audit AI-generated unit tests. Your goal is to aggressively search
**OBJECTIVE:** Audit AI-generated unit tests. Your goal is to aggressively search for "Test Tautologies", "Logic Echoing", and "Contract Negligence". You are the final gatekeeper. If a test is meaningless, you MUST reject it.
**INPUT:**
1. SOURCE CODE (with GRACE-Poly `[DEF]` Contract: `@PRE`, `@POST`, `@TEST_DATA`).
1. SOURCE CODE (with GRACE-Poly `[DEF]` Contract: `@PRE`, `@POST`, `@TEST_CONTRACT`, `@TEST_FIXTURE`, `@TEST_EDGE`, `@TEST_INVARIANT`).
2. GENERATED TEST CODE.
### I. CRITICAL ANTI-PATTERNS (REJECT IMMEDIATELY IF FOUND):
@@ -17,7 +17,7 @@ description: Audit AI-generated unit tests. Your goal is to aggressively search
2. **The Logic Mirror (Echoing):**
- *Definition:* The test re-implements the exact same algorithmic logic found in the source code to calculate the `expected_result`. If the original logic is flawed, the test will falsely pass.
- *Rule:* Tests must assert against **static, predefined outcomes** (from `@TEST_DATA` or explicit constants), NOT dynamically calculated outcomes using the same logic as the source.
- *Rule:* Tests must assert against **static, predefined outcomes** (from `@TEST_FIXTURE`, `@TEST_EDGE`, `@TEST_INVARIANT` or explicit constants), NOT dynamically calculated outcomes using the same logic as the source.
3. **The "Happy Path" Illusion:**
- *Definition:* The test suite only checks successful executions but ignores the `@PRE` conditions (Negative Testing).
@@ -26,26 +26,78 @@ description: Audit AI-generated unit tests. Your goal is to aggressively search
4. **Missing Post-Condition Verification:**
- *Definition:* The test calls the function but only checks the return value, ignoring `@SIDE_EFFECT` or `@POST` state changes (e.g., failing to verify that a DB call was made or a Store was updated).
### II. AUDIT CHECKLIST
5. **Missing Edge Case Coverage:**
- *Definition:* The test suite ignores `@TEST_EDGE` scenarios defined in the contract.
- *Rule:* Every `@TEST_EDGE` in the source contract MUST have a corresponding test case.
6. **Missing Invariant Verification:**
- *Definition:* The test suite does not verify `@TEST_INVARIANT` conditions.
- *Rule:* Every `@TEST_INVARIANT` MUST be verified by at least one test that attempts to break it.
7. **Missing UX State Testing (Svelte Components):**
- *Definition:* For Svelte components with `@UX_STATE`, the test suite does not verify state transitions.
- *Rule:* Every `@UX_STATE` transition MUST have a test verifying the visual/behavioral change.
- *Check:* `@UX_FEEDBACK` mechanisms (toast, shake, color) must be tested.
- *Check:* `@UX_RECOVERY` mechanisms (retry, clear input) must be tested.
### II. SEMANTIC PROTOCOL COMPLIANCE
Verify the test file follows GRACE-Poly semantics:
1. **Anchor Integrity:**
- Test file MUST start with `[DEF:__tests__/test_name:Module]`
- Test file MUST end with `[/DEF:__tests__/test_name:Module]`
2. **Required Tags:**
- `@RELATION: VERIFIES -> <path_to_source>` must be present
- `@PURPOSE:` must describe what is being tested
3. **TIER Alignment:**
- If source is `@TIER: CRITICAL`, test MUST cover all `@TEST_CONTRACT`, `@TEST_FIXTURE`, `@TEST_EDGE`, `@TEST_INVARIANT`
- If source is `@TIER: STANDARD`, test MUST cover `@PRE` and `@POST`
- If source is `@TIER: TRIVIAL`, basic smoke test is acceptable
### III. AUDIT CHECKLIST
Evaluate the test code against these criteria:
1. **Target Invocation:** Does the test actually import and call the function/component declared in the `@RELATION: VERIFIES` tag?
2. **Contract Alignment:** Does the test suite cover 100% of the `@PRE` (negative tests) and `@POST` (assertions) conditions from the source contract?
3. **Data Usage:** Does the test use the exact scenarios defined in `@TEST_DATA`?
4. **Mocking Sanity:** Are external dependencies mocked correctly WITHOUT mocking the system under test itself?
3. **Test Contract Compliance:** Does the test follow the interface defined in `@TEST_CONTRACT`?
4. **Data Usage:** Does the test use the exact scenarios defined in `@TEST_FIXTURE`?
5. **Edge Coverage:** Are all `@TEST_EDGE` scenarios tested?
6. **Invariant Coverage:** Are all `@TEST_INVARIANT` conditions verified?
7. **UX Coverage (if applicable):** Are all `@UX_STATE`, `@UX_FEEDBACK`, `@UX_RECOVERY` tested?
8. **Mocking Sanity:** Are external dependencies mocked correctly WITHOUT mocking the system under test itself?
9. **Semantic Anchor:** Does the test file have proper `[DEF]` and `[/DEF]` anchors?
### III. OUTPUT FORMAT
### IV. OUTPUT FORMAT
You MUST respond strictly in the following JSON format. Do not add markdown blocks outside the JSON.
{
"verdict": "APPROVED" | "REJECTED",
"rejection_reason": "TAUTOLOGY" | "LOGIC_MIRROR" | "WEAK_CONTRACT_COVERAGE" | "OVER_MOCKED" | "NONE",
"rejection_reason": "TAUTOLOGY" | "LOGIC_MIRROR" | "WEAK_CONTRACT_COVERAGE" | "OVER_MOCKED" | "MISSING_EDGES" | "MISSING_INVARIANTS" | "MISSING_UX_TESTS" | "SEMANTIC_VIOLATION" | "NONE",
"audit_details": {
"target_invoked": true/false,
"pre_conditions_tested": true/false,
"post_conditions_tested": true/false,
"test_data_used": true/false
"test_fixture_used": true/false,
"edges_covered": true/false,
"invariants_verified": true/false,
"ux_states_tested": true/false,
"semantic_anchors_present": true/false
},
"coverage_summary": {
"total_edges": number,
"edges_tested": number,
"total_invariants": number,
"invariants_tested": number,
"total_ux_states": number,
"ux_states_tested": number
},
"tier_compliance": {
"source_tier": "CRITICAL" | "STANDARD" | "TRIVIAL",
"meets_tier_requirements": true/false
},
"feedback": "Strict, actionable feedback for the test generator agent. Explain exactly which anti-pattern was detected and how to fix it."
}

View File

@@ -1,4 +1,4 @@
---
description: USE SEMANTIC
---
Прочитай .specify/memory/semantics.md (или .ai/standards/semantics.md, если не найден). ОБЯЗАТЕЛЬНО используй его при разработке
Прочитай .ai/standards/semantics.md. ОБЯЗАТЕЛЬНО используй его при разработке

View File

@@ -63,6 +63,7 @@ Load only the minimal necessary context from each artifact:
**From constitution:**
- Load `.ai/standards/constitution.md` for principle validation
- Load `.ai/standards/semantics.md` for technical standard validation
### 3. Build Semantic Models

View File

@@ -20,7 +20,7 @@ Analyze test failure reports, identify root causes, and fix implementation issue
1. **USE CODER MODE**: Always switch to `coder` mode for code fixes
2. **SEMANTIC PROTOCOL**: Never remove semantic annotations ([DEF], @TAGS). Only update code logic.
3. **TEST DATA**: If tests use @TEST_DATA fixtures, preserve them when fixing
3. **TEST DATA**: If tests use @TEST_ fixtures, preserve them when fixing
4. **NO DELETION**: Never delete existing tests or semantic annotations
5. **REPORT FIRST**: Always write a fix report before making changes

View File

@@ -53,6 +53,15 @@ You **MUST** consider the user input before proceeding (if not empty).
- **IF EXISTS**: Read research.md for technical decisions and constraints
- **IF EXISTS**: Read quickstart.md for integration scenarios
3. Load and analyze the implementation context:
- **REQUIRED**: Read `.ai/standards/semantics.md` for strict coding standards and contract requirements
- **REQUIRED**: Read tasks.md for the complete task list and execution plan
- **REQUIRED**: Read plan.md for tech stack, architecture, and file structure
- **IF EXISTS**: Read data-model.md for entities and relationships
- **IF EXISTS**: Read contracts/ for API specifications and test requirements
- **IF EXISTS**: Read research.md for technical decisions and constraints
- **IF EXISTS**: Read quickstart.md for integration scenarios
4. **Project Setup Verification**:
- **REQUIRED**: Create/verify ignore files based on actual project setup:
@@ -111,7 +120,13 @@ You **MUST** consider the user input before proceeding (if not empty).
- **Validation checkpoints**: Verify each phase completion before proceeding
7. Implementation execution rules:
- **Setup first**: Initialize project structure, dependencies, configuration
- **Strict Adherence**: Apply `.ai/standards/semantics.md` rules:
- Every file MUST start with a `[DEF:id:Type]` header and end with a closing `[/DEF:id:Type]` anchor.
- Include `@TIER` and define contracts (`@PRE`, `@POST`).
- For Svelte components, use `@UX_STATE`, `@UX_FEEDBACK`, `@UX_RECOVERY`, and explicitly declare reactivity with `@UX_REATIVITY: State: $state, Derived: $derived`.
- **Molecular Topology Logging**: Use prefixes `[EXPLORE]`, `[REASON]`, `[REFLECT]` in logs to trace logic.
- **CRITICAL Contracts**: If a task description contains a contract summary (e.g., `CRITICAL: PRE: ..., POST: ...`), these constraints are **MANDATORY** and must be strictly implemented in the code using guards/assertions (if applicable per protocol).
- **Setup first**: Initialize project structure, dependencies, configuration
- **Tests before code**: If you need to write tests for contracts, entities, and integration scenarios
- **Core development**: Implement models, services, CLI commands, endpoints
- **Integration work**: Database connections, middleware, logging, external services

View File

@@ -22,7 +22,7 @@ You **MUST** consider the user input before proceeding (if not empty).
1. **Setup**: Run `.specify/scripts/bash/setup-plan.sh --json` from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
2. **Load context**: Read FEATURE_SPEC and `.ai/standards/constitution.md`. Load IMPL_PLAN template (already copied).
2. **Load context**: Read `.ai/ROOT.md` and `.ai/PROJECT_MAP.md` to understand the project structure and navigation. Then read required standards: `.ai/standards/constitution.md` and `.ai/standards/semantics.md`. Load IMPL_PLAN template.
3. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to:
- Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")
@@ -64,16 +64,30 @@ You **MUST** consider the user input before proceeding (if not empty).
**Prerequisites:** `research.md` complete
1. **Extract entities from feature spec** → `data-model.md`:
- Entity name, fields, relationships
- Validation rules from requirements
- State transitions if applicable
0. **Validate Design against UX Reference**:
- Check if the proposed architecture supports the latency, interactivity, and flow defined in `ux_reference.md`.
- **Linkage**: Ensure key UI states from `ux_reference.md` map to Component Contracts (`@UX_STATE`).
- **CRITICAL**: If the technical plan compromises the UX (e.g. "We can't do real-time validation"), you **MUST STOP** and warn the user.
2. **Define interface contracts** (if project has external interfaces) → `/contracts/`:
- Identify what interfaces the project exposes to users or other systems
- Document the contract format appropriate for the project type
- Examples: public APIs for libraries, command schemas for CLI tools, endpoints for web services, grammars for parsers, UI contracts for applications
- Skip if project is purely internal (build scripts, one-off tools, etc.)
1. **Extract entities from feature spec** → `data-model.md`:
- Entity name, fields, relationships, validation rules.
2. **Design & Verify Contracts (Semantic Protocol)**:
- **Drafting**: Define `[DEF:id:Type]` Headers, Contracts, and closing `[/DEF:id:Type]` for all new modules based on `.ai/standards/semantics.md`.
- **TIER Classification**: Explicitly assign `@TIER: [CRITICAL|STANDARD|TRIVIAL]` to each module.
- **CRITICAL Requirements**: For all CRITICAL modules, define full `@PRE`, `@POST`, and (if UI) `@UX_STATE` contracts. **MUST** also define testing contracts: `@TEST_CONTRACT`, `@TEST_FIXTURE`, `@TEST_EDGE`, and `@TEST_INVARIANT`.
- **Self-Review**:
- *Completeness*: Do `@PRE`/`@POST` cover edge cases identified in Research? Are test contracts present for CRITICAL?
- *Connectivity*: Do `@RELATION` tags form a coherent graph?
- *Compliance*: Does syntax match `[DEF:id:Type]` exactly and is it closed with `[/DEF:id:Type]`?
- **Output**: Write verified contracts to `contracts/modules.md`.
3. **Simulate Contract Usage**:
- Trace one key user scenario through the defined contracts to ensure data flow continuity.
- If a contract interface mismatch is found, fix it immediately.
4. **Generate API contracts**:
- Output OpenAPI/GraphQL schema to `/contracts/` for backend-frontend sync.
3. **Agent context update**:
- Run `.specify/scripts/bash/update-agent-context.sh agy`

View File

@@ -24,7 +24,7 @@ You **MUST** consider the user input before proceeding (if not empty).
1. **Setup**: Run `.specify/scripts/bash/check-prerequisites.sh --json` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
2. **Load design documents**: Read from FEATURE_DIR:
- **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities)
- **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities), ux_reference.md (experience source of truth)
- **Optional**: data-model.md (entities), contracts/ (interface contracts), research.md (decisions), quickstart.md (test scenarios)
- Note: Not all projects have all documents. Generate tasks based on what's available.
@@ -70,6 +70,12 @@ The tasks.md should be immediately executable - each task must be specific enoug
**Tests are OPTIONAL**: Only generate test tasks if explicitly requested in the feature specification or if user requests TDD approach.
### UX Preservation (CRITICAL)
- **Source of Truth**: `ux_reference.md` is the absolute standard for the "feel" of the feature.
- **Violation Warning**: If any task would inherently violate the UX (e.g. "Remove progress bar to simplify code"), you **MUST** flag this to the user immediately.
- **Verification Task**: You **MUST** add a specific task at the end of each User Story phase: `- [ ] Txxx [USx] Verify implementation matches ux_reference.md (Happy Path & Errors)`
### Checklist Format (REQUIRED)
Every task MUST strictly follow this format:
@@ -113,9 +119,12 @@ Every task MUST strictly follow this format:
- If tests requested: Tests specific to that story
- Mark story dependencies (most stories should be independent)
2. **From Contracts**:
- Map each interface contract → to the user story it serves
- If tests requested: Each interface contract → contract test task [P] before implementation in that story's phase
2. **From Contracts (CRITICAL TIER)**:
- Identify components marked as `@TIER: CRITICAL` in `contracts/modules.md`.
- For these components, **MUST** append the summary of `@PRE`, `@POST`, `@UX_STATE`, and test contracts (`@TEST_FIXTURE`, `@TEST_EDGE`) directly to the task description.
- Example: `- [ ] T005 [P] [US1] Implement Auth (CRITICAL: PRE: token exists, POST: returns User, TESTS: 2 edges) in src/auth.py`
- Map each contract/endpoint → to the user story it serves
- If tests requested: Each contract → contract test task [P] before implementation in that story's phase
3. **From Data Model**:
- Map each entity to the user story(ies) that need it

View File

@@ -20,7 +20,7 @@ Execute full testing cycle: analyze code for testable modules, write tests with
1. **NEVER delete existing tests** - Only update if they fail due to bugs in the test or implementation
2. **NEVER duplicate tests** - Check existing tests first before creating new ones
3. **Use TEST_DATA fixtures** - For CRITICAL tier modules, read @TEST_DATA from .specify/memory/semantics.md
3. **Use TEST_FIXTURE fixtures** - For CRITICAL tier modules, read @TEST_FIXTURE from semantics header
4. **Co-location required** - Write tests in `__tests__` directories relative to the code being tested
## Execution Steps
@@ -40,9 +40,9 @@ Determine:
- Identify completed implementation tasks (not test tasks)
- Extract file paths that need tests
**From .specify/memory/semantics.md:**
**From .ai/standards/semantics.md:**
- Read @TIER annotations for modules
- For CRITICAL modules: Read @TEST_DATA fixtures
- For CRITICAL modules: Read @TEST_ fixtures
**From existing tests:**
- Scan `__tests__` directories for existing tests
@@ -52,8 +52,8 @@ Determine:
Create coverage matrix:
| Module | File | Has Tests | TIER | TEST_DATA Available |
|--------|------|-----------|------|-------------------|
| Module | File | Has Tests | TIER | TEST_FIXTURE Available |
|--------|------|-----------|------|----------------------|
| ... | ... | ... | ... | ... |
### 4. Write Tests (TDD Approach)
@@ -61,7 +61,7 @@ Create coverage matrix:
For each module requiring tests:
1. **Check existing tests**: Scan `__tests__/` for duplicates
2. **Read TEST_DATA**: If CRITICAL tier, read @TEST_DATA from .specify/memory/semantics.md
2. **Read TEST_FIXTURE**: If CRITICAL tier, read @TEST_FIXTURE from semantic header
3. **Write test**: Follow co-location strategy
- Python: `src/module/__tests__/test_module.py`
- Svelte: `src/lib/components/__tests__/test_component.test.js`
@@ -102,6 +102,7 @@ describe('Component UX States', () => {
// @UX_RECOVERY: Retry on error
it('should allow retry on error', async () => { ... });
});
// [/DEF:__tests__/test_Component:Module]
```
### 5. Test Documentation
@@ -170,7 +171,7 @@ Generate test execution report:
- [ ] Fix failed tests
- [ ] Add more coverage for [module]
- [ ] Review TEST_DATA fixtures
- [ ] Review TEST_FIXTURE fixtures
```
## Context for Testing

View File

@@ -45,6 +45,8 @@ Auto-generated from all feature plans. Last updated: 2025-12-19
- SQLite task/result persistence (existing task DB), filesystem only for existing artifacts (no new primary store required) (020-task-reports-design)
- Node.js 18+ runtime, SvelteKit (existing frontend stack) + SvelteKit, Tailwind CSS, existing frontend UI primitives under `frontend/src/lib/components/ui` (001-unify-frontend-style)
- N/A (UI styling and component behavior only) (001-unify-frontend-style)
- Python 3.9+ (backend scripts/services), Shell (release tooling) + FastAPI stack (existing backend), ConfigManager, TaskManager, файловые утилиты, internal artifact registries (020-clean-repo-enterprise)
- PostgreSQL (конфигурации/метаданные), filesystem (артефакты дистрибутива, отчёты проверки) (020-clean-repo-enterprise)
- Python 3.9+ (Backend), Node.js 18+ (Frontend Build) (001-plugin-arch-svelte-ui)
@@ -65,9 +67,9 @@ cd src; pytest; ruff check .
Python 3.9+ (Backend), Node.js 18+ (Frontend Build): Follow standard conventions
## Recent Changes
- 020-clean-repo-enterprise: Added Python 3.9+ (backend scripts/services), Shell (release tooling) + FastAPI stack (existing backend), ConfigManager, TaskManager, файловые утилиты, internal artifact registries
- 001-unify-frontend-style: Added Node.js 18+ runtime, SvelteKit (existing frontend stack) + SvelteKit, Tailwind CSS, existing frontend UI primitives under `frontend/src/lib/components/ui`
- 020-task-reports-design: Added Python 3.9+ (backend), Node.js 18+ (frontend) + FastAPI, SvelteKit, Tailwind CSS, SQLAlchemy/Pydantic task models, existing task/websocket stack
- 019-superset-ux-redesign: Added Python 3.9+ (Backend), Node.js 18+ (Frontend) + FastAPI, SvelteKit, Tailwind CSS, SQLAlchemy, WebSocket (existing)
<!-- MANUAL ADDITIONS START -->

View File

@@ -0,0 +1,103 @@
---
description: Audit AI-generated unit tests. Your goal is to aggressively search for "Test Tautologies", "Logic Echoing", and "Contract Negligence". You are the final gatekeeper. If a test is meaningless, you MUST reject it.
---
**ROLE:** Elite Quality Assurance Architect and Red Teamer.
**OBJECTIVE:** Audit AI-generated unit tests. Your goal is to aggressively search for "Test Tautologies", "Logic Echoing", and "Contract Negligence". You are the final gatekeeper. If a test is meaningless, you MUST reject it.
**INPUT:**
1. SOURCE CODE (with GRACE-Poly `[DEF]` Contract: `@PRE`, `@POST`, `@TEST_CONTRACT`, `@TEST_FIXTURE`, `@TEST_EDGE`, `@TEST_INVARIANT`).
2. GENERATED TEST CODE.
### I. CRITICAL ANTI-PATTERNS (REJECT IMMEDIATELY IF FOUND):
1. **The Tautology (Self-Fulfilling Prophecy):**
- *Definition:* The test asserts hardcoded values against hardcoded values without executing the core business logic, or mocks the actual function being tested.
- *Example of Failure:* `assert 2 + 2 == 4` or mocking the class under test so that it returns exactly what the test asserts.
2. **The Logic Mirror (Echoing):**
- *Definition:* The test re-implements the exact same algorithmic logic found in the source code to calculate the `expected_result`. If the original logic is flawed, the test will falsely pass.
- *Rule:* Tests must assert against **static, predefined outcomes** (from `@TEST_FIXTURE`, `@TEST_EDGE`, `@TEST_INVARIANT` or explicit constants), NOT dynamically calculated outcomes using the same logic as the source.
3. **The "Happy Path" Illusion:**
- *Definition:* The test suite only checks successful executions but ignores the `@PRE` conditions (Negative Testing).
- *Rule:* Every `@PRE` tag in the source contract MUST have a corresponding test that deliberately violates it and asserts the correct Exception/Error state.
4. **Missing Post-Condition Verification:**
- *Definition:* The test calls the function but only checks the return value, ignoring `@SIDE_EFFECT` or `@POST` state changes (e.g., failing to verify that a DB call was made or a Store was updated).
5. **Missing Edge Case Coverage:**
- *Definition:* The test suite ignores `@TEST_EDGE` scenarios defined in the contract.
- *Rule:* Every `@TEST_EDGE` in the source contract MUST have a corresponding test case.
6. **Missing Invariant Verification:**
- *Definition:* The test suite does not verify `@TEST_INVARIANT` conditions.
- *Rule:* Every `@TEST_INVARIANT` MUST be verified by at least one test that attempts to break it.
7. **Missing UX State Testing (Svelte Components):**
- *Definition:* For Svelte components with `@UX_STATE`, the test suite does not verify state transitions.
- *Rule:* Every `@UX_STATE` transition MUST have a test verifying the visual/behavioral change.
- *Check:* `@UX_FEEDBACK` mechanisms (toast, shake, color) must be tested.
- *Check:* `@UX_RECOVERY` mechanisms (retry, clear input) must be tested.
### II. SEMANTIC PROTOCOL COMPLIANCE
Verify the test file follows GRACE-Poly semantics:
1. **Anchor Integrity:**
- Test file MUST start with `[DEF:__tests__/test_name:Module]`
- Test file MUST end with `[/DEF:__tests__/test_name:Module]`
2. **Required Tags:**
- `@RELATION: VERIFIES -> <path_to_source>` must be present
- `@PURPOSE:` must describe what is being tested
3. **TIER Alignment:**
- If source is `@TIER: CRITICAL`, test MUST cover all `@TEST_CONTRACT`, `@TEST_FIXTURE`, `@TEST_EDGE`, `@TEST_INVARIANT`
- If source is `@TIER: STANDARD`, test MUST cover `@PRE` and `@POST`
- If source is `@TIER: TRIVIAL`, basic smoke test is acceptable
### III. AUDIT CHECKLIST
Evaluate the test code against these criteria:
1. **Target Invocation:** Does the test actually import and call the function/component declared in the `@RELATION: VERIFIES` tag?
2. **Contract Alignment:** Does the test suite cover 100% of the `@PRE` (negative tests) and `@POST` (assertions) conditions from the source contract?
3. **Test Contract Compliance:** Does the test follow the interface defined in `@TEST_CONTRACT`?
4. **Data Usage:** Does the test use the exact scenarios defined in `@TEST_FIXTURE`?
5. **Edge Coverage:** Are all `@TEST_EDGE` scenarios tested?
6. **Invariant Coverage:** Are all `@TEST_INVARIANT` conditions verified?
7. **UX Coverage (if applicable):** Are all `@UX_STATE`, `@UX_FEEDBACK`, `@UX_RECOVERY` tested?
8. **Mocking Sanity:** Are external dependencies mocked correctly WITHOUT mocking the system under test itself?
9. **Semantic Anchor:** Does the test file have proper `[DEF]` and `[/DEF]` anchors?
### IV. OUTPUT FORMAT
You MUST respond strictly in the following JSON format. Do not add markdown blocks outside the JSON.
{
"verdict": "APPROVED" | "REJECTED",
"rejection_reason": "TAUTOLOGY" | "LOGIC_MIRROR" | "WEAK_CONTRACT_COVERAGE" | "OVER_MOCKED" | "MISSING_EDGES" | "MISSING_INVARIANTS" | "MISSING_UX_TESTS" | "SEMANTIC_VIOLATION" | "NONE",
"audit_details": {
"target_invoked": true/false,
"pre_conditions_tested": true/false,
"post_conditions_tested": true/false,
"test_fixture_used": true/false,
"edges_covered": true/false,
"invariants_verified": true/false,
"ux_states_tested": true/false,
"semantic_anchors_present": true/false
},
"coverage_summary": {
"total_edges": number,
"edges_tested": number,
"total_invariants": number,
"invariants_tested": number,
"total_ux_states": number,
"ux_states_tested": number
},
"tier_compliance": {
"source_tier": "CRITICAL" | "STANDARD" | "TRIVIAL",
"meets_tier_requirements": true/false
},
"feedback": "Strict, actionable feedback for the test generator agent. Explain exactly which anti-pattern was detected and how to fix it."
}

View File

@@ -20,7 +20,7 @@ Analyze test failure reports, identify root causes, and fix implementation issue
1. **USE CODER MODE**: Always switch to `coder` mode for code fixes
2. **SEMANTIC PROTOCOL**: Never remove semantic annotations ([DEF], @TAGS). Only update code logic.
3. **TEST DATA**: If tests use @TEST_DATA fixtures, preserve them when fixing
3. **TEST DATA**: If tests use @TEST_ fixtures, preserve them when fixing
4. **NO DELETION**: Never delete existing tests or semantic annotations
5. **REPORT FIRST**: Always write a fix report before making changes

View File

@@ -117,7 +117,11 @@ You **MUST** consider the user input before proceeding (if not empty).
- **Validation checkpoints**: Verify each phase completion before proceeding
7. Implementation execution rules:
- **Strict Adherence**: Apply `.ai/standards/semantics.md` rules - every file must start with [DEF] header, include @TIER, and define contracts.
- **Strict Adherence**: Apply `.ai/standards/semantics.md` rules:
- Every file MUST start with a `[DEF:id:Type]` header and end with a closing `[/DEF:id:Type]` anchor.
- Include `@TIER` and define contracts (`@PRE`, `@POST`).
- For Svelte components, use `@UX_STATE`, `@UX_FEEDBACK`, `@UX_RECOVERY`, and explicitly declare reactivity with `@UX_REATIVITY: State: $state, Derived: $derived`.
- **Molecular Topology Logging**: Use prefixes `[EXPLORE]`, `[REASON]`, `[REFLECT]` in logs to trace logic.
- **CRITICAL Contracts**: If a task description contains a contract summary (e.g., `CRITICAL: PRE: ..., POST: ...`), these constraints are **MANDATORY** and must be strictly implemented in the code using guards/assertions (if applicable per protocol).
- **Setup first**: Initialize project structure, dependencies, configuration
- **Tests before code**: If you need to write tests for contracts, entities, and integration scenarios

View File

@@ -73,13 +73,13 @@ You **MUST** consider the user input before proceeding (if not empty).
- Entity name, fields, relationships, validation rules.
2. **Design & Verify Contracts (Semantic Protocol)**:
- **Drafting**: Define [DEF] Headers and Contracts for all new modules based on `.ai/standards/semantics.md`.
- **Drafting**: Define `[DEF:id:Type]` Headers, Contracts, and closing `[/DEF:id:Type]` for all new modules based on `.ai/standards/semantics.md`.
- **TIER Classification**: Explicitly assign `@TIER: [CRITICAL|STANDARD|TRIVIAL]` to each module.
- **CRITICAL Requirements**: For all CRITICAL modules, define full `@PRE`, `@POST`, and (if UI) `@UX_STATE` contracts.
- **CRITICAL Requirements**: For all CRITICAL modules, define full `@PRE`, `@POST`, and (if UI) `@UX_STATE` contracts. **MUST** also define testing contracts: `@TEST_CONTRACT`, `@TEST_FIXTURE`, `@TEST_EDGE`, and `@TEST_INVARIANT`.
- **Self-Review**:
- *Completeness*: Do `@PRE`/`@POST` cover edge cases identified in Research?
- *Completeness*: Do `@PRE`/`@POST` cover edge cases identified in Research? Are test contracts present for CRITICAL?
- *Connectivity*: Do `@RELATION` tags form a coherent graph?
- *Compliance*: Does syntax match `[DEF:id:Type]` exactly?
- *Compliance*: Does syntax match `[DEF:id:Type]` exactly and is it closed with `[/DEF:id:Type]`?
- **Output**: Write verified contracts to `contracts/modules.md`.
3. **Simulate Contract Usage**:

View File

@@ -121,8 +121,8 @@ Every task MUST strictly follow this format:
2. **From Contracts (CRITICAL TIER)**:
- Identify components marked as `@TIER: CRITICAL` in `contracts/modules.md`.
- For these components, **MUST** append the summary of `@PRE`, `@POST`, and `@UX_STATE` contracts directly to the task description.
- Example: `- [ ] T005 [P] [US1] Implement Auth (CRITICAL: PRE: token exists, POST: returns User) in src/auth.py`
- For these components, **MUST** append the summary of `@PRE`, `@POST`, `@UX_STATE`, and test contracts (`@TEST_FIXTURE`, `@TEST_EDGE`) directly to the task description.
- Example: `- [ ] T005 [P] [US1] Implement Auth (CRITICAL: PRE: token exists, POST: returns User, TESTS: 2 edges) in src/auth.py`
- Map each contract/endpoint → to the user story it serves
- If tests requested: Each contract → contract test task [P] before implementation in that story's phase

View File

@@ -20,7 +20,7 @@ Execute full testing cycle: analyze code for testable modules, write tests with
1. **NEVER delete existing tests** - Only update if they fail due to bugs in the test or implementation
2. **NEVER duplicate tests** - Check existing tests first before creating new ones
3. **Use TEST_DATA fixtures** - For CRITICAL tier modules, read @TEST_DATA from .ai/standards/semantics.md
3. **Use TEST_FIXTURE fixtures** - For CRITICAL tier modules, read @TEST_FIXTURE from .ai/standards/semantics.md
4. **Co-location required** - Write tests in `__tests__` directories relative to the code being tested
## Execution Steps
@@ -42,7 +42,7 @@ Determine:
**From .ai/standards/semantics.md:**
- Read @TIER annotations for modules
- For CRITICAL modules: Read @TEST_DATA fixtures
- For CRITICAL modules: Read @TEST_ fixtures
**From existing tests:**
- Scan `__tests__` directories for existing tests
@@ -52,8 +52,8 @@ Determine:
Create coverage matrix:
| Module | File | Has Tests | TIER | TEST_DATA Available |
|--------|------|-----------|------|-------------------|
| Module | File | Has Tests | TIER | TEST_FIXTURE Available |
|--------|------|-----------|------|----------------------|
| ... | ... | ... | ... | ... |
### 4. Write Tests (TDD Approach)
@@ -61,7 +61,7 @@ Create coverage matrix:
For each module requiring tests:
1. **Check existing tests**: Scan `__tests__/` for duplicates
2. **Read TEST_DATA**: If CRITICAL tier, read @TEST_DATA from .ai/standards/semantics.md
2. **Read TEST_FIXTURE**: If CRITICAL tier, read @TEST_FIXTURE from semantics header
3. **Write test**: Follow co-location strategy
- Python: `src/module/__tests__/test_module.py`
- Svelte: `src/lib/components/__tests__/test_component.test.js`
@@ -102,6 +102,7 @@ describe('Component UX States', () => {
// @UX_RECOVERY: Retry on error
it('should allow retry on error', async () => { ... });
});
// [/DEF:__tests__/test_Component:Module]
```
### 5. Test Documentation
@@ -170,7 +171,7 @@ Generate test execution report:
- [ ] Fix failed tests
- [ ] Add more coverage for [module]
- [ ] Review TEST_DATA fixtures
- [ ] Review TEST_FIXTURE fixtures
```
## Context for Testing

337
README.md
View File

@@ -1,143 +1,276 @@
# ss-tools
Инструменты автоматизации для Apache Superset: миграция, маппинг, хранение артефактов, Git-интеграция, отчеты по задачам и LLM-assistant.
**Инструменты автоматизации для Apache Superset: миграция, версионирование, аналитика и управление данными**
## Возможности
- Миграция дашбордов и датасетов между окружениями.
- Ручной и полуавтоматический маппинг ресурсов.
- Логи фоновых задач и отчеты о выполнении.
- Локальное хранилище файлов и бэкапов.
- Git-операции по Superset-ассетам через UI.
- Модуль LLM-анализа и assistant API.
- Многопользовательская авторизация (RBAC).
## 📋 О проекте
## Стек
- Backend: Python, FastAPI, SQLAlchemy, APScheduler.
- Frontend: SvelteKit, Vite, Tailwind CSS.
- База данных: PostgreSQL (основная конфигурация), поддержка миграции с legacy SQLite.
ss-tools — это комплексная платформа для автоматизации работы с Apache Superset, предоставляющая инструменты для миграции дашбордов, управления версиями через Git, LLM-анализа данных и многопользовательского контроля доступа. Система построена на модульной архитектуре с плагинной системой расширений.
## Структура репозитория
- `backend/` — API, плагины, сервисы, скрипты миграции и тесты.
- `frontend/` — SPA-интерфейс (SvelteKit).
- `docs/` — документация по архитектуре и плагинам.
- `specs/` — спецификации и планы реализации.
- `docker/` и `docker-compose.yml` — контейнеризация.
### 🎯 Ключевые возможности
## Быстрый старт (локально)
#### 🔄 Миграция данных
- **Миграция дашбордов и датасетов** между окружениями (dev/staging/prod)
- **Dry-run режим** с детальным анализом рисков и предпросмотром изменений
- **Автоматическое маппинг** баз данных и ресурсов между окружениями
- **Поддержка legacy-данных** с миграцией из SQLite в PostgreSQL
#### 🌿 Git-интеграция
- **Версионирование** дашбордов через Git-репозитории
- **Управление ветками** и коммитами с помощью LLM
- **Деплой** дашбордов из Git в целевые окружения
- **История изменений** с детальным diff
#### 🤖 LLM-аналитика
- **Автоматическая валидация** дашбордов с помощью ИИ
- **Генерация документации** для датасетов
- **Assistant API** для natural language команд
- **Интеллектуальное коммитинг** с подсказками сообщений
#### 📊 Управление и мониторинг
- **Многопользовательская авторизация** (RBAC)
- **Фоновые задачи** с реальным логированием через WebSocket
- **Унифицированные отчеты** по выполненным задачам
- **Хранение артефактов** с политиками retention
- **Аудит логирование** всех действий
#### 🔌 Плагины
- **MigrationPlugin** — миграция дашбордов
- **BackupPlugin** — резервное копирование
- **GitPlugin** — управление версиями
- **LLMAnalysisPlugin** — аналитика и документация
- **MapperPlugin** — маппинг колонок
- **DebugPlugin** — диагностика системы
- **SearchPlugin** — поиск по датасетам
## 🏗️ Архитектура
### Технологический стек
**Backend:**
- Python 3.9+ (FastAPI, SQLAlchemy, APScheduler)
- PostgreSQL (основная БД)
- GitPython для Git-операций
- OpenAI API для LLM-функций
- Playwright для скриншотов
**Frontend:**
- SvelteKit (Svelte 5.x)
- Vite
- Tailwind CSS
- WebSocket для реального логирования
**DevOps:**
- Docker & Docker Compose
- PostgreSQL 16
### Модульная структура
```
ss-tools/
├── backend/ # Backend API
│ ├── src/
│ │ ├── api/ # API маршруты
│ │ ├── core/ # Ядро системы
│ │ │ ├── task_manager/ # Управление задачами
│ │ │ ├── auth/ # Авторизация
│ │ │ ├── migration/ # Миграция данных
│ │ │ └── plugins/ # Плагины
│ │ ├── models/ # Модели данных
│ │ ├── services/ # Бизнес-логика
│ │ └── schemas/ # Pydantic схемы
│ └── tests/ # Тесты
├── frontend/ # SvelteKit приложение
│ ├── src/
│ │ ├── routes/ # Страницы
│ │ ├── lib/
│ │ │ ├── components/ # UI компоненты
│ │ │ ├── stores/ # Svelte stores
│ │ │ └── api/ # API клиент
│ │ └── i18n/ # Мультиязычность
│ └── tests/
├── docker/ # Docker конфигурация
├── docs/ # Документация
└── specs/ # Спецификации
```
## 🚀 Быстрый старт
### Требования
**Локальная разработка:**
- Python 3.9+
- Node.js 18+
- npm
- 2 GB RAM (минимум)
- 5 GB свободного места
**Docker (рекомендуется):**
- Docker Engine 24+
- Docker Compose v2
- 4 GB RAM (для стабильной работы)
### Установка и запуск
#### Вариант 1: Docker (рекомендуется)
### Запуск backend + frontend одним скриптом
```bash
./run.sh
```
# Клонирование репозитория
git clone <repository-url>
cd ss-tools
Что делает `run.sh`:
- проверяет версии Python/npm;
- создает `backend/.venv` (если нет);
- устанавливает `backend/requirements.txt` и `frontend` зависимости;
- запускает backend и frontend параллельно.
Опции:
- `./run.sh --skip-install` — пропустить установку зависимостей.
- `./run.sh --help` — показать справку.
Переменные окружения для локального запуска:
- `BACKEND_PORT` (по умолчанию `8000`)
- `FRONTEND_PORT` (по умолчанию `5173`)
- `POSTGRES_URL`
- `DATABASE_URL`
- `TASKS_DATABASE_URL`
- `AUTH_DATABASE_URL`
## Docker
### Запуск
```bash
# Запуск всех сервисов
docker compose up --build
# После запуска:
# Frontend: http://localhost:8000
# Backend API: http://localhost:8001
# PostgreSQL: localhost:5432
```
После старта сервисы доступны по адресам:
- Frontend: `http://localhost:8000`
- Backend API: `http://localhost:8001`
- PostgreSQL: `localhost:5432` (`postgres/postgres`, БД `ss_tools`)
#### Вариант 2: Локально
### Остановка
```bash
docker compose down
```
### Очистка БД-тома
```bash
docker compose down -v
```
### Альтернативный образ PostgreSQL
Если есть проблемы с pull `postgres:16-alpine`:
```bash
POSTGRES_IMAGE=mirror.gcr.io/library/postgres:16-alpine docker compose up -d db
```
или
```bash
POSTGRES_IMAGE=bitnami/postgresql:latest docker compose up -d db
```
Если порт `5432` занят:
```bash
POSTGRES_HOST_PORT=5433 docker compose up -d db
```
## Разработка
### Ручной запуск сервисов
```bash
# Backend
cd backend
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
python3 -m uvicorn src.app:app --reload --port 8000
```
В другом терминале:
```bash
# Frontend (в новом терминале)
cd frontend
npm install
npm run dev -- --port 5173
```
### Тесты
Backend:
```bash
cd backend
source .venv/bin/activate
pytest
```
### Первичная настройка
Frontend:
```bash
cd frontend
npm run test
```
## Инициализация auth (опционально)
```bash
# Инициализация БД
cd backend
source .venv/bin/activate
python src/scripts/init_auth_db.py
# Создание администратора
python src/scripts/create_admin.py --username admin --password admin
```
## Миграция legacy-данных (опционально)
## 🏢 Enterprise Clean Deployment (internal-only)
Для разворота в корпоративной сети используйте профиль enterprise clean:
- очищенный дистрибутив без test/demo/load-test данных;
- запрет внешних интернет-источников;
- загрузка ресурсов только с внутренних серверов компании;
- обязательная блокирующая проверка clean/compliance перед выпуском.
Быстрый запуск TUI-проверки:
```bash
cd backend
source .venv/bin/activate
PYTHONPATH=. python src/scripts/migrate_sqlite_to_postgres.py --sqlite-path tasks.db
cd /home/busya/dev/ss-tools
./backend/.venv/bin/python3 -m backend.src.scripts.clean_release_tui
```
## Дополнительная документация
- `docs/plugin_dev.md`
- `docs/settings.md`
- `semantic_protocol.md`
Типовые внутренние источники:
- `repo.intra.company.local`
- `artifacts.intra.company.local`
- `pypi.intra.company.local`
Если найден внешний endpoint, выпуск получает статус `BLOCKED` до исправления.
## 📖 Документация
- [Установка и настройка](docs/installation.md)
- [Архитектура системы](docs/architecture.md)
- [Разработка плагинов](docs/plugin_dev.md)
- [API документация](http://localhost:8001/docs)
- [Настройка окружений](docs/settings.md)
## 🧪 Тестирование
```bash
# Backend тесты
cd backend
source .venv/bin/activate
pytest
# Frontend тесты
cd frontend
npm run test
# Запуск конкретного теста
pytest tests/test_auth.py::test_create_user
```
## 🔐 Авторизация
Система поддерживает два метода аутентификации:
1. **Локальная аутентификация** (username/password)
2. **ADFS SSO** (Active Directory Federation Services)
### Управление пользователями и ролями
```bash
# Получение списка пользователей
GET /api/admin/users
# Создание пользователя
POST /api/admin/users
{
"username": "newuser",
"email": "user@example.com",
"password": "password123",
"roles": ["analyst"]
}
# Создание роли
POST /api/admin/roles
{
"name": "analyst",
"permissions": ["dashboards:read", "dashboards:write"]
}
```
## 📊 Мониторинг
### Отчеты о задачах
```bash
# Список всех отчетов
GET /api/reports?page=1&page_size=20
# Детали отчета
GET /api/reports/{report_id}
# Фильтры
GET /api/reports?status=failed&task_type=validation&date_from=2024-01-01
```
### Активность
- **Dashboard Hub** — управление дашбордами с Git-статусом
- **Dataset Hub** — управление датасетами с прогрессом маппинга
- **Task Drawer** — мониторинг выполнения фоновых задач
- **Unified Reports** — унифицированные отчеты по всем типам задач
## 🔄 Обновление системы
```bash
# Обновление Docker контейнеров
docker compose pull
docker compose up -d
# Обновление зависимостей Python
cd backend
source .venv/bin/activate
pip install -r requirements.txt --upgrade
# Обновление зависимостей Node.js
cd frontend
npm install
```

File diff suppressed because it is too large Load Diff

View File

@@ -6,7 +6,7 @@
# @RELATION: DEPENDS_ON -> importlib
# @INVARIANT: Only names listed in __all__ are importable via __getattr__.
__all__ = ['plugins', 'tasks', 'settings', 'connections', 'environments', 'mappings', 'migration', 'git', 'storage', 'admin', 'reports', 'assistant']
__all__ = ['plugins', 'tasks', 'settings', 'connections', 'environments', 'mappings', 'migration', 'git', 'storage', 'admin', 'reports', 'assistant', 'clean_release']
# [DEF:__getattr__:Function]

View File

@@ -76,11 +76,15 @@ class _FakeTaskManager:
class _FakeConfigManager:
def get_environments(self):
return [
SimpleNamespace(id="dev", name="Development"),
SimpleNamespace(id="prod", name="Production"),
SimpleNamespace(id="dev", name="Development", url="http://dev", credentials_id="dev", username="fakeuser", password="fakepassword"),
SimpleNamespace(id="prod", name="Production", url="http://prod", credentials_id="prod", username="fakeuser", password="fakepassword"),
]
def get_config(self):
return SimpleNamespace(
settings=SimpleNamespace(migration_sync_cron="0 0 * * *"),
environments=self.get_environments()
)
# [/DEF:_FakeConfigManager:Class]
# [DEF:_admin_user:Function]
# @TIER: TRIVIAL
@@ -645,5 +649,49 @@ def test_confirm_nonexistent_id_returns_404():
assert exc.value.status_code == 404
# [/DEF:test_guarded_operation_confirm_roundtrip:Function]
# [DEF:test_migration_with_dry_run_includes_summary:Function]
# @PURPOSE: Migration command with dry run flag must return the dry run summary in confirmation text.
# @PRE: user specifies a migration with --dry-run flag.
# @POST: Response state is needs_confirmation and text contains dry-run summary counts.
def test_migration_with_dry_run_includes_summary(monkeypatch):
import src.core.migration.dry_run_orchestrator as dry_run_module
from unittest.mock import MagicMock
_clear_assistant_state()
task_manager = _FakeTaskManager()
db = _FakeDb()
class _FakeDryRunService:
def run(self, selection, source_client, target_client, db_session):
return {
"summary": {
"dashboards": {"create": 1, "update": 0, "delete": 0},
"charts": {"create": 3, "update": 2, "delete": 1},
"datasets": {"create": 0, "update": 1, "delete": 0}
}
}
monkeypatch.setattr(dry_run_module, "MigrationDryRunService", _FakeDryRunService)
import src.core.superset_client as superset_client_module
monkeypatch.setattr(superset_client_module, "SupersetClient", lambda env: MagicMock())
start = _run_async(
assistant_module.send_message(
request=assistant_module.AssistantMessageRequest(
message="миграция с dev на prod для дашборда 10 --dry-run"
),
current_user=_admin_user(),
task_manager=task_manager,
config_manager=_FakeConfigManager(),
db=db,
)
)
assert start.state == "needs_confirmation"
assert "отчет dry-run: ВКЛ" in start.text
assert "Отчет dry-run:" in start.text
assert "создано новых объектов: 4" in start.text
assert "обновлено: 3" in start.text
assert "удалено: 1" in start.text
# [/DEF:test_migration_with_dry_run_includes_summary:Function]
# [/DEF:backend.src.api.routes.__tests__.test_assistant_api:Module]

View File

@@ -10,6 +10,41 @@ from datetime import datetime, timezone
from fastapi.testclient import TestClient
from src.app import app
from src.api.routes.dashboards import DashboardsResponse
from src.dependencies import get_current_user, has_permission, get_config_manager, get_task_manager, get_resource_service, get_mapping_service
# Global mock user for get_current_user dependency overrides
mock_user = MagicMock()
mock_user.username = "testuser"
mock_user.roles = []
admin_role = MagicMock()
admin_role.name = "Admin"
mock_user.roles.append(admin_role)
@pytest.fixture(autouse=True)
def mock_deps():
config_manager = MagicMock()
task_manager = MagicMock()
resource_service = MagicMock()
mapping_service = MagicMock()
app.dependency_overrides[get_config_manager] = lambda: config_manager
app.dependency_overrides[get_task_manager] = lambda: task_manager
app.dependency_overrides[get_resource_service] = lambda: resource_service
app.dependency_overrides[get_mapping_service] = lambda: mapping_service
app.dependency_overrides[get_current_user] = lambda: mock_user
app.dependency_overrides[has_permission("plugin:migration", "READ")] = lambda: mock_user
app.dependency_overrides[has_permission("plugin:migration", "EXECUTE")] = lambda: mock_user
app.dependency_overrides[has_permission("plugin:backup", "EXECUTE")] = lambda: mock_user
app.dependency_overrides[has_permission("tasks", "READ")] = lambda: mock_user
yield {
"config": config_manager,
"task": task_manager,
"resource": resource_service,
"mapping": mapping_service
}
app.dependency_overrides.clear()
client = TestClient(app)
@@ -18,45 +53,35 @@ client = TestClient(app)
# @TEST: GET /api/dashboards returns 200 and valid schema
# @PRE: env_id exists
# @POST: Response matches DashboardsResponse schema
def test_get_dashboards_success():
with patch("src.api.routes.dashboards.get_config_manager") as mock_config, \
patch("src.api.routes.dashboards.get_resource_service") as mock_service, \
patch("src.api.routes.dashboards.get_task_manager") as mock_task_mgr, \
patch("src.api.routes.dashboards.has_permission") as mock_perm:
# Mock environment
mock_env = MagicMock()
mock_env.id = "prod"
mock_config.return_value.get_environments.return_value = [mock_env]
# Mock task manager
mock_task_mgr.return_value.get_all_tasks.return_value = []
# Mock resource service response
async def mock_get_dashboards(env, tasks):
return [
{
"id": 1,
"title": "Sales Report",
"slug": "sales",
"git_status": {"branch": "main", "sync_status": "OK"},
"last_task": {"task_id": "task-1", "status": "SUCCESS"}
}
]
mock_service.return_value.get_dashboards_with_status = AsyncMock(
side_effect=mock_get_dashboards
)
# Mock permission
mock_perm.return_value = lambda: True
def test_get_dashboards_success(mock_deps):
"""Uses @TEST_FIXTURE: dashboard_list_happy data."""
mock_env = MagicMock()
mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_deps["task"].get_all_tasks.return_value = []
response = client.get("/api/dashboards?env_id=prod")
assert response.status_code == 200
data = response.json()
assert "dashboards" in data
assert "total" in data
assert "page" in data
# @TEST_FIXTURE: dashboard_list_happy -> {"id": 1, "title": "Main Revenue"}
mock_deps["resource"].get_dashboards_with_status = AsyncMock(return_value=[
{
"id": 1,
"title": "Main Revenue",
"slug": "main-revenue",
"git_status": {"branch": "main", "sync_status": "OK"},
"last_task": {"task_id": "task-1", "status": "SUCCESS"}
}
])
response = client.get("/api/dashboards?env_id=prod")
assert response.status_code == 200
data = response.json()
# exhaustive @POST assertions
assert "dashboards" in data
assert len(data["dashboards"]) == 1
assert data["dashboards"][0]["title"] == "Main Revenue"
assert data["total"] == 1
assert "page" in data
DashboardsResponse(**data)
# [/DEF:test_get_dashboards_success:Function]
@@ -66,55 +91,81 @@ def test_get_dashboards_success():
# @TEST: GET /api/dashboards filters by search term
# @PRE: search parameter provided
# @POST: Only matching dashboards returned
def test_get_dashboards_with_search():
with patch("src.api.routes.dashboards.get_config_manager") as mock_config, \
patch("src.api.routes.dashboards.get_resource_service") as mock_service, \
patch("src.api.routes.dashboards.get_task_manager") as mock_task_mgr, \
patch("src.api.routes.dashboards.has_permission") as mock_perm:
# Mock environment
mock_env = MagicMock()
mock_env.id = "prod"
mock_config.return_value.get_environments.return_value = [mock_env]
mock_task_mgr.return_value.get_all_tasks.return_value = []
async def mock_get_dashboards(env, tasks):
return [
{"id": 1, "title": "Sales Report", "slug": "sales"},
{"id": 2, "title": "Marketing Dashboard", "slug": "marketing"}
]
mock_service.return_value.get_dashboards_with_status = AsyncMock(
side_effect=mock_get_dashboards
)
mock_perm.return_value = lambda: True
def test_get_dashboards_with_search(mock_deps):
mock_env = MagicMock()
mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_deps["task"].get_all_tasks.return_value = []
response = client.get("/api/dashboards?env_id=prod&search=sales")
assert response.status_code == 200
data = response.json()
# Filtered by search term
async def mock_get_dashboards(env, tasks):
return [
{"id": 1, "title": "Sales Report", "slug": "sales"},
{"id": 2, "title": "Marketing Dashboard", "slug": "marketing"}
]
mock_deps["resource"].get_dashboards_with_status = AsyncMock(
side_effect=mock_get_dashboards
)
response = client.get("/api/dashboards?env_id=prod&search=sales")
assert response.status_code == 200
data = response.json()
# @POST: Filtered result count must match search
assert len(data["dashboards"]) == 1
assert data["dashboards"][0]["title"] == "Sales Report"
# [/DEF:test_get_dashboards_with_search:Function]
# [DEF:test_get_dashboards_empty:Function]
# @TEST_EDGE: empty_dashboards -> {env_id: 'empty_env', expected_total: 0}
def test_get_dashboards_empty(mock_deps):
"""@TEST_EDGE: empty_dashboards -> {env_id: 'empty_env', expected_total: 0}"""
mock_env = MagicMock()
mock_env.id = "empty_env"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_deps["task"].get_all_tasks.return_value = []
mock_deps["resource"].get_dashboards_with_status = AsyncMock(return_value=[])
response = client.get("/api/dashboards?env_id=empty_env")
assert response.status_code == 200
data = response.json()
assert data["total"] == 0
assert len(data["dashboards"]) == 0
assert data["total_pages"] == 1
DashboardsResponse(**data)
# [/DEF:test_get_dashboards_empty:Function]
# [DEF:test_get_dashboards_superset_failure:Function]
# @TEST_EDGE: external_superset_failure -> {env_id: 'bad_conn', status: 503}
def test_get_dashboards_superset_failure(mock_deps):
"""@TEST_EDGE: external_superset_failure -> {env_id: 'bad_conn', status: 503}"""
mock_env = MagicMock()
mock_env.id = "bad_conn"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_deps["task"].get_all_tasks.return_value = []
mock_deps["resource"].get_dashboards_with_status = AsyncMock(
side_effect=Exception("Connection refused")
)
response = client.get("/api/dashboards?env_id=bad_conn")
assert response.status_code == 503
assert "Failed to fetch dashboards" in response.json()["detail"]
# [/DEF:test_get_dashboards_superset_failure:Function]
# [DEF:test_get_dashboards_env_not_found:Function]
# @TEST: GET /api/dashboards returns 404 if env_id missing
# @PRE: env_id does not exist
# @POST: Returns 404 error
def test_get_dashboards_env_not_found():
with patch("src.api.routes.dashboards.get_config_manager") as mock_config, \
patch("src.api.routes.dashboards.has_permission") as mock_perm:
mock_config.return_value.get_environments.return_value = []
mock_perm.return_value = lambda: True
response = client.get("/api/dashboards?env_id=nonexistent")
assert response.status_code == 404
assert "Environment not found" in response.json()["detail"]
def test_get_dashboards_env_not_found(mock_deps):
mock_deps["config"].get_environments.return_value = []
response = client.get("/api/dashboards?env_id=nonexistent")
assert response.status_code == 404
assert "Environment not found" in response.json()["detail"]
# [/DEF:test_get_dashboards_env_not_found:Function]
@@ -124,40 +175,29 @@ def test_get_dashboards_env_not_found():
# @TEST: GET /api/dashboards returns 400 for invalid page/page_size
# @PRE: page < 1 or page_size > 100
# @POST: Returns 400 error
def test_get_dashboards_invalid_pagination():
with patch("src.api.routes.dashboards.get_config_manager") as mock_config, \
patch("src.api.routes.dashboards.has_permission") as mock_perm:
def test_get_dashboards_invalid_pagination(mock_deps):
mock_env = MagicMock()
mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
# Invalid page
response = client.get("/api/dashboards?env_id=prod&page=0")
assert response.status_code == 400
assert "Page must be >= 1" in response.json()["detail"]
mock_env = MagicMock()
mock_env.id = "prod"
mock_config.return_value.get_environments.return_value = [mock_env]
mock_perm.return_value = lambda: True
# Invalid page
response = client.get("/api/dashboards?env_id=prod&page=0")
assert response.status_code == 400
assert "Page must be >= 1" in response.json()["detail"]
# Invalid page_size
response = client.get("/api/dashboards?env_id=prod&page_size=101")
assert response.status_code == 400
assert "Page size must be between 1 and 100" in response.json()["detail"]
# Invalid page_size
response = client.get("/api/dashboards?env_id=prod&page_size=101")
assert response.status_code == 400
assert "Page size must be between 1 and 100" in response.json()["detail"]
# [/DEF:test_get_dashboards_invalid_pagination:Function]
# [DEF:test_get_dashboard_detail_success:Function]
# @TEST: GET /api/dashboards/{id} returns dashboard detail with charts and datasets
def test_get_dashboard_detail_success():
with patch("src.api.routes.dashboards.get_config_manager") as mock_config, \
patch("src.api.routes.dashboards.has_permission") as mock_perm, \
patch("src.api.routes.dashboards.SupersetClient") as mock_client_cls:
def test_get_dashboard_detail_success(mock_deps):
with patch("src.api.routes.dashboards.SupersetClient") as mock_client_cls:
mock_env = MagicMock()
mock_env.id = "prod"
mock_config.return_value.get_environments.return_value = [mock_env]
mock_perm.return_value = lambda: True
mock_deps["config"].get_environments.return_value = [mock_env]
mock_client = MagicMock()
mock_client.get_dashboard_detail.return_value = {
@@ -205,56 +245,46 @@ def test_get_dashboard_detail_success():
# [DEF:test_get_dashboard_detail_env_not_found:Function]
# @TEST: GET /api/dashboards/{id} returns 404 for missing environment
def test_get_dashboard_detail_env_not_found():
with patch("src.api.routes.dashboards.get_config_manager") as mock_config, \
patch("src.api.routes.dashboards.has_permission") as mock_perm:
mock_config.return_value.get_environments.return_value = []
mock_perm.return_value = lambda: True
def test_get_dashboard_detail_env_not_found(mock_deps):
mock_deps["config"].get_environments.return_value = []
response = client.get("/api/dashboards/42?env_id=missing")
response = client.get("/api/dashboards/42?env_id=missing")
assert response.status_code == 404
assert "Environment not found" in response.json()["detail"]
assert response.status_code == 404
assert "Environment not found" in response.json()["detail"]
# [/DEF:test_get_dashboard_detail_env_not_found:Function]
# [DEF:test_migrate_dashboards_success:Function]
# @TEST: POST /api/dashboards/migrate creates migration task
# @PRE: Valid source_env_id, target_env_id, dashboard_ids
# @POST: Returns task_id
def test_migrate_dashboards_success():
with patch("src.api.routes.dashboards.get_config_manager") as mock_config, \
patch("src.api.routes.dashboards.get_task_manager") as mock_task_mgr, \
patch("src.api.routes.dashboards.has_permission") as mock_perm:
# Mock environments
mock_source = MagicMock()
mock_source.id = "source"
mock_target = MagicMock()
mock_target.id = "target"
mock_config.return_value.get_environments.return_value = [mock_source, mock_target]
# Mock task manager
mock_task = MagicMock()
mock_task.id = "task-migrate-123"
mock_task_mgr.return_value.create_task = AsyncMock(return_value=mock_task)
# Mock permission
mock_perm.return_value = lambda: True
# @POST: Returns task_id and create_task was called
def test_migrate_dashboards_success(mock_deps):
mock_source = MagicMock()
mock_source.id = "source"
mock_target = MagicMock()
mock_target.id = "target"
mock_deps["config"].get_environments.return_value = [mock_source, mock_target]
response = client.post(
"/api/dashboards/migrate",
json={
"source_env_id": "source",
"target_env_id": "target",
"dashboard_ids": [1, 2, 3],
"db_mappings": {"old_db": "new_db"}
}
)
assert response.status_code == 200
data = response.json()
assert "task_id" in data
mock_task = MagicMock()
mock_task.id = "task-migrate-123"
mock_deps["task"].create_task = AsyncMock(return_value=mock_task)
response = client.post(
"/api/dashboards/migrate",
json={
"source_env_id": "source",
"target_env_id": "target",
"dashboard_ids": [1, 2, 3],
"db_mappings": {"old_db": "new_db"}
}
)
assert response.status_code == 200
data = response.json()
assert "task_id" in data
# @POST/@SIDE_EFFECT: create_task was called
mock_deps["task"].create_task.assert_called_once()
# [/DEF:test_migrate_dashboards_success:Function]
@@ -264,154 +294,184 @@ def test_migrate_dashboards_success():
# @TEST: POST /api/dashboards/migrate returns 400 for empty dashboard_ids
# @PRE: dashboard_ids is empty
# @POST: Returns 400 error
def test_migrate_dashboards_no_ids():
with patch("src.api.routes.dashboards.has_permission") as mock_perm:
mock_perm.return_value = lambda: True
def test_migrate_dashboards_no_ids(mock_deps):
response = client.post(
"/api/dashboards/migrate",
json={
"source_env_id": "source",
"target_env_id": "target",
"dashboard_ids": []
}
)
response = client.post(
"/api/dashboards/migrate",
json={
"source_env_id": "source",
"target_env_id": "target",
"dashboard_ids": []
}
)
assert response.status_code == 400
assert "At least one dashboard ID must be provided" in response.json()["detail"]
assert response.status_code == 400
assert "At least one dashboard ID must be provided" in response.json()["detail"]
# [/DEF:test_migrate_dashboards_no_ids:Function]
# [DEF:test_migrate_dashboards_env_not_found:Function]
# @PRE: source_env_id and target_env_id are valid environment IDs
def test_migrate_dashboards_env_not_found(mock_deps):
"""@PRE: source_env_id and target_env_id are valid environment IDs."""
mock_deps["config"].get_environments.return_value = []
response = client.post(
"/api/dashboards/migrate",
json={
"source_env_id": "ghost",
"target_env_id": "t",
"dashboard_ids": [1]
}
)
assert response.status_code == 404
assert "Source environment not found" in response.json()["detail"]
# [/DEF:test_migrate_dashboards_env_not_found:Function]
# [DEF:test_backup_dashboards_success:Function]
# @TEST: POST /api/dashboards/backup creates backup task
# @PRE: Valid env_id, dashboard_ids
# @POST: Returns task_id
def test_backup_dashboards_success():
with patch("src.api.routes.dashboards.get_config_manager") as mock_config, \
patch("src.api.routes.dashboards.get_task_manager") as mock_task_mgr, \
patch("src.api.routes.dashboards.has_permission") as mock_perm:
# Mock environment
mock_env = MagicMock()
mock_env.id = "prod"
mock_config.return_value.get_environments.return_value = [mock_env]
# Mock task manager
mock_task = MagicMock()
mock_task.id = "task-backup-456"
mock_task_mgr.return_value.create_task = AsyncMock(return_value=mock_task)
# Mock permission
mock_perm.return_value = lambda: True
# @POST: Returns task_id and create_task was called
def test_backup_dashboards_success(mock_deps):
mock_env = MagicMock()
mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
response = client.post(
"/api/dashboards/backup",
json={
"env_id": "prod",
"dashboard_ids": [1, 2, 3],
"schedule": "0 0 * * *"
}
)
assert response.status_code == 200
data = response.json()
assert "task_id" in data
mock_task = MagicMock()
mock_task.id = "task-backup-456"
mock_deps["task"].create_task = AsyncMock(return_value=mock_task)
response = client.post(
"/api/dashboards/backup",
json={
"env_id": "prod",
"dashboard_ids": [1, 2, 3],
"schedule": "0 0 * * *"
}
)
assert response.status_code == 200
data = response.json()
assert "task_id" in data
# @POST/@SIDE_EFFECT: create_task was called
mock_deps["task"].create_task.assert_called_once()
# [/DEF:test_backup_dashboards_success:Function]
# [DEF:test_backup_dashboards_env_not_found:Function]
# @PRE: env_id is a valid environment ID
def test_backup_dashboards_env_not_found(mock_deps):
"""@PRE: env_id is a valid environment ID."""
mock_deps["config"].get_environments.return_value = []
response = client.post(
"/api/dashboards/backup",
json={
"env_id": "ghost",
"dashboard_ids": [1]
}
)
assert response.status_code == 404
assert "Environment not found" in response.json()["detail"]
# [/DEF:test_backup_dashboards_env_not_found:Function]
# [DEF:test_get_database_mappings_success:Function]
# @TEST: GET /api/dashboards/db-mappings returns mapping suggestions
# @PRE: Valid source_env_id, target_env_id
# @POST: Returns list of database mappings
def test_get_database_mappings_success():
with patch("src.api.routes.dashboards.get_mapping_service") as mock_service, \
patch("src.api.routes.dashboards.has_permission") as mock_perm:
# Mock mapping service
mock_service.return_value.get_suggestions = AsyncMock(return_value=[
{
"source_db": "old_sales",
"target_db": "new_sales",
"source_db_uuid": "uuid-1",
"target_db_uuid": "uuid-2",
"confidence": 0.95
}
])
# Mock permission
mock_perm.return_value = lambda: True
def test_get_database_mappings_success(mock_deps):
mock_source = MagicMock()
mock_source.id = "prod"
mock_target = MagicMock()
mock_target.id = "staging"
mock_deps["config"].get_environments.return_value = [mock_source, mock_target]
response = client.get("/api/dashboards/db-mappings?source_env_id=prod&target_env_id=staging")
assert response.status_code == 200
data = response.json()
assert "mappings" in data
mock_deps["mapping"].get_suggestions = AsyncMock(return_value=[
{
"source_db": "old_sales",
"target_db": "new_sales",
"source_db_uuid": "uuid-1",
"target_db_uuid": "uuid-2",
"confidence": 0.95
}
])
response = client.get("/api/dashboards/db-mappings?source_env_id=prod&target_env_id=staging")
assert response.status_code == 200
data = response.json()
assert "mappings" in data
assert len(data["mappings"]) == 1
assert data["mappings"][0]["confidence"] == 0.95
# [/DEF:test_get_database_mappings_success:Function]
# [DEF:test_get_database_mappings_env_not_found:Function]
# @PRE: source_env_id and target_env_id are valid environment IDs
def test_get_database_mappings_env_not_found(mock_deps):
"""@PRE: source_env_id must be a valid environment."""
mock_deps["config"].get_environments.return_value = []
response = client.get("/api/dashboards/db-mappings?source_env_id=ghost&target_env_id=t")
assert response.status_code == 404
# [/DEF:test_get_database_mappings_env_not_found:Function]
# [DEF:test_get_dashboard_tasks_history_filters_success:Function]
# @TEST: GET /api/dashboards/{id}/tasks returns backup and llm tasks for dashboard
def test_get_dashboard_tasks_history_filters_success():
with patch("src.api.routes.dashboards.get_task_manager") as mock_task_mgr, \
patch("src.api.routes.dashboards.has_permission") as mock_perm:
now = datetime.now(timezone.utc)
def test_get_dashboard_tasks_history_filters_success(mock_deps):
now = datetime.now(timezone.utc)
llm_task = MagicMock()
llm_task.id = "task-llm-1"
llm_task.plugin_id = "llm_dashboard_validation"
llm_task.status = "SUCCESS"
llm_task.started_at = now
llm_task.finished_at = now
llm_task.params = {"dashboard_id": "42", "environment_id": "prod"}
llm_task.result = {"summary": "LLM validation complete"}
llm_task = MagicMock()
llm_task.id = "task-llm-1"
llm_task.plugin_id = "llm_dashboard_validation"
llm_task.status = "SUCCESS"
llm_task.started_at = now
llm_task.finished_at = now
llm_task.params = {"dashboard_id": "42", "environment_id": "prod"}
llm_task.result = {"summary": "LLM validation complete"}
backup_task = MagicMock()
backup_task.id = "task-backup-1"
backup_task.plugin_id = "superset-backup"
backup_task.status = "RUNNING"
backup_task.started_at = now
backup_task.finished_at = None
backup_task.params = {"env": "prod", "dashboards": [42]}
backup_task.result = {}
backup_task = MagicMock()
backup_task.id = "task-backup-1"
backup_task.plugin_id = "superset-backup"
backup_task.status = "RUNNING"
backup_task.started_at = now
backup_task.finished_at = None
backup_task.params = {"env": "prod", "dashboards": [42]}
backup_task.result = {}
other_task = MagicMock()
other_task.id = "task-other"
other_task.plugin_id = "superset-backup"
other_task.status = "SUCCESS"
other_task.started_at = now
other_task.finished_at = now
other_task.params = {"env": "prod", "dashboards": [777]}
other_task.result = {}
other_task = MagicMock()
other_task.id = "task-other"
other_task.plugin_id = "superset-backup"
other_task.status = "SUCCESS"
other_task.started_at = now
other_task.finished_at = now
other_task.params = {"env": "prod", "dashboards": [777]}
other_task.result = {}
mock_task_mgr.return_value.get_all_tasks.return_value = [other_task, llm_task, backup_task]
mock_perm.return_value = lambda: True
mock_deps["task"].get_all_tasks.return_value = [other_task, llm_task, backup_task]
response = client.get("/api/dashboards/42/tasks?env_id=prod&limit=10")
response = client.get("/api/dashboards/42/tasks?env_id=prod&limit=10")
assert response.status_code == 200
data = response.json()
assert data["dashboard_id"] == 42
assert len(data["items"]) == 2
assert {item["plugin_id"] for item in data["items"]} == {"llm_dashboard_validation", "superset-backup"}
assert response.status_code == 200
data = response.json()
assert data["dashboard_id"] == 42
assert len(data["items"]) == 2
assert {item["plugin_id"] for item in data["items"]} == {"llm_dashboard_validation", "superset-backup"}
# [/DEF:test_get_dashboard_tasks_history_filters_success:Function]
# [DEF:test_get_dashboard_thumbnail_success:Function]
# @TEST: GET /api/dashboards/{id}/thumbnail proxies image bytes from Superset
def test_get_dashboard_thumbnail_success():
with patch("src.api.routes.dashboards.get_config_manager") as mock_config, \
patch("src.api.routes.dashboards.has_permission") as mock_perm, \
patch("src.api.routes.dashboards.SupersetClient") as mock_client_cls:
def test_get_dashboard_thumbnail_success(mock_deps):
with patch("src.api.routes.dashboards.SupersetClient") as mock_client_cls:
mock_env = MagicMock()
mock_env.id = "prod"
mock_config.return_value.get_environments.return_value = [mock_env]
mock_perm.return_value = lambda: True
mock_deps["config"].get_environments.return_value = [mock_env]
mock_client = MagicMock()
mock_response = MagicMock()

View File

@@ -11,6 +11,41 @@ from unittest.mock import MagicMock, patch, AsyncMock
from fastapi.testclient import TestClient
from src.app import app
from src.api.routes.datasets import DatasetsResponse, DatasetDetailResponse
from src.dependencies import get_current_user, has_permission, get_config_manager, get_task_manager, get_resource_service, get_mapping_service
# Global mock user for get_current_user dependency overrides
mock_user = MagicMock()
mock_user.username = "testuser"
mock_user.roles = []
admin_role = MagicMock()
admin_role.name = "Admin"
mock_user.roles.append(admin_role)
@pytest.fixture(autouse=True)
def mock_deps():
config_manager = MagicMock()
task_manager = MagicMock()
resource_service = MagicMock()
mapping_service = MagicMock()
app.dependency_overrides[get_config_manager] = lambda: config_manager
app.dependency_overrides[get_task_manager] = lambda: task_manager
app.dependency_overrides[get_resource_service] = lambda: resource_service
app.dependency_overrides[get_mapping_service] = lambda: mapping_service
app.dependency_overrides[get_current_user] = lambda: mock_user
app.dependency_overrides[has_permission("plugin:migration", "READ")] = lambda: mock_user
app.dependency_overrides[has_permission("plugin:migration", "EXECUTE")] = lambda: mock_user
app.dependency_overrides[has_permission("plugin:backup", "EXECUTE")] = lambda: mock_user
app.dependency_overrides[has_permission("tasks", "READ")] = lambda: mock_user
yield {
"config": config_manager,
"task": task_manager,
"resource": resource_service,
"mapping": mapping_service
}
app.dependency_overrides.clear()
client = TestClient(app)
@@ -20,41 +55,34 @@ client = TestClient(app)
# @TEST: GET /api/datasets returns 200 and valid schema
# @PRE: env_id exists
# @POST: Response matches DatasetsResponse schema
def test_get_datasets_success():
with patch("src.api.routes.datasets.get_config_manager") as mock_config, \
patch("src.api.routes.datasets.get_resource_service") as mock_service, \
patch("src.api.routes.datasets.has_permission") as mock_perm:
# Mock environment
mock_env = MagicMock()
mock_env.id = "prod"
mock_config.return_value.get_environments.return_value = [mock_env]
# Mock resource service response
mock_service.return_value.get_datasets_with_status.return_value = AsyncMock()(
return_value=[
{
"id": 1,
"table_name": "sales_data",
"schema": "public",
"database": "sales_db",
"mapped_fields": {"total": 10, "mapped": 5},
"last_task": {"task_id": "task-1", "status": "SUCCESS"}
}
]
)
# Mock permission
mock_perm.return_value = lambda: True
def test_get_datasets_success(mock_deps):
# Mock environment
mock_env = MagicMock()
mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
# Mock resource service response
mock_deps["resource"].get_datasets_with_status = AsyncMock(
return_value=[
{
"id": 1,
"table_name": "sales_data",
"schema": "public",
"database": "sales_db",
"mapped_fields": {"total": 10, "mapped": 5},
"last_task": {"task_id": "task-1", "status": "SUCCESS"}
}
]
)
response = client.get("/api/datasets?env_id=prod")
assert response.status_code == 200
data = response.json()
assert "datasets" in data
assert len(data["datasets"]) >= 0
# Validate against Pydantic model
DatasetsResponse(**data)
response = client.get("/api/datasets?env_id=prod")
assert response.status_code == 200
data = response.json()
assert "datasets" in data
assert len(data["datasets"]) >= 0
# Validate against Pydantic model
DatasetsResponse(**data)
# [/DEF:test_get_datasets_success:Function]
@@ -64,17 +92,13 @@ def test_get_datasets_success():
# @TEST: GET /api/datasets returns 404 if env_id missing
# @PRE: env_id does not exist
# @POST: Returns 404 error
def test_get_datasets_env_not_found():
with patch("src.api.routes.datasets.get_config_manager") as mock_config, \
patch("src.api.routes.datasets.has_permission") as mock_perm:
mock_config.return_value.get_environments.return_value = []
mock_perm.return_value = lambda: True
def test_get_datasets_env_not_found(mock_deps):
mock_deps["config"].get_environments.return_value = []
response = client.get("/api/datasets?env_id=nonexistent")
assert response.status_code == 404
assert "Environment not found" in response.json()["detail"]
response = client.get("/api/datasets?env_id=nonexistent")
assert response.status_code == 404
assert "Environment not found" in response.json()["detail"]
# [/DEF:test_get_datasets_env_not_found:Function]
@@ -84,24 +108,25 @@ def test_get_datasets_env_not_found():
# @TEST: GET /api/datasets returns 400 for invalid page/page_size
# @PRE: page < 1 or page_size > 100
# @POST: Returns 400 error
def test_get_datasets_invalid_pagination():
with patch("src.api.routes.datasets.get_config_manager") as mock_config, \
patch("src.api.routes.datasets.has_permission") as mock_perm:
mock_env = MagicMock()
mock_env.id = "prod"
mock_config.return_value.get_environments.return_value = [mock_env]
mock_perm.return_value = lambda: True
def test_get_datasets_invalid_pagination(mock_deps):
mock_env = MagicMock()
mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
# Invalid page
response = client.get("/api/datasets?env_id=prod&page=0")
assert response.status_code == 400
assert "Page must be >= 1" in response.json()["detail"]
# Invalid page_size
response = client.get("/api/datasets?env_id=prod&page_size=0")
assert response.status_code == 400
assert "Page size must be between 1 and 100" in response.json()["detail"]
# Invalid page
response = client.get("/api/datasets?env_id=prod&page=0")
assert response.status_code == 400
assert "Page must be >= 1" in response.json()["detail"]
# Invalid page_size (too small)
response = client.get("/api/datasets?env_id=prod&page_size=0")
assert response.status_code == 400
assert "Page size must be between 1 and 100" in response.json()["detail"]
# @TEST_EDGE: page_size > 100 exceeds max
response = client.get("/api/datasets?env_id=prod&page_size=101")
assert response.status_code == 400
assert "Page size must be between 1 and 100" in response.json()["detail"]
# [/DEF:test_get_datasets_invalid_pagination:Function]
@@ -111,36 +136,31 @@ def test_get_datasets_invalid_pagination():
# @TEST: POST /api/datasets/map-columns creates mapping task
# @PRE: Valid env_id, dataset_ids, source_type
# @POST: Returns task_id
def test_map_columns_success():
with patch("src.api.routes.datasets.get_config_manager") as mock_config, \
patch("src.api.routes.datasets.get_task_manager") as mock_task_mgr, \
patch("src.api.routes.datasets.has_permission") as mock_perm:
# Mock environment
mock_env = MagicMock()
mock_env.id = "prod"
mock_config.return_value.get_environments.return_value = [mock_env]
# Mock task manager
mock_task = MagicMock()
mock_task.id = "task-123"
mock_task_mgr.return_value.create_task = AsyncMock(return_value=mock_task)
# Mock permission
mock_perm.return_value = lambda: True
def test_map_columns_success(mock_deps):
# Mock environment
mock_env = MagicMock()
mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
# Mock task manager
mock_task = MagicMock()
mock_task.id = "task-123"
mock_deps["task"].create_task = AsyncMock(return_value=mock_task)
response = client.post(
"/api/datasets/map-columns",
json={
"env_id": "prod",
"dataset_ids": [1, 2, 3],
"source_type": "postgresql"
}
)
assert response.status_code == 200
data = response.json()
assert "task_id" in data
response = client.post(
"/api/datasets/map-columns",
json={
"env_id": "prod",
"dataset_ids": [1, 2, 3],
"source_type": "postgresql"
}
)
assert response.status_code == 200
data = response.json()
assert "task_id" in data
# @POST/@SIDE_EFFECT: create_task was called
mock_deps["task"].create_task.assert_called_once()
# [/DEF:test_map_columns_success:Function]
@@ -150,21 +170,18 @@ def test_map_columns_success():
# @TEST: POST /api/datasets/map-columns returns 400 for invalid source_type
# @PRE: source_type is not 'postgresql' or 'xlsx'
# @POST: Returns 400 error
def test_map_columns_invalid_source_type():
with patch("src.api.routes.datasets.has_permission") as mock_perm:
mock_perm.return_value = lambda: True
response = client.post(
"/api/datasets/map-columns",
json={
"env_id": "prod",
"dataset_ids": [1],
"source_type": "invalid"
}
)
assert response.status_code == 400
assert "Source type must be 'postgresql' or 'xlsx'" in response.json()["detail"]
def test_map_columns_invalid_source_type(mock_deps):
response = client.post(
"/api/datasets/map-columns",
json={
"env_id": "prod",
"dataset_ids": [1],
"source_type": "invalid"
}
)
assert response.status_code == 400
assert "Source type must be 'postgresql' or 'xlsx'" in response.json()["detail"]
# [/DEF:test_map_columns_invalid_source_type:Function]
@@ -174,39 +191,110 @@ def test_map_columns_invalid_source_type():
# @TEST: POST /api/datasets/generate-docs creates doc generation task
# @PRE: Valid env_id, dataset_ids, llm_provider
# @POST: Returns task_id
def test_generate_docs_success():
with patch("src.api.routes.datasets.get_config_manager") as mock_config, \
patch("src.api.routes.datasets.get_task_manager") as mock_task_mgr, \
patch("src.api.routes.datasets.has_permission") as mock_perm:
# Mock environment
mock_env = MagicMock()
mock_env.id = "prod"
mock_config.return_value.get_environments.return_value = [mock_env]
# Mock task manager
mock_task = MagicMock()
mock_task.id = "task-456"
mock_task_mgr.return_value.create_task = AsyncMock(return_value=mock_task)
# Mock permission
mock_perm.return_value = lambda: True
def test_generate_docs_success(mock_deps):
# Mock environment
mock_env = MagicMock()
mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
# Mock task manager
mock_task = MagicMock()
mock_task.id = "task-456"
mock_deps["task"].create_task = AsyncMock(return_value=mock_task)
response = client.post(
"/api/datasets/generate-docs",
json={
"env_id": "prod",
"dataset_ids": [1],
"llm_provider": "openai"
}
)
assert response.status_code == 200
data = response.json()
assert "task_id" in data
response = client.post(
"/api/datasets/generate-docs",
json={
"env_id": "prod",
"dataset_ids": [1],
"llm_provider": "openai"
}
)
assert response.status_code == 200
data = response.json()
assert "task_id" in data
# @POST/@SIDE_EFFECT: create_task was called
mock_deps["task"].create_task.assert_called_once()
# [/DEF:test_generate_docs_success:Function]
# [DEF:test_map_columns_empty_ids:Function]
# @TEST: POST /api/datasets/map-columns returns 400 for empty dataset_ids
# @PRE: dataset_ids is empty
# @POST: Returns 400 error
def test_map_columns_empty_ids(mock_deps):
"""@PRE: dataset_ids must be non-empty."""
response = client.post(
"/api/datasets/map-columns",
json={
"env_id": "prod",
"dataset_ids": [],
"source_type": "postgresql"
}
)
assert response.status_code == 400
assert "At least one dataset ID must be provided" in response.json()["detail"]
# [/DEF:test_map_columns_empty_ids:Function]
# [DEF:test_generate_docs_empty_ids:Function]
# @TEST: POST /api/datasets/generate-docs returns 400 for empty dataset_ids
# @PRE: dataset_ids is empty
# @POST: Returns 400 error
def test_generate_docs_empty_ids(mock_deps):
"""@PRE: dataset_ids must be non-empty."""
response = client.post(
"/api/datasets/generate-docs",
json={
"env_id": "prod",
"dataset_ids": [],
"llm_provider": "openai"
}
)
assert response.status_code == 400
assert "At least one dataset ID must be provided" in response.json()["detail"]
# [/DEF:test_generate_docs_empty_ids:Function]
# [DEF:test_generate_docs_env_not_found:Function]
# @TEST: POST /api/datasets/generate-docs returns 404 for missing env
# @PRE: env_id does not exist
# @POST: Returns 404 error
def test_generate_docs_env_not_found(mock_deps):
"""@PRE: env_id must be a valid environment."""
mock_deps["config"].get_environments.return_value = []
response = client.post(
"/api/datasets/generate-docs",
json={
"env_id": "ghost",
"dataset_ids": [1],
"llm_provider": "openai"
}
)
assert response.status_code == 404
assert "Environment not found" in response.json()["detail"]
# [/DEF:test_generate_docs_env_not_found:Function]
# [DEF:test_get_datasets_superset_failure:Function]
# @TEST_EDGE: external_superset_failure -> {status: 503}
def test_get_datasets_superset_failure(mock_deps):
"""@TEST_EDGE: external_superset_failure -> {status: 503}"""
mock_env = MagicMock()
mock_env.id = "bad_conn"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_deps["task"].get_all_tasks.return_value = []
mock_deps["resource"].get_datasets_with_status = AsyncMock(
side_effect=Exception("Connection refused")
)
response = client.get("/api/datasets?env_id=bad_conn")
assert response.status_code == 503
assert "Failed to fetch datasets" in response.json()["detail"]
# [/DEF:test_get_datasets_superset_failure:Function]
# [/DEF:backend.src.api.routes.__tests__.test_datasets:Module]

View File

@@ -0,0 +1,198 @@
# [DEF:backend.src.api.routes.__tests__.test_git_status_route:Module]
# @TIER: STANDARD
# @SEMANTICS: tests, git, api, status, no_repo
# @PURPOSE: Validate status endpoint behavior for missing and error repository states.
# @LAYER: Domain (Tests)
# @RELATION: CALLS -> src.api.routes.git.get_repository_status
from fastapi import HTTPException
import pytest
import asyncio
from src.api.routes import git as git_routes
# [DEF:test_get_repository_status_returns_no_repo_payload_for_missing_repo:Function]
# @PURPOSE: Ensure missing local repository is represented as NO_REPO payload instead of an API error.
# @PRE: GitService.get_status raises HTTPException(404).
# @POST: Route returns a deterministic NO_REPO status payload.
def test_get_repository_status_returns_no_repo_payload_for_missing_repo(monkeypatch):
class MissingRepoGitService:
def _get_repo_path(self, dashboard_id: int) -> str:
return f"/tmp/missing-repo-{dashboard_id}"
def get_status(self, dashboard_id: int) -> dict:
raise AssertionError("get_status must not be called when repository path is missing")
monkeypatch.setattr(git_routes, "git_service", MissingRepoGitService())
response = asyncio.run(git_routes.get_repository_status(34))
assert response["sync_status"] == "NO_REPO"
assert response["sync_state"] == "NO_REPO"
assert response["has_repo"] is False
assert response["current_branch"] is None
# [/DEF:test_get_repository_status_returns_no_repo_payload_for_missing_repo:Function]
# [DEF:test_get_repository_status_propagates_non_404_http_exception:Function]
# @PURPOSE: Ensure HTTP exceptions other than 404 are not masked.
# @PRE: GitService.get_status raises HTTPException with non-404 status.
# @POST: Raised exception preserves original status and detail.
def test_get_repository_status_propagates_non_404_http_exception(monkeypatch):
class ConflictGitService:
def _get_repo_path(self, dashboard_id: int) -> str:
return f"/tmp/existing-repo-{dashboard_id}"
def get_status(self, dashboard_id: int) -> dict:
raise HTTPException(status_code=409, detail="Conflict")
monkeypatch.setattr(git_routes, "git_service", ConflictGitService())
monkeypatch.setattr(git_routes.os.path, "exists", lambda _path: True)
with pytest.raises(HTTPException) as exc_info:
asyncio.run(git_routes.get_repository_status(34))
assert exc_info.value.status_code == 409
assert exc_info.value.detail == "Conflict"
# [/DEF:test_get_repository_status_propagates_non_404_http_exception:Function]
# [DEF:test_get_repository_diff_propagates_http_exception:Function]
# @PURPOSE: Ensure diff endpoint preserves domain HTTP errors from GitService.
# @PRE: GitService.get_diff raises HTTPException.
# @POST: Endpoint raises same HTTPException values.
def test_get_repository_diff_propagates_http_exception(monkeypatch):
class DiffGitService:
def get_diff(self, dashboard_id: int, file_path=None, staged: bool = False) -> str:
raise HTTPException(status_code=404, detail="Repository missing")
monkeypatch.setattr(git_routes, "git_service", DiffGitService())
with pytest.raises(HTTPException) as exc_info:
asyncio.run(git_routes.get_repository_diff(12))
assert exc_info.value.status_code == 404
assert exc_info.value.detail == "Repository missing"
# [/DEF:test_get_repository_diff_propagates_http_exception:Function]
# [DEF:test_get_history_wraps_unexpected_error_as_500:Function]
# @PURPOSE: Ensure non-HTTP exceptions in history endpoint become deterministic 500 errors.
# @PRE: GitService.get_commit_history raises ValueError.
# @POST: Endpoint returns HTTPException with status 500 and route context.
def test_get_history_wraps_unexpected_error_as_500(monkeypatch):
class HistoryGitService:
def get_commit_history(self, dashboard_id: int, limit: int = 50):
raise ValueError("broken parser")
monkeypatch.setattr(git_routes, "git_service", HistoryGitService())
with pytest.raises(HTTPException) as exc_info:
asyncio.run(git_routes.get_history(12))
assert exc_info.value.status_code == 500
assert exc_info.value.detail == "get_history failed: broken parser"
# [/DEF:test_get_history_wraps_unexpected_error_as_500:Function]
# [DEF:test_commit_changes_wraps_unexpected_error_as_500:Function]
# @PURPOSE: Ensure commit endpoint does not leak unexpected errors as 400.
# @PRE: GitService.commit_changes raises RuntimeError.
# @POST: Endpoint raises HTTPException(500) with route context.
def test_commit_changes_wraps_unexpected_error_as_500(monkeypatch):
class CommitGitService:
def commit_changes(self, dashboard_id: int, message: str, files):
raise RuntimeError("index lock")
class CommitPayload:
message = "test"
files = ["dashboards/a.yaml"]
monkeypatch.setattr(git_routes, "git_service", CommitGitService())
with pytest.raises(HTTPException) as exc_info:
asyncio.run(git_routes.commit_changes(12, CommitPayload()))
assert exc_info.value.status_code == 500
assert exc_info.value.detail == "commit_changes failed: index lock"
# [/DEF:test_commit_changes_wraps_unexpected_error_as_500:Function]
# [DEF:test_get_repository_status_batch_returns_mixed_statuses:Function]
# @PURPOSE: Ensure batch endpoint returns per-dashboard statuses in one response.
# @PRE: Some repositories are missing and some are initialized.
# @POST: Returned map includes resolved status for each requested dashboard ID.
def test_get_repository_status_batch_returns_mixed_statuses(monkeypatch):
class BatchGitService:
def _get_repo_path(self, dashboard_id: int) -> str:
return f"/tmp/repo-{dashboard_id}"
def get_status(self, dashboard_id: int) -> dict:
if dashboard_id == 2:
return {"sync_state": "SYNCED", "sync_status": "OK"}
raise HTTPException(status_code=404, detail="not found")
monkeypatch.setattr(git_routes, "git_service", BatchGitService())
monkeypatch.setattr(git_routes.os.path, "exists", lambda path: path.endswith("/repo-2"))
class BatchRequest:
dashboard_ids = [1, 2]
response = asyncio.run(git_routes.get_repository_status_batch(BatchRequest()))
assert response.statuses["1"]["sync_status"] == "NO_REPO"
assert response.statuses["2"]["sync_state"] == "SYNCED"
# [/DEF:test_get_repository_status_batch_returns_mixed_statuses:Function]
# [DEF:test_get_repository_status_batch_marks_item_as_error_on_service_failure:Function]
# @PURPOSE: Ensure batch endpoint marks failed items as ERROR without failing entire request.
# @PRE: GitService raises non-HTTP exception for one dashboard.
# @POST: Failed dashboard status is marked as ERROR.
def test_get_repository_status_batch_marks_item_as_error_on_service_failure(monkeypatch):
class BatchErrorGitService:
def _get_repo_path(self, dashboard_id: int) -> str:
return f"/tmp/repo-{dashboard_id}"
def get_status(self, dashboard_id: int) -> dict:
raise RuntimeError("boom")
monkeypatch.setattr(git_routes, "git_service", BatchErrorGitService())
monkeypatch.setattr(git_routes.os.path, "exists", lambda _path: True)
class BatchRequest:
dashboard_ids = [9]
response = asyncio.run(git_routes.get_repository_status_batch(BatchRequest()))
assert response.statuses["9"]["sync_status"] == "ERROR"
assert response.statuses["9"]["sync_state"] == "ERROR"
# [/DEF:test_get_repository_status_batch_marks_item_as_error_on_service_failure:Function]
# [DEF:test_get_repository_status_batch_deduplicates_and_truncates_ids:Function]
# @PURPOSE: Ensure batch endpoint protects server from oversized payloads.
# @PRE: request includes duplicate IDs and more than MAX_REPOSITORY_STATUS_BATCH entries.
# @POST: Result contains unique IDs up to configured cap.
def test_get_repository_status_batch_deduplicates_and_truncates_ids(monkeypatch):
class SafeBatchGitService:
def _get_repo_path(self, dashboard_id: int) -> str:
return f"/tmp/repo-{dashboard_id}"
def get_status(self, dashboard_id: int) -> dict:
return {"sync_state": "SYNCED", "sync_status": "OK"}
monkeypatch.setattr(git_routes, "git_service", SafeBatchGitService())
monkeypatch.setattr(git_routes.os.path, "exists", lambda _path: True)
class BatchRequest:
dashboard_ids = [1, 1] + list(range(2, 90))
response = asyncio.run(git_routes.get_repository_status_batch(BatchRequest()))
assert len(response.statuses) == git_routes.MAX_REPOSITORY_STATUS_BATCH
assert "1" in response.statuses
# [/DEF:test_get_repository_status_batch_deduplicates_and_truncates_ids:Function]
# [/DEF:backend.src.api.routes.__tests__.test_git_status_route:Module]

View File

@@ -407,4 +407,104 @@ async def test_execute_migration_invalid_env_raises_400(_mock_env):
assert exc.value.status_code == 400
@pytest.mark.asyncio
async def test_dry_run_migration_returns_diff_and_risk(db_session):
# @TEST_EDGE: missing_target_datasource -> validates high risk item generation
# @TEST_EDGE: breaking_reference -> validates high risk on missing dataset link
from src.api.routes.migration import dry_run_migration
from src.models.dashboard import DashboardSelection
env_source = MagicMock()
env_source.id = "src"
env_source.name = "Source"
env_source.url = "http://source"
env_source.username = "admin"
env_source.password = "admin"
env_source.verify_ssl = False
env_source.timeout = 30
env_target = MagicMock()
env_target.id = "tgt"
env_target.name = "Target"
env_target.url = "http://target"
env_target.username = "admin"
env_target.password = "admin"
env_target.verify_ssl = False
env_target.timeout = 30
cm = _make_sync_config_manager([env_source, env_target])
selection = DashboardSelection(
selected_ids=[42],
source_env_id="src",
target_env_id="tgt",
replace_db_config=False,
fix_cross_filters=True,
)
with patch("src.api.routes.migration.SupersetClient") as MockClient, \
patch("src.api.routes.migration.MigrationDryRunService") as MockService:
source_client = MagicMock()
target_client = MagicMock()
MockClient.side_effect = [source_client, target_client]
service_instance = MagicMock()
service_payload = {
"generated_at": "2026-02-27T00:00:00+00:00",
"selection": selection.model_dump(),
"selected_dashboard_titles": ["Sales"],
"diff": {
"dashboards": {"create": [], "update": [{"uuid": "dash-1"}], "delete": []},
"charts": {"create": [{"uuid": "chart-1"}], "update": [], "delete": []},
"datasets": {"create": [{"uuid": "dataset-1"}], "update": [], "delete": []},
},
"summary": {
"dashboards": {"create": 0, "update": 1, "delete": 0},
"charts": {"create": 1, "update": 0, "delete": 0},
"datasets": {"create": 1, "update": 0, "delete": 0},
"selected_dashboards": 1,
},
"risk": {
"score": 75,
"level": "high",
"items": [
{"code": "missing_datasource"},
{"code": "breaking_reference"},
],
},
}
service_instance.run.return_value = service_payload
MockService.return_value = service_instance
result = await dry_run_migration(selection=selection, config_manager=cm, db=db_session, _=None)
assert result["summary"]["dashboards"]["update"] == 1
assert result["summary"]["charts"]["create"] == 1
assert result["summary"]["datasets"]["create"] == 1
assert result["risk"]["score"] > 0
assert any(item["code"] == "missing_datasource" for item in result["risk"]["items"])
assert any(item["code"] == "breaking_reference" for item in result["risk"]["items"])
@pytest.mark.asyncio
async def test_dry_run_migration_rejects_same_environment(db_session):
from src.api.routes.migration import dry_run_migration
from src.models.dashboard import DashboardSelection
env = MagicMock()
env.id = "same"
env.name = "Same"
env.url = "http://same"
env.username = "admin"
env.password = "admin"
env.verify_ssl = False
env.timeout = 30
cm = _make_sync_config_manager([env])
selection = DashboardSelection(selected_ids=[1], source_env_id="same", target_env_id="same")
with pytest.raises(HTTPException) as exc:
await dry_run_migration(selection=selection, config_manager=cm, db=db_session, _=None)
assert exc.value.status_code == 400
# [/DEF:backend.src.api.routes.__tests__.test_migration_routes:Module]

View File

@@ -810,6 +810,9 @@ def _parse_command(message: str, config_manager: ConfigManager) -> Dict[str, Any
if any(k in lower for k in ["миграц", "migration", "migrate"]):
src = _extract_id(lower, [r"(?:с|from)\s+([a-z0-9_-]+)"])
tgt = _extract_id(lower, [r"(?:на|to)\s+([a-z0-9_-]+)"])
dry_run = "--dry-run" in lower or "dry run" in lower
replace_db_config = "--replace-db-config" in lower
fix_cross_filters = "--fix-cross-filters" not in lower # Default true usually, but let's say test uses --dry-run
is_dangerous = _is_production_env(tgt, config_manager)
return {
"domain": "migration",
@@ -818,10 +821,13 @@ def _parse_command(message: str, config_manager: ConfigManager) -> Dict[str, Any
"dashboard_id": int(dashboard_id) if dashboard_id else None,
"source_env": src,
"target_env": tgt,
"dry_run": dry_run,
"replace_db_config": replace_db_config,
"fix_cross_filters": True,
},
"confidence": 0.95 if dashboard_id and src and tgt else 0.72,
"risk_level": "dangerous" if is_dangerous else "guarded",
"requires_confirmation": is_dangerous,
"requires_confirmation": is_dangerous or dry_run,
}
# Backup
@@ -1057,7 +1063,7 @@ _SAFE_OPS = {"show_capabilities", "get_task_status"}
# @PURPOSE: Build human-readable confirmation prompt for an intent before execution.
# @PRE: intent contains operation and entities fields.
# @POST: Returns descriptive Russian-language text ending with confirmation prompt.
def _confirmation_summary(intent: Dict[str, Any]) -> str:
async def _async_confirmation_summary(intent: Dict[str, Any], config_manager: ConfigManager, db: Session) -> str:
operation = intent.get("operation", "")
entities = intent.get("entities", {})
descriptions: Dict[str, str] = {
@@ -1085,8 +1091,67 @@ def _confirmation_summary(intent: Dict[str, Any]) -> str:
tgt=_label(entities.get("target_env")),
dataset=_label(entities.get("dataset_id")),
)
if operation == "execute_migration":
flags = []
flags.append("маппинг БД: " + ("ВКЛ" if _coerce_query_bool(entities.get("replace_db_config", False)) else "ВЫКЛ"))
flags.append("исправление кроссфильтров: " + ("ВКЛ" if _coerce_query_bool(entities.get("fix_cross_filters", True)) else "ВЫКЛ"))
dry_run_enabled = _coerce_query_bool(entities.get("dry_run", False))
flags.append("отчет dry-run: " + ("ВКЛ" if dry_run_enabled else "ВЫКЛ"))
text += f" ({', '.join(flags)})"
if dry_run_enabled:
try:
from ...core.migration.dry_run_orchestrator import MigrationDryRunService
from ...models.dashboard import DashboardSelection
from ...core.superset_client import SupersetClient
src_token = entities.get("source_env")
tgt_token = entities.get("target_env")
dashboard_id = _resolve_dashboard_id_entity(entities, config_manager, env_hint=src_token)
if dashboard_id and src_token and tgt_token:
src_env_id = _resolve_env_id(src_token, config_manager)
tgt_env_id = _resolve_env_id(tgt_token, config_manager)
if src_env_id and tgt_env_id:
env_map = {env.id: env for env in config_manager.get_environments()}
source_env = env_map.get(src_env_id)
target_env = env_map.get(tgt_env_id)
if source_env and target_env and source_env.id != target_env.id:
selection = DashboardSelection(
source_env_id=source_env.id,
target_env_id=target_env.id,
selected_ids=[dashboard_id],
replace_db_config=_coerce_query_bool(entities.get("replace_db_config", False)),
fix_cross_filters=_coerce_query_bool(entities.get("fix_cross_filters", True))
)
service = MigrationDryRunService()
source_client = SupersetClient(source_env)
target_client = SupersetClient(target_env)
report = service.run(selection, source_client, target_client, db)
s = report.get("summary", {})
dash_s = s.get("dashboards", {})
charts_s = s.get("charts", {})
ds_s = s.get("datasets", {})
# Determine main actions counts
creates = dash_s.get("create", 0) + charts_s.get("create", 0) + ds_s.get("create", 0)
updates = dash_s.get("update", 0) + charts_s.get("update", 0) + ds_s.get("update", 0)
deletes = dash_s.get("delete", 0) + charts_s.get("delete", 0) + ds_s.get("delete", 0)
text += f"\n\nОтчет dry-run:\n- Будет создано новых объектов: {creates}\n- Будет обновлено: {updates}\n- Будет удалено: {deletes}"
else:
text += "\n\n(Не удалось загрузить отчет dry-run: неверные окружения)."
except Exception as e:
import traceback
logger.warning("[assistant.dry_run_summary][failed] Exception: %s\n%s", e, traceback.format_exc())
text += f"\n\n(Не удалось загрузить отчет dry-run: {e})."
return f"Выполнить: {text}. Подтвердите или отмените."
# [/DEF:_confirmation_summary:Function]
# [/DEF:_async_confirmation_summary:Function]
# [DEF:_clarification_text_for_intent:Function]
@@ -1176,7 +1241,8 @@ async def _plan_intent_with_llm(
]
)
except Exception as exc:
logger.warning(f"[assistant.planner][fallback] LLM planner unavailable: {exc}")
import traceback
logger.warning(f"[assistant.planner][fallback] LLM planner unavailable: {exc}\n{traceback.format_exc()}")
return None
if not isinstance(response, dict):
return None
@@ -1580,7 +1646,7 @@ async def send_message(
)
CONFIRMATIONS[confirmation_id] = confirm
_persist_confirmation(db, confirm)
text = _confirmation_summary(intent)
text = await _async_confirmation_summary(intent, config_manager, db)
_append_history(
user_id,
conversation_id,
@@ -1895,6 +1961,39 @@ async def list_conversations(
# [/DEF:list_conversations:Function]
# [DEF:delete_conversation:Function]
# @PURPOSE: Soft-delete or hard-delete a conversation and clear its in-memory trace.
# @PRE: conversation_id belongs to current_user.
# @POST: Conversation records are removed from DB and CONVERSATIONS cache.
@router.delete("/conversations/{conversation_id}")
async def delete_conversation(
conversation_id: str,
current_user: User = Depends(get_current_user),
db: Session = Depends(get_db),
):
with belief_scope("assistant.conversations.delete"):
user_id = current_user.id
# 1. Remove from in-memory cache
key = (user_id, conversation_id)
if key in CONVERSATIONS:
del CONVERSATIONS[key]
# 2. Delete from database
deleted_count = db.query(AssistantMessageRecord).filter(
AssistantMessageRecord.user_id == user_id,
AssistantMessageRecord.conversation_id == conversation_id
).delete()
db.commit()
if deleted_count == 0:
raise HTTPException(status_code=404, detail="Conversation not found or already deleted")
return {"status": "success", "deleted": deleted_count, "conversation_id": conversation_id}
# [/DEF:delete_conversation:Function]
@router.get("/history")
# [DEF:get_history:Function]
# @PURPOSE: Retrieve paginated assistant conversation history for current user.

View File

@@ -0,0 +1,185 @@
# [DEF:backend.src.api.routes.clean_release:Module]
# @TIER: STANDARD
# @SEMANTICS: api, clean-release, candidate-preparation, compliance
# @PURPOSE: Expose clean release endpoints for candidate preparation and subsequent compliance flow.
# @LAYER: API
# @RELATION: DEPENDS_ON -> backend.src.dependencies.get_clean_release_repository
# @RELATION: DEPENDS_ON -> backend.src.services.clean_release.preparation_service
# @INVARIANT: API never reports prepared status if preparation errors are present.
from __future__ import annotations
from datetime import datetime, timezone
from typing import Any, Dict, List
from fastapi import APIRouter, Depends, HTTPException, status
from pydantic import BaseModel, Field
from ...core.logger import belief_scope, logger
from ...dependencies import get_clean_release_repository
from ...services.clean_release.preparation_service import prepare_candidate
from ...services.clean_release.repository import CleanReleaseRepository
from ...services.clean_release.compliance_orchestrator import CleanComplianceOrchestrator
from ...services.clean_release.report_builder import ComplianceReportBuilder
from ...models.clean_release import (
CheckFinalStatus,
CheckStageName,
CheckStageResult,
CheckStageStatus,
ComplianceViolation,
ViolationCategory,
ViolationSeverity,
)
router = APIRouter(prefix="/api/clean-release", tags=["Clean Release"])
# [DEF:PrepareCandidateRequest:Class]
# @PURPOSE: Request schema for candidate preparation endpoint.
class PrepareCandidateRequest(BaseModel):
candidate_id: str = Field(min_length=1)
artifacts: List[Dict[str, Any]] = Field(default_factory=list)
sources: List[str] = Field(default_factory=list)
operator_id: str = Field(min_length=1)
# [/DEF:PrepareCandidateRequest:Class]
# [DEF:StartCheckRequest:Class]
# @PURPOSE: Request schema for clean compliance check run startup.
class StartCheckRequest(BaseModel):
candidate_id: str = Field(min_length=1)
profile: str = Field(default="enterprise-clean")
execution_mode: str = Field(default="tui")
triggered_by: str = Field(default="system")
# [/DEF:StartCheckRequest:Class]
# [DEF:prepare_candidate_endpoint:Function]
# @PURPOSE: Prepare candidate with policy evaluation and deterministic manifest generation.
# @PRE: Candidate and active policy exist in repository.
# @POST: Returns preparation result including manifest reference and violations.
@router.post("/candidates/prepare")
async def prepare_candidate_endpoint(
payload: PrepareCandidateRequest,
repository: CleanReleaseRepository = Depends(get_clean_release_repository),
):
try:
result = prepare_candidate(
repository=repository,
candidate_id=payload.candidate_id,
artifacts=payload.artifacts,
sources=payload.sources,
operator_id=payload.operator_id,
)
return result
except ValueError as exc:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail={"message": str(exc), "code": "CLEAN_PREPARATION_ERROR"},
)
# [/DEF:prepare_candidate_endpoint:Function]
# [DEF:start_check:Function]
# @PURPOSE: Start and finalize a clean compliance check run and persist report artifacts.
# @PRE: Active policy and candidate exist.
# @POST: Returns accepted payload with check_run_id and started_at.
@router.post("/checks", status_code=status.HTTP_202_ACCEPTED)
async def start_check(
payload: StartCheckRequest,
repository: CleanReleaseRepository = Depends(get_clean_release_repository),
):
with belief_scope("clean_release.start_check"):
logger.reason("Starting clean-release compliance check run")
policy = repository.get_active_policy()
if policy is None:
raise HTTPException(status_code=409, detail={"message": "Active policy not found", "code": "POLICY_NOT_FOUND"})
candidate = repository.get_candidate(payload.candidate_id)
if candidate is None:
raise HTTPException(status_code=409, detail={"message": "Candidate not found", "code": "CANDIDATE_NOT_FOUND"})
orchestrator = CleanComplianceOrchestrator(repository)
run = orchestrator.start_check_run(
candidate_id=payload.candidate_id,
policy_id=policy.policy_id,
triggered_by=payload.triggered_by,
execution_mode=payload.execution_mode,
)
forced = [
CheckStageResult(stage=CheckStageName.DATA_PURITY, status=CheckStageStatus.PASS, details="ok"),
CheckStageResult(stage=CheckStageName.INTERNAL_SOURCES_ONLY, status=CheckStageStatus.PASS, details="ok"),
CheckStageResult(stage=CheckStageName.NO_EXTERNAL_ENDPOINTS, status=CheckStageStatus.PASS, details="ok"),
CheckStageResult(stage=CheckStageName.MANIFEST_CONSISTENCY, status=CheckStageStatus.PASS, details="ok"),
]
run = orchestrator.execute_stages(run, forced_results=forced)
run = orchestrator.finalize_run(run)
if run.final_status == CheckFinalStatus.BLOCKED:
logger.explore("Run ended as BLOCKED, persisting synthetic external-source violation")
violation = ComplianceViolation(
violation_id=f"viol-{run.check_run_id}",
check_run_id=run.check_run_id,
category=ViolationCategory.EXTERNAL_SOURCE,
severity=ViolationSeverity.CRITICAL,
location="external.example.com",
remediation="Replace with approved internal server",
blocked_release=True,
detected_at=datetime.now(timezone.utc),
)
repository.save_violation(violation)
builder = ComplianceReportBuilder(repository)
report = builder.build_report_payload(run, repository.get_violations_by_check_run(run.check_run_id))
builder.persist_report(report)
logger.reflect(f"Compliance report persisted for check_run_id={run.check_run_id}")
return {
"check_run_id": run.check_run_id,
"candidate_id": run.candidate_id,
"status": "running",
"started_at": run.started_at.isoformat(),
}
# [/DEF:start_check:Function]
# [DEF:get_check_status:Function]
# @PURPOSE: Return terminal/intermediate status payload for a check run.
# @PRE: check_run_id references an existing run.
# @POST: Deterministic payload shape includes checks and violations arrays.
@router.get("/checks/{check_run_id}")
async def get_check_status(check_run_id: str, repository: CleanReleaseRepository = Depends(get_clean_release_repository)):
with belief_scope("clean_release.get_check_status"):
run = repository.get_check_run(check_run_id)
if run is None:
raise HTTPException(status_code=404, detail={"message": "Check run not found", "code": "CHECK_NOT_FOUND"})
logger.reflect(f"Returning check status for check_run_id={check_run_id}")
return {
"check_run_id": run.check_run_id,
"candidate_id": run.candidate_id,
"final_status": run.final_status.value,
"started_at": run.started_at.isoformat(),
"finished_at": run.finished_at.isoformat() if run.finished_at else None,
"checks": [c.model_dump() for c in run.checks],
"violations": [v.model_dump() for v in repository.get_violations_by_check_run(check_run_id)],
}
# [/DEF:get_check_status:Function]
# [DEF:get_report:Function]
# @PURPOSE: Return persisted compliance report by report_id.
# @PRE: report_id references an existing report.
# @POST: Returns serialized report object.
@router.get("/reports/{report_id}")
async def get_report(report_id: str, repository: CleanReleaseRepository = Depends(get_clean_release_repository)):
with belief_scope("clean_release.get_report"):
report = repository.get_report(report_id)
if report is None:
raise HTTPException(status_code=404, detail={"message": "Report not found", "code": "REPORT_NOT_FOUND"})
logger.reflect(f"Returning compliance report report_id={report_id}")
return report.model_dump()
# [/DEF:get_report:Function]
# [/DEF:backend.src.api.routes.clean_release:Module]

View File

@@ -1,6 +1,6 @@
# [DEF:backend.src.api.routes.dashboards:Module]
#
# @TIER: STANDARD
# @TIER: CRITICAL
# @SEMANTICS: api, dashboards, resources, hub
# @PURPOSE: API endpoints for the Dashboard Hub - listing dashboards with Git and task status
# @LAYER: API
@@ -9,6 +9,27 @@
# @RELATION: DEPENDS_ON -> backend.src.core.superset_client
#
# @INVARIANT: All dashboard responses include git_status and last_task metadata
#
# @TEST_CONTRACT: DashboardsAPI -> {
# required_fields: {env_id: string, page: integer, page_size: integer},
# optional_fields: {search: string},
# invariants: ["Pagination must be valid", "Environment must exist"]
# }
#
# @TEST_FIXTURE: dashboard_list_happy -> {
# "env_id": "prod",
# "expected_count": 1,
# "dashboards": [{"id": 1, "title": "Main Revenue"}]
# }
#
# @TEST_EDGE: pagination_zero_page -> {"env_id": "prod", "page": 0, "status": 400}
# @TEST_EDGE: pagination_oversize -> {"env_id": "prod", "page_size": 101, "status": 400}
# @TEST_EDGE: missing_env -> {"env_id": "ghost", "status": 404}
# @TEST_EDGE: empty_dashboards -> {"env_id": "empty_env", "expected_total": 0}
# @TEST_EDGE: external_superset_failure -> {"env_id": "bad_conn", "status": 503}
#
# @TEST_INVARIANT: metadata_consistency -> verifies: [dashboard_list_happy, empty_dashboards]
#
# [SECTION: IMPORTS]
from fastapi import APIRouter, Depends, HTTPException, Query, Response
@@ -21,6 +42,7 @@ from ...dependencies import get_config_manager, get_task_manager, get_resource_s
from ...core.logger import logger, belief_scope
from ...core.superset_client import SupersetClient
from ...core.utils.network import DashboardNotFoundError
from ...services.resource_service import ResourceService
# [/SECTION]
router = APIRouter(prefix="/api/dashboards", tags=["Dashboards"])
@@ -36,7 +58,11 @@ class GitStatus(BaseModel):
# [DEF:LastTask:DataClass]
class LastTask(BaseModel):
task_id: Optional[str] = None
status: Optional[str] = Field(None, pattern="^RUNNING|SUCCESS|ERROR|WAITING_INPUT$")
status: Optional[str] = Field(
None,
pattern="^PENDING|RUNNING|SUCCESS|FAILED|ERROR|AWAITING_INPUT|WAITING_INPUT|AWAITING_MAPPING$",
)
validation_status: Optional[str] = Field(None, pattern="^PASS|FAIL|WARN|UNKNOWN$")
# [/DEF:LastTask:DataClass]
# [DEF:DashboardItem:DataClass]
@@ -46,6 +72,9 @@ class DashboardItem(BaseModel):
slug: Optional[str] = None
url: Optional[str] = None
last_modified: Optional[str] = None
created_by: Optional[str] = None
modified_by: Optional[str] = None
owners: Optional[List[str]] = None
git_status: Optional[GitStatus] = None
last_task: Optional[LastTask] = None
# [/DEF:DashboardItem:DataClass]
@@ -126,6 +155,93 @@ class DatabaseMappingsResponse(BaseModel):
mappings: List[DatabaseMapping]
# [/DEF:DatabaseMappingsResponse:DataClass]
# [DEF:_find_dashboard_id_by_slug:Function]
# @PURPOSE: Resolve dashboard numeric ID by slug using Superset list endpoint.
# @PRE: `dashboard_slug` is non-empty.
# @POST: Returns dashboard ID when found, otherwise None.
def _find_dashboard_id_by_slug(
client: SupersetClient,
dashboard_slug: str,
) -> Optional[int]:
query_variants = [
{"filters": [{"col": "slug", "opr": "eq", "value": dashboard_slug}], "page": 0, "page_size": 1},
{"filters": [{"col": "slug", "op": "eq", "value": dashboard_slug}], "page": 0, "page_size": 1},
]
for query in query_variants:
try:
_count, dashboards = client.get_dashboards_page(query=query)
if dashboards:
resolved_id = dashboards[0].get("id")
if resolved_id is not None:
return int(resolved_id)
except Exception:
continue
return None
# [/DEF:_find_dashboard_id_by_slug:Function]
# [DEF:_resolve_dashboard_id_from_ref:Function]
# @PURPOSE: Resolve dashboard ID from slug-first reference with numeric fallback.
# @PRE: `dashboard_ref` is provided in route path.
# @POST: Returns a valid dashboard ID or raises HTTPException(404).
def _resolve_dashboard_id_from_ref(
dashboard_ref: str,
client: SupersetClient,
) -> int:
normalized_ref = str(dashboard_ref or "").strip()
if not normalized_ref:
raise HTTPException(status_code=404, detail="Dashboard not found")
# Slug-first: even if ref looks numeric, try slug first.
slug_match_id = _find_dashboard_id_by_slug(client, normalized_ref)
if slug_match_id is not None:
return slug_match_id
if normalized_ref.isdigit():
return int(normalized_ref)
raise HTTPException(status_code=404, detail="Dashboard not found")
# [/DEF:_resolve_dashboard_id_from_ref:Function]
# [DEF:_normalize_filter_values:Function]
# @PURPOSE: Normalize query filter values to lower-cased non-empty tokens.
# @PRE: values may be None or list of strings.
# @POST: Returns trimmed normalized list preserving input order.
def _normalize_filter_values(values: Optional[List[str]]) -> List[str]:
if not values:
return []
normalized: List[str] = []
for value in values:
token = str(value or "").strip().lower()
if token:
normalized.append(token)
return normalized
# [/DEF:_normalize_filter_values:Function]
# [DEF:_dashboard_git_filter_value:Function]
# @PURPOSE: Build comparable git status token for dashboards filtering.
# @PRE: dashboard payload may contain git_status or None.
# @POST: Returns one of ok|diff|no_repo|error|pending.
def _dashboard_git_filter_value(dashboard: Dict[str, Any]) -> str:
git_status = dashboard.get("git_status") or {}
sync_status = str(git_status.get("sync_status") or "").strip().upper()
has_repo = git_status.get("has_repo")
if has_repo is False or sync_status == "NO_REPO":
return "no_repo"
if sync_status == "DIFF":
return "diff"
if sync_status == "OK":
return "ok"
if sync_status == "ERROR":
return "error"
return "pending"
# [/DEF:_dashboard_git_filter_value:Function]
# [DEF:get_dashboards:Function]
# @PURPOSE: Fetch list of dashboards from a specific environment with Git status and last task status
# @PRE: env_id must be a valid environment ID
@@ -145,6 +261,11 @@ async def get_dashboards(
search: Optional[str] = None,
page: int = 1,
page_size: int = 10,
filter_title: Optional[List[str]] = Query(default=None),
filter_git_status: Optional[List[str]] = Query(default=None),
filter_llm_status: Optional[List[str]] = Query(default=None),
filter_changed_on: Optional[List[str]] = Query(default=None),
filter_actor: Optional[List[str]] = Query(default=None),
config_manager=Depends(get_config_manager),
task_manager=Depends(get_task_manager),
resource_service=Depends(get_resource_service),
@@ -169,27 +290,134 @@ async def get_dashboards(
try:
# Get all tasks for status lookup
all_tasks = task_manager.get_all_tasks()
# Fetch dashboards with status using ResourceService
dashboards = await resource_service.get_dashboards_with_status(env, all_tasks)
# Apply search filter if provided
if search:
search_lower = search.lower()
dashboards = [
d for d in dashboards
if search_lower in d.get('title', '').lower()
or search_lower in d.get('slug', '').lower()
]
# Calculate pagination
total = len(dashboards)
total_pages = (total + page_size - 1) // page_size if total > 0 else 1
start_idx = (page - 1) * page_size
end_idx = start_idx + page_size
# Slice dashboards for current page
paginated_dashboards = dashboards[start_idx:end_idx]
title_filters = _normalize_filter_values(filter_title)
git_filters = _normalize_filter_values(filter_git_status)
llm_filters = _normalize_filter_values(filter_llm_status)
changed_on_filters = _normalize_filter_values(filter_changed_on)
actor_filters = _normalize_filter_values(filter_actor)
has_column_filters = any(
(
title_filters,
git_filters,
llm_filters,
changed_on_filters,
actor_filters,
)
)
# Fast path: real ResourceService -> one Superset page call per API request.
if isinstance(resource_service, ResourceService) and not has_column_filters:
try:
page_payload = await resource_service.get_dashboards_page_with_status(
env,
all_tasks,
page=page,
page_size=page_size,
search=search,
include_git_status=False,
)
paginated_dashboards = page_payload["dashboards"]
total = page_payload["total"]
total_pages = page_payload["total_pages"]
except Exception as page_error:
logger.warning(
"[get_dashboards][Action] Page-based fetch failed; using compatibility fallback: %s",
page_error,
)
dashboards = await resource_service.get_dashboards_with_status(
env,
all_tasks,
include_git_status=False,
)
if search:
search_lower = search.lower()
dashboards = [
d for d in dashboards
if search_lower in d.get('title', '').lower()
or search_lower in d.get('slug', '').lower()
]
total = len(dashboards)
total_pages = (total + page_size - 1) // page_size if total > 0 else 1
start_idx = (page - 1) * page_size
end_idx = start_idx + page_size
paginated_dashboards = dashboards[start_idx:end_idx]
elif isinstance(resource_service, ResourceService) and has_column_filters:
dashboards = await resource_service.get_dashboards_with_status(
env,
all_tasks,
include_git_status=bool(git_filters),
)
if search:
search_lower = search.lower()
dashboards = [
d for d in dashboards
if search_lower in d.get("title", "").lower()
or search_lower in d.get("slug", "").lower()
]
def _matches_dashboard_filters(dashboard: Dict[str, Any]) -> bool:
title_value = str(dashboard.get("title") or "").strip().lower()
if title_filters and title_value not in title_filters:
return False
if git_filters:
git_value = _dashboard_git_filter_value(dashboard)
if git_value not in git_filters:
return False
llm_value = str(
((dashboard.get("last_task") or {}).get("validation_status"))
or "UNKNOWN"
).strip().lower()
if llm_filters and llm_value not in llm_filters:
return False
changed_on_raw = str(dashboard.get("last_modified") or "").strip().lower()
changed_on_prefix = changed_on_raw[:10] if len(changed_on_raw) >= 10 else changed_on_raw
if changed_on_filters and changed_on_raw not in changed_on_filters and changed_on_prefix not in changed_on_filters:
return False
owners = dashboard.get("owners") or []
if isinstance(owners, list):
actor_value = ", ".join(str(item).strip() for item in owners if str(item).strip()).lower()
else:
actor_value = str(owners).strip().lower()
if not actor_value:
actor_value = "-"
if actor_filters and actor_value not in actor_filters:
return False
return True
dashboards = [d for d in dashboards if _matches_dashboard_filters(d)]
total = len(dashboards)
total_pages = (total + page_size - 1) // page_size if total > 0 else 1
start_idx = (page - 1) * page_size
end_idx = start_idx + page_size
paginated_dashboards = dashboards[start_idx:end_idx]
else:
# Compatibility path for mocked services in route tests.
dashboards = await resource_service.get_dashboards_with_status(
env,
all_tasks,
include_git_status=False,
)
if search:
search_lower = search.lower()
dashboards = [
d for d in dashboards
if search_lower in d.get('title', '').lower()
or search_lower in d.get('slug', '').lower()
]
total = len(dashboards)
total_pages = (total + page_size - 1) // page_size if total > 0 else 1
start_idx = (page - 1) * page_size
end_idx = start_idx + page_size
paginated_dashboards = dashboards[start_idx:end_idx]
logger.info(f"[get_dashboards][Coherence:OK] Returning {len(paginated_dashboards)} dashboards (page {page}/{total_pages}, total: {total})")
@@ -219,10 +447,23 @@ async def get_dashboards(
async def get_database_mappings(
source_env_id: str,
target_env_id: str,
config_manager=Depends(get_config_manager),
mapping_service=Depends(get_mapping_service),
_ = Depends(has_permission("plugin:migration", "READ"))
):
with belief_scope("get_database_mappings", f"source={source_env_id}, target={target_env_id}"):
# Validate environments exist
environments = config_manager.get_environments()
source_env = next((e for e in environments if e.id == source_env_id), None)
target_env = next((e for e in environments if e.id == target_env_id), None)
if not source_env:
logger.error(f"[get_database_mappings][Coherence:Failed] Source environment not found: {source_env_id}")
raise HTTPException(status_code=404, detail="Source environment not found")
if not target_env:
logger.error(f"[get_database_mappings][Coherence:Failed] Target environment not found: {target_env_id}")
raise HTTPException(status_code=404, detail="Target environment not found")
try:
# Get mapping suggestions using MappingService
suggestions = await mapping_service.get_suggestions(source_env_id, target_env_id)
@@ -250,17 +491,17 @@ async def get_database_mappings(
# [DEF:get_dashboard_detail:Function]
# @PURPOSE: Fetch detailed dashboard info with related charts and datasets
# @PRE: env_id must be valid and dashboard_id must exist
# @PRE: env_id must be valid and dashboard ref (slug or id) must exist
# @POST: Returns dashboard detail payload for overview page
# @RELATION: CALLS -> SupersetClient.get_dashboard_detail
@router.get("/{dashboard_id:int}", response_model=DashboardDetailResponse)
@router.get("/{dashboard_ref}", response_model=DashboardDetailResponse)
async def get_dashboard_detail(
dashboard_id: int,
dashboard_ref: str,
env_id: str,
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:migration", "READ"))
):
with belief_scope("get_dashboard_detail", f"dashboard_id={dashboard_id}, env_id={env_id}"):
with belief_scope("get_dashboard_detail", f"dashboard_ref={dashboard_ref}, env_id={env_id}"):
environments = config_manager.get_environments()
env = next((e for e in environments if e.id == env_id), None)
if not env:
@@ -269,9 +510,10 @@ async def get_dashboard_detail(
try:
client = SupersetClient(env)
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, client)
detail = client.get_dashboard_detail(dashboard_id)
logger.info(
f"[get_dashboard_detail][Coherence:OK] Dashboard {dashboard_id}: {detail.get('chart_count', 0)} charts, {detail.get('dataset_count', 0)} datasets"
f"[get_dashboard_detail][Coherence:OK] Dashboard ref={dashboard_ref} resolved_id={dashboard_id}: {detail.get('chart_count', 0)} charts, {detail.get('dataset_count', 0)} datasets"
)
return DashboardDetailResponse(**detail)
except HTTPException:
@@ -317,17 +559,38 @@ def _task_matches_dashboard(task: Any, dashboard_id: int, env_id: Optional[str])
# [DEF:get_dashboard_tasks_history:Function]
# @PURPOSE: Returns history of backup and LLM validation tasks for a dashboard.
# @PRE: dashboard_id is valid integer.
# @PRE: dashboard ref (slug or id) is valid.
# @POST: Response contains sorted task history (newest first).
@router.get("/{dashboard_id:int}/tasks", response_model=DashboardTaskHistoryResponse)
@router.get("/{dashboard_ref}/tasks", response_model=DashboardTaskHistoryResponse)
async def get_dashboard_tasks_history(
dashboard_id: int,
dashboard_ref: str,
env_id: Optional[str] = None,
limit: int = Query(20, ge=1, le=100),
config_manager=Depends(get_config_manager),
task_manager=Depends(get_task_manager),
_ = Depends(has_permission("tasks", "READ"))
):
with belief_scope("get_dashboard_tasks_history", f"dashboard_id={dashboard_id}, env_id={env_id}, limit={limit}"):
with belief_scope("get_dashboard_tasks_history", f"dashboard_ref={dashboard_ref}, env_id={env_id}, limit={limit}"):
dashboard_id: Optional[int] = None
if dashboard_ref.isdigit():
dashboard_id = int(dashboard_ref)
elif env_id:
environments = config_manager.get_environments()
env = next((e for e in environments if e.id == env_id), None)
if not env:
logger.error(f"[get_dashboard_tasks_history][Coherence:Failed] Environment not found: {env_id}")
raise HTTPException(status_code=404, detail="Environment not found")
client = SupersetClient(env)
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, client)
else:
logger.error(
"[get_dashboard_tasks_history][Coherence:Failed] Non-numeric dashboard ref requires env_id"
)
raise HTTPException(
status_code=400,
detail="env_id is required when dashboard reference is a slug",
)
matching_tasks = []
for task in task_manager.get_all_tasks():
if _task_matches_dashboard(task, dashboard_id, env_id):
@@ -370,7 +633,7 @@ async def get_dashboard_tasks_history(
)
)
logger.info(f"[get_dashboard_tasks_history][Coherence:OK] Found {len(items)} tasks for dashboard {dashboard_id}")
logger.info(f"[get_dashboard_tasks_history][Coherence:OK] Found {len(items)} tasks for dashboard_ref={dashboard_ref}, dashboard_id={dashboard_id}")
return DashboardTaskHistoryResponse(dashboard_id=dashboard_id, items=items)
# [/DEF:get_dashboard_tasks_history:Function]
@@ -379,15 +642,15 @@ async def get_dashboard_tasks_history(
# @PURPOSE: Proxies Superset dashboard thumbnail with cache support.
# @PRE: env_id must exist.
# @POST: Returns image bytes or 202 when thumbnail is being prepared by Superset.
@router.get("/{dashboard_id:int}/thumbnail")
@router.get("/{dashboard_ref}/thumbnail")
async def get_dashboard_thumbnail(
dashboard_id: int,
dashboard_ref: str,
env_id: str,
force: bool = Query(False),
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:migration", "READ"))
):
with belief_scope("get_dashboard_thumbnail", f"dashboard_id={dashboard_id}, env_id={env_id}, force={force}"):
with belief_scope("get_dashboard_thumbnail", f"dashboard_ref={dashboard_ref}, env_id={env_id}, force={force}"):
environments = config_manager.get_environments()
env = next((e for e in environments if e.id == env_id), None)
if not env:
@@ -396,6 +659,7 @@ async def get_dashboard_thumbnail(
try:
client = SupersetClient(env)
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, client)
digest = None
thumb_endpoint = None

View File

@@ -20,6 +20,18 @@ from ...core.logger import belief_scope
router = APIRouter(prefix="/api/environments", tags=["Environments"])
# [DEF:_normalize_superset_env_url:Function]
# @PURPOSE: Canonicalize Superset environment URL to base host/path without trailing /api/v1.
# @PRE: raw_url can be empty.
# @POST: Returns normalized base URL.
def _normalize_superset_env_url(raw_url: str) -> str:
normalized = str(raw_url or "").strip().rstrip("/")
if normalized.lower().endswith("/api/v1"):
normalized = normalized[:-len("/api/v1")]
return normalized.rstrip("/")
# [/DEF:_normalize_superset_env_url:Function]
# [DEF:ScheduleSchema:DataClass]
class ScheduleSchema(BaseModel):
enabled: bool = False
@@ -31,6 +43,7 @@ class EnvironmentResponse(BaseModel):
id: str
name: str
url: str
stage: str = "DEV"
is_production: bool = False
backup_schedule: Optional[ScheduleSchema] = None
# [/DEF:EnvironmentResponse:DataClass]
@@ -59,18 +72,26 @@ async def get_environments(
# Ensure envs is a list
if not isinstance(envs, list):
envs = []
return [
EnvironmentResponse(
id=e.id,
name=e.name,
url=e.url,
is_production=getattr(e, "is_production", False),
backup_schedule=ScheduleSchema(
enabled=e.backup_schedule.enabled,
cron_expression=e.backup_schedule.cron_expression
) if getattr(e, 'backup_schedule', None) else None
) for e in envs
]
response_items = []
for e in envs:
resolved_stage = str(
getattr(e, "stage", "")
or ("PROD" if bool(getattr(e, "is_production", False)) else "DEV")
).upper()
response_items.append(
EnvironmentResponse(
id=e.id,
name=e.name,
url=_normalize_superset_env_url(e.url),
stage=resolved_stage,
is_production=(resolved_stage == "PROD"),
backup_schedule=ScheduleSchema(
enabled=e.backup_schedule.enabled,
cron_expression=e.backup_schedule.cron_expression
) if getattr(e, 'backup_schedule', None) else None
)
)
return response_items
# [/DEF:get_environments:Function]
# [DEF:update_environment_schedule:Function]

View File

@@ -14,16 +14,22 @@ from fastapi import APIRouter, Depends, HTTPException
from sqlalchemy.orm import Session
from typing import List, Optional
import typing
import os
from src.dependencies import get_config_manager, has_permission
from src.core.database import get_db
from src.models.git import GitServerConfig, GitRepository
from src.models.git import GitServerConfig, GitRepository, GitProvider
from src.api.routes.git_schemas import (
GitServerConfigSchema, GitServerConfigCreate,
BranchSchema, BranchCreate,
BranchCheckout, CommitSchema, CommitCreate,
DeploymentEnvironmentSchema, DeployRequest, RepoInitRequest
DeploymentEnvironmentSchema, DeployRequest, RepoInitRequest,
RepoStatusBatchRequest, RepoStatusBatchResponse,
GiteaRepoCreateRequest, GiteaRepoSchema,
RemoteRepoCreateRequest, RemoteRepoSchema,
PromoteRequest, PromoteResponse,
)
from src.services.git_service import GitService
from src.core.superset_client import SupersetClient
from src.core.logger import logger, belief_scope
from ...services.llm_prompt_templates import (
DEFAULT_LLM_PROMPTS,
@@ -33,6 +39,173 @@ from ...services.llm_prompt_templates import (
router = APIRouter(tags=["git"])
git_service = GitService()
MAX_REPOSITORY_STATUS_BATCH = 50
# [DEF:_build_no_repo_status_payload:Function]
# @PURPOSE: Build a consistent status payload for dashboards without initialized repositories.
# @PRE: None.
# @POST: Returns a stable payload compatible with frontend repository status parsing.
# @RETURN: dict
def _build_no_repo_status_payload() -> dict:
return {
"is_dirty": False,
"untracked_files": [],
"modified_files": [],
"staged_files": [],
"current_branch": None,
"upstream_branch": None,
"has_upstream": False,
"ahead_count": 0,
"behind_count": 0,
"is_diverged": False,
"sync_state": "NO_REPO",
"sync_status": "NO_REPO",
"has_repo": False,
}
# [/DEF:_build_no_repo_status_payload:Function]
# [DEF:_handle_unexpected_git_route_error:Function]
# @PURPOSE: Convert unexpected route-level exceptions to stable 500 API responses.
# @PRE: `error` is a non-HTTPException instance.
# @POST: Raises HTTPException(500) with route-specific context.
# @PARAM: route_name (str)
# @PARAM: error (Exception)
def _handle_unexpected_git_route_error(route_name: str, error: Exception) -> None:
logger.error(f"[{route_name}][Coherence:Failed] {error}")
raise HTTPException(status_code=500, detail=f"{route_name} failed: {str(error)}")
# [/DEF:_handle_unexpected_git_route_error:Function]
# [DEF:_resolve_repository_status:Function]
# @PURPOSE: Resolve repository status for one dashboard with graceful NO_REPO semantics.
# @PRE: `dashboard_id` is a valid integer.
# @POST: Returns standard status payload or `NO_REPO` payload when repository path is absent.
# @PARAM: dashboard_id (int)
# @RETURN: dict
def _resolve_repository_status(dashboard_id: int) -> dict:
repo_path = git_service._get_repo_path(dashboard_id)
if not os.path.exists(repo_path):
logger.debug(
f"[get_repository_status][Action] Repository is not initialized for dashboard {dashboard_id}"
)
return _build_no_repo_status_payload()
try:
return git_service.get_status(dashboard_id)
except HTTPException as e:
if e.status_code == 404:
logger.debug(
f"[get_repository_status][Action] Repository is not initialized for dashboard {dashboard_id}"
)
return _build_no_repo_status_payload()
raise
# [/DEF:_resolve_repository_status:Function]
# [DEF:_get_git_config_or_404:Function]
# @PURPOSE: Resolve GitServerConfig by id or raise 404.
# @PRE: db session is available.
# @POST: Returns GitServerConfig model.
def _get_git_config_or_404(db: Session, config_id: str) -> GitServerConfig:
config = db.query(GitServerConfig).filter(GitServerConfig.id == config_id).first()
if not config:
raise HTTPException(status_code=404, detail="Git configuration not found")
return config
# [/DEF:_get_git_config_or_404:Function]
# [DEF:_find_dashboard_id_by_slug:Function]
# @PURPOSE: Resolve dashboard numeric ID by slug in a specific environment.
# @PRE: dashboard_slug is non-empty.
# @POST: Returns dashboard ID or None when not found.
def _find_dashboard_id_by_slug(
client: SupersetClient,
dashboard_slug: str,
) -> Optional[int]:
query_variants = [
{"filters": [{"col": "slug", "opr": "eq", "value": dashboard_slug}], "page": 0, "page_size": 1},
{"filters": [{"col": "slug", "op": "eq", "value": dashboard_slug}], "page": 0, "page_size": 1},
]
for query in query_variants:
try:
_count, dashboards = client.get_dashboards_page(query=query)
if dashboards:
resolved_id = dashboards[0].get("id")
if resolved_id is not None:
return int(resolved_id)
except Exception:
continue
return None
# [/DEF:_find_dashboard_id_by_slug:Function]
# [DEF:_resolve_dashboard_id_from_ref:Function]
# @PURPOSE: Resolve dashboard ID from slug-or-id reference for Git routes.
# @PRE: dashboard_ref is provided; env_id is required for slug values.
# @POST: Returns numeric dashboard ID or raises HTTPException.
def _resolve_dashboard_id_from_ref(
dashboard_ref: str,
config_manager,
env_id: Optional[str] = None,
) -> int:
normalized_ref = str(dashboard_ref or "").strip()
if not normalized_ref:
raise HTTPException(status_code=400, detail="dashboard_ref is required")
if normalized_ref.isdigit():
return int(normalized_ref)
if not env_id:
raise HTTPException(
status_code=400,
detail="env_id is required for slug-based Git operations",
)
environments = config_manager.get_environments()
env = next((e for e in environments if e.id == env_id), None)
if not env:
raise HTTPException(status_code=404, detail="Environment not found")
dashboard_id = _find_dashboard_id_by_slug(SupersetClient(env), normalized_ref)
if dashboard_id is None:
raise HTTPException(status_code=404, detail=f"Dashboard slug '{normalized_ref}' not found")
return dashboard_id
# [/DEF:_resolve_dashboard_id_from_ref:Function]
# [DEF:_resolve_repo_key_from_ref:Function]
# @PURPOSE: Resolve repository folder key with slug-first strategy and deterministic fallback.
# @PRE: dashboard_id is resolved and valid.
# @POST: Returns safe key to be used in local repository path.
# @RETURN: str
def _resolve_repo_key_from_ref(
dashboard_ref: str,
dashboard_id: int,
config_manager,
env_id: Optional[str] = None,
) -> str:
normalized_ref = str(dashboard_ref or "").strip()
if normalized_ref and not normalized_ref.isdigit():
return normalized_ref
if env_id:
try:
environments = config_manager.get_environments()
env = next((e for e in environments if e.id == env_id), None)
if env:
payload = SupersetClient(env).get_dashboard(dashboard_id)
dashboard_data = payload.get("result", payload) if isinstance(payload, dict) else {}
dashboard_slug = dashboard_data.get("slug")
if dashboard_slug:
return str(dashboard_slug)
except Exception:
pass
return f"dashboard-{dashboard_id}"
# [/DEF:_resolve_repo_key_from_ref:Function]
# [DEF:get_git_configs:Function]
# @PURPOSE: List all configured Git servers.
@@ -107,20 +280,176 @@ async def test_git_config(
raise HTTPException(status_code=400, detail="Connection failed")
# [/DEF:test_git_config:Function]
# [DEF:list_gitea_repositories:Function]
# @PURPOSE: List repositories in Gitea for a saved Gitea config.
# @PRE: config_id exists and provider is GITEA.
# @POST: Returns repositories visible to PAT user.
@router.get("/config/{config_id}/gitea/repos", response_model=List[GiteaRepoSchema])
async def list_gitea_repositories(
config_id: str,
db: Session = Depends(get_db),
_ = Depends(has_permission("admin:settings", "READ"))
):
with belief_scope("list_gitea_repositories"):
config = _get_git_config_or_404(db, config_id)
if config.provider != GitProvider.GITEA:
raise HTTPException(status_code=400, detail="This endpoint supports GITEA provider only")
repos = await git_service.list_gitea_repositories(config.url, config.pat)
return [
GiteaRepoSchema(
name=repo.get("name", ""),
full_name=repo.get("full_name", ""),
private=bool(repo.get("private", False)),
clone_url=repo.get("clone_url"),
html_url=repo.get("html_url"),
ssh_url=repo.get("ssh_url"),
default_branch=repo.get("default_branch"),
)
for repo in repos
]
# [/DEF:list_gitea_repositories:Function]
# [DEF:create_gitea_repository:Function]
# @PURPOSE: Create a repository in Gitea for a saved Gitea config.
# @PRE: config_id exists and provider is GITEA.
# @POST: Returns created repository payload.
@router.post("/config/{config_id}/gitea/repos", response_model=GiteaRepoSchema)
async def create_gitea_repository(
config_id: str,
request: GiteaRepoCreateRequest,
db: Session = Depends(get_db),
_ = Depends(has_permission("admin:settings", "WRITE"))
):
with belief_scope("create_gitea_repository"):
config = _get_git_config_or_404(db, config_id)
if config.provider != GitProvider.GITEA:
raise HTTPException(status_code=400, detail="This endpoint supports GITEA provider only")
repo = await git_service.create_gitea_repository(
server_url=config.url,
pat=config.pat,
name=request.name,
private=request.private,
description=request.description,
auto_init=request.auto_init,
default_branch=request.default_branch,
)
return GiteaRepoSchema(
name=repo.get("name", ""),
full_name=repo.get("full_name", ""),
private=bool(repo.get("private", False)),
clone_url=repo.get("clone_url"),
html_url=repo.get("html_url"),
ssh_url=repo.get("ssh_url"),
default_branch=repo.get("default_branch"),
)
# [/DEF:create_gitea_repository:Function]
# [DEF:create_remote_repository:Function]
# @PURPOSE: Create repository on remote Git server using selected provider config.
# @PRE: config_id exists and PAT has creation permissions.
# @POST: Returns normalized remote repository payload.
@router.post("/config/{config_id}/repositories", response_model=RemoteRepoSchema)
async def create_remote_repository(
config_id: str,
request: RemoteRepoCreateRequest,
db: Session = Depends(get_db),
_ = Depends(has_permission("admin:settings", "WRITE"))
):
with belief_scope("create_remote_repository"):
config = _get_git_config_or_404(db, config_id)
if config.provider == GitProvider.GITEA:
repo = await git_service.create_gitea_repository(
server_url=config.url,
pat=config.pat,
name=request.name,
private=request.private,
description=request.description,
auto_init=request.auto_init,
default_branch=request.default_branch,
)
elif config.provider == GitProvider.GITHUB:
repo = await git_service.create_github_repository(
server_url=config.url,
pat=config.pat,
name=request.name,
private=request.private,
description=request.description,
auto_init=request.auto_init,
default_branch=request.default_branch,
)
elif config.provider == GitProvider.GITLAB:
repo = await git_service.create_gitlab_repository(
server_url=config.url,
pat=config.pat,
name=request.name,
private=request.private,
description=request.description,
auto_init=request.auto_init,
default_branch=request.default_branch,
)
else:
raise HTTPException(status_code=501, detail=f"Provider {config.provider} is not supported")
return RemoteRepoSchema(
provider=config.provider,
name=repo.get("name", ""),
full_name=repo.get("full_name", repo.get("name", "")),
private=bool(repo.get("private", False)),
clone_url=repo.get("clone_url"),
html_url=repo.get("html_url"),
ssh_url=repo.get("ssh_url"),
default_branch=repo.get("default_branch"),
)
# [/DEF:create_remote_repository:Function]
# [DEF:delete_gitea_repository:Function]
# @PURPOSE: Delete repository in Gitea for a saved Gitea config.
# @PRE: config_id exists and provider is GITEA.
# @POST: Target repository is deleted on Gitea.
@router.delete("/config/{config_id}/gitea/repos/{owner}/{repo_name}")
async def delete_gitea_repository(
config_id: str,
owner: str,
repo_name: str,
db: Session = Depends(get_db),
_ = Depends(has_permission("admin:settings", "WRITE"))
):
with belief_scope("delete_gitea_repository"):
config = _get_git_config_or_404(db, config_id)
if config.provider != GitProvider.GITEA:
raise HTTPException(status_code=400, detail="This endpoint supports GITEA provider only")
await git_service.delete_gitea_repository(
server_url=config.url,
pat=config.pat,
owner=owner,
repo_name=repo_name,
)
return {"status": "success", "message": "Repository deleted"}
# [/DEF:delete_gitea_repository:Function]
# [DEF:init_repository:Function]
# @PURPOSE: Link a dashboard to a Git repository and perform initial clone/init.
# @PRE: `dashboard_id` exists and `init_data` contains valid config_id and remote_url.
# @PRE: `dashboard_ref` exists and `init_data` contains valid config_id and remote_url.
# @POST: Repository is initialized on disk and a GitRepository record is saved in DB.
# @PARAM: dashboard_id (int)
# @PARAM: dashboard_ref (str)
# @PARAM: init_data (RepoInitRequest)
@router.post("/repositories/{dashboard_id}/init")
@router.post("/repositories/{dashboard_ref}/init")
async def init_repository(
dashboard_id: int,
dashboard_ref: str,
init_data: RepoInitRequest,
env_id: Optional[str] = None,
config_manager=Depends(get_config_manager),
db: Session = Depends(get_db),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("init_repository"):
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
repo_key = _resolve_repo_key_from_ref(dashboard_ref, dashboard_id, config_manager, env_id)
# 1. Get config
config = db.query(GitServerConfig).filter(GitServerConfig.id == init_data.config_id).first()
if not config:
@@ -129,10 +458,10 @@ async def init_repository(
try:
# 2. Perform Git clone/init
logger.info(f"[init_repository][Action] Initializing repo for dashboard {dashboard_id}")
git_service.init_repo(dashboard_id, init_data.remote_url, config.pat)
git_service.init_repo(dashboard_id, init_data.remote_url, config.pat, repo_key=repo_key)
# 3. Save to DB
repo_path = git_service._get_repo_path(dashboard_id)
repo_path = git_service._get_repo_path(dashboard_id, repo_key=repo_key)
db_repo = db.query(GitRepository).filter(GitRepository.dashboard_id == dashboard_id).first()
if not db_repo:
db_repo = GitRepository(
@@ -153,137 +482,172 @@ async def init_repository(
except Exception as e:
db.rollback()
logger.error(f"[init_repository][Coherence:Failed] Failed to init repository: {e}")
raise HTTPException(status_code=400, detail=str(e))
if isinstance(e, HTTPException):
raise
_handle_unexpected_git_route_error("init_repository", e)
# [/DEF:init_repository:Function]
# [DEF:get_branches:Function]
# @PURPOSE: List all branches for a dashboard's repository.
# @PRE: Repository for `dashboard_id` is initialized.
# @PRE: Repository for `dashboard_ref` is initialized.
# @POST: Returns a list of branches from the local repository.
# @PARAM: dashboard_id (int)
# @PARAM: dashboard_ref (str)
# @RETURN: List[BranchSchema]
@router.get("/repositories/{dashboard_id}/branches", response_model=List[BranchSchema])
@router.get("/repositories/{dashboard_ref}/branches", response_model=List[BranchSchema])
async def get_branches(
dashboard_id: int,
dashboard_ref: str,
env_id: Optional[str] = None,
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("get_branches"):
try:
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
return git_service.list_branches(dashboard_id)
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=404, detail=str(e))
_handle_unexpected_git_route_error("get_branches", e)
# [/DEF:get_branches:Function]
# [DEF:create_branch:Function]
# @PURPOSE: Create a new branch in the dashboard's repository.
# @PRE: `dashboard_id` repository exists and `branch_data` has name and from_branch.
# @PRE: `dashboard_ref` repository exists and `branch_data` has name and from_branch.
# @POST: A new branch is created in the local repository.
# @PARAM: dashboard_id (int)
# @PARAM: dashboard_ref (str)
# @PARAM: branch_data (BranchCreate)
@router.post("/repositories/{dashboard_id}/branches")
@router.post("/repositories/{dashboard_ref}/branches")
async def create_branch(
dashboard_id: int,
dashboard_ref: str,
branch_data: BranchCreate,
env_id: Optional[str] = None,
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("create_branch"):
try:
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
git_service.create_branch(dashboard_id, branch_data.name, branch_data.from_branch)
return {"status": "success"}
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=400, detail=str(e))
_handle_unexpected_git_route_error("create_branch", e)
# [/DEF:create_branch:Function]
# [DEF:checkout_branch:Function]
# @PURPOSE: Switch the dashboard's repository to a specific branch.
# @PRE: `dashboard_id` repository exists and branch `checkout_data.name` exists.
# @PRE: `dashboard_ref` repository exists and branch `checkout_data.name` exists.
# @POST: The local repository HEAD is moved to the specified branch.
# @PARAM: dashboard_id (int)
# @PARAM: dashboard_ref (str)
# @PARAM: checkout_data (BranchCheckout)
@router.post("/repositories/{dashboard_id}/checkout")
@router.post("/repositories/{dashboard_ref}/checkout")
async def checkout_branch(
dashboard_id: int,
dashboard_ref: str,
checkout_data: BranchCheckout,
env_id: Optional[str] = None,
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("checkout_branch"):
try:
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
git_service.checkout_branch(dashboard_id, checkout_data.name)
return {"status": "success"}
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=400, detail=str(e))
_handle_unexpected_git_route_error("checkout_branch", e)
# [/DEF:checkout_branch:Function]
# [DEF:commit_changes:Function]
# @PURPOSE: Stage and commit changes in the dashboard's repository.
# @PRE: `dashboard_id` repository exists and `commit_data` has message and files.
# @PRE: `dashboard_ref` repository exists and `commit_data` has message and files.
# @POST: Specified files are staged and a new commit is created.
# @PARAM: dashboard_id (int)
# @PARAM: dashboard_ref (str)
# @PARAM: commit_data (CommitCreate)
@router.post("/repositories/{dashboard_id}/commit")
@router.post("/repositories/{dashboard_ref}/commit")
async def commit_changes(
dashboard_id: int,
dashboard_ref: str,
commit_data: CommitCreate,
env_id: Optional[str] = None,
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("commit_changes"):
try:
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
git_service.commit_changes(dashboard_id, commit_data.message, commit_data.files)
return {"status": "success"}
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=400, detail=str(e))
_handle_unexpected_git_route_error("commit_changes", e)
# [/DEF:commit_changes:Function]
# [DEF:push_changes:Function]
# @PURPOSE: Push local commits to the remote repository.
# @PRE: `dashboard_id` repository exists and has a remote configured.
# @PRE: `dashboard_ref` repository exists and has a remote configured.
# @POST: Local commits are pushed to the remote repository.
# @PARAM: dashboard_id (int)
@router.post("/repositories/{dashboard_id}/push")
# @PARAM: dashboard_ref (str)
@router.post("/repositories/{dashboard_ref}/push")
async def push_changes(
dashboard_id: int,
dashboard_ref: str,
env_id: Optional[str] = None,
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("push_changes"):
try:
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
git_service.push_changes(dashboard_id)
return {"status": "success"}
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=400, detail=str(e))
_handle_unexpected_git_route_error("push_changes", e)
# [/DEF:push_changes:Function]
# [DEF:pull_changes:Function]
# @PURPOSE: Pull changes from the remote repository.
# @PRE: `dashboard_id` repository exists and has a remote configured.
# @PRE: `dashboard_ref` repository exists and has a remote configured.
# @POST: Remote changes are fetched and merged into the local branch.
# @PARAM: dashboard_id (int)
@router.post("/repositories/{dashboard_id}/pull")
# @PARAM: dashboard_ref (str)
@router.post("/repositories/{dashboard_ref}/pull")
async def pull_changes(
dashboard_id: int,
dashboard_ref: str,
env_id: Optional[str] = None,
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("pull_changes"):
try:
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
git_service.pull_changes(dashboard_id)
return {"status": "success"}
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=400, detail=str(e))
_handle_unexpected_git_route_error("pull_changes", e)
# [/DEF:pull_changes:Function]
# [DEF:sync_dashboard:Function]
# @PURPOSE: Sync dashboard state from Superset to Git using the GitPlugin.
# @PRE: `dashboard_id` is valid; GitPlugin is available.
# @PRE: `dashboard_ref` is valid; GitPlugin is available.
# @POST: Dashboard YAMLs are exported from Superset and committed to Git.
# @PARAM: dashboard_id (int)
# @PARAM: dashboard_ref (str)
# @PARAM: source_env_id (Optional[str])
@router.post("/repositories/{dashboard_id}/sync")
@router.post("/repositories/{dashboard_ref}/sync")
async def sync_dashboard(
dashboard_id: int,
dashboard_ref: str,
env_id: Optional[str] = None,
source_env_id: typing.Optional[str] = None,
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("sync_dashboard"):
try:
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
from src.plugins.git_plugin import GitPlugin
plugin = GitPlugin()
return await plugin.execute({
@@ -291,10 +655,113 @@ async def sync_dashboard(
"dashboard_id": dashboard_id,
"source_env_id": source_env_id
})
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=400, detail=str(e))
_handle_unexpected_git_route_error("sync_dashboard", e)
# [/DEF:sync_dashboard:Function]
# [DEF:promote_dashboard:Function]
# @PURPOSE: Promote changes between branches via MR or direct merge.
# @PRE: dashboard repository is initialized and Git config is valid.
# @POST: Returns promotion result metadata.
@router.post("/repositories/{dashboard_ref}/promote", response_model=PromoteResponse)
async def promote_dashboard(
dashboard_ref: str,
payload: PromoteRequest,
env_id: Optional[str] = None,
config_manager=Depends(get_config_manager),
db: Session = Depends(get_db),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("promote_dashboard"):
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
db_repo = db.query(GitRepository).filter(GitRepository.dashboard_id == dashboard_id).first()
if not db_repo:
raise HTTPException(status_code=404, detail=f"Repository for dashboard {dashboard_ref} is not initialized")
config = _get_git_config_or_404(db, db_repo.config_id)
from_branch = payload.from_branch.strip()
to_branch = payload.to_branch.strip()
if not from_branch or not to_branch:
raise HTTPException(status_code=400, detail="from_branch and to_branch are required")
if from_branch == to_branch:
raise HTTPException(status_code=400, detail="from_branch and to_branch must be different")
mode = (payload.mode or "mr").strip().lower()
if mode == "direct":
reason = (payload.reason or "").strip()
if not reason:
raise HTTPException(status_code=400, detail="Direct promote requires non-empty reason")
logger.warning(
"[promote_dashboard][PolicyViolation] Direct promote without MR by actor=unknown dashboard_ref=%s from=%s to=%s reason=%s",
dashboard_ref,
from_branch,
to_branch,
reason,
)
result = git_service.promote_direct_merge(
dashboard_id=dashboard_id,
from_branch=from_branch,
to_branch=to_branch,
)
return PromoteResponse(
mode="direct",
from_branch=from_branch,
to_branch=to_branch,
status=result.get("status", "merged"),
policy_violation=True,
)
title = (payload.title or "").strip() or f"Promote {from_branch} -> {to_branch}"
description = payload.description
if config.provider == GitProvider.GITEA:
pr = await git_service.create_gitea_pull_request(
server_url=config.url,
pat=config.pat,
remote_url=db_repo.remote_url,
from_branch=from_branch,
to_branch=to_branch,
title=title,
description=description,
)
elif config.provider == GitProvider.GITHUB:
pr = await git_service.create_github_pull_request(
server_url=config.url,
pat=config.pat,
remote_url=db_repo.remote_url,
from_branch=from_branch,
to_branch=to_branch,
title=title,
description=description,
draft=payload.draft,
)
elif config.provider == GitProvider.GITLAB:
pr = await git_service.create_gitlab_merge_request(
server_url=config.url,
pat=config.pat,
remote_url=db_repo.remote_url,
from_branch=from_branch,
to_branch=to_branch,
title=title,
description=description,
remove_source_branch=payload.remove_source_branch,
)
else:
raise HTTPException(status_code=501, detail=f"Provider {config.provider} does not support promotion API")
return PromoteResponse(
mode="mr",
from_branch=from_branch,
to_branch=to_branch,
status=pr.get("status", "opened"),
url=pr.get("url"),
reference_id=str(pr.get("id")) if pr.get("id") is not None else None,
policy_violation=False,
)
# [/DEF:promote_dashboard:Function]
# [DEF:get_environments:Function]
# @PURPOSE: List all deployment environments.
# @PRE: Config manager is accessible.
@@ -319,18 +786,21 @@ async def get_environments(
# [DEF:deploy_dashboard:Function]
# @PURPOSE: Deploy dashboard from Git to a target environment.
# @PRE: `dashboard_id` and `deploy_data.environment_id` are valid.
# @PRE: `dashboard_ref` and `deploy_data.environment_id` are valid.
# @POST: Dashboard YAMLs are read from Git and imported into the target Superset.
# @PARAM: dashboard_id (int)
# @PARAM: dashboard_ref (str)
# @PARAM: deploy_data (DeployRequest)
@router.post("/repositories/{dashboard_id}/deploy")
@router.post("/repositories/{dashboard_ref}/deploy")
async def deploy_dashboard(
dashboard_id: int,
dashboard_ref: str,
deploy_data: DeployRequest,
env_id: Optional[str] = None,
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("deploy_dashboard"):
try:
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
from src.plugins.git_plugin import GitPlugin
plugin = GitPlugin()
return await plugin.execute({
@@ -338,84 +808,147 @@ async def deploy_dashboard(
"dashboard_id": dashboard_id,
"environment_id": deploy_data.environment_id
})
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=400, detail=str(e))
_handle_unexpected_git_route_error("deploy_dashboard", e)
# [/DEF:deploy_dashboard:Function]
# [DEF:get_history:Function]
# @PURPOSE: View commit history for a dashboard's repository.
# @PRE: `dashboard_id` repository exists.
# @PRE: `dashboard_ref` repository exists.
# @POST: Returns a list of recent commits from the repository.
# @PARAM: dashboard_id (int)
# @PARAM: dashboard_ref (str)
# @PARAM: limit (int)
# @RETURN: List[CommitSchema]
@router.get("/repositories/{dashboard_id}/history", response_model=List[CommitSchema])
@router.get("/repositories/{dashboard_ref}/history", response_model=List[CommitSchema])
async def get_history(
dashboard_id: int,
dashboard_ref: str,
limit: int = 50,
env_id: Optional[str] = None,
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("get_history"):
try:
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
return git_service.get_commit_history(dashboard_id, limit)
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=404, detail=str(e))
_handle_unexpected_git_route_error("get_history", e)
# [/DEF:get_history:Function]
# [DEF:get_repository_status:Function]
# @PURPOSE: Get current Git status for a dashboard repository.
# @PRE: `dashboard_id` repository exists.
# @POST: Returns the status of the working directory (staged, unstaged, untracked).
# @PARAM: dashboard_id (int)
# @PRE: `dashboard_ref` resolves to a valid dashboard.
# @POST: Returns repository status; if repo is not initialized, returns `NO_REPO` payload.
# @PARAM: dashboard_ref (str)
# @RETURN: dict
@router.get("/repositories/{dashboard_id}/status")
@router.get("/repositories/{dashboard_ref}/status")
async def get_repository_status(
dashboard_id: int,
dashboard_ref: str,
env_id: Optional[str] = None,
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("get_repository_status"):
try:
return git_service.get_status(dashboard_id)
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
return _resolve_repository_status(dashboard_id)
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=400, detail=str(e))
_handle_unexpected_git_route_error("get_repository_status", e)
# [/DEF:get_repository_status:Function]
# [DEF:get_repository_status_batch:Function]
# @PURPOSE: Get Git statuses for multiple dashboard repositories in one request.
# @PRE: `request.dashboard_ids` is provided.
# @POST: Returns `statuses` map where each key is dashboard ID and value is repository status payload.
# @PARAM: request (RepoStatusBatchRequest)
# @RETURN: RepoStatusBatchResponse
@router.post("/repositories/status/batch", response_model=RepoStatusBatchResponse)
async def get_repository_status_batch(
request: RepoStatusBatchRequest,
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("get_repository_status_batch"):
dashboard_ids = list(dict.fromkeys(request.dashboard_ids))
if len(dashboard_ids) > MAX_REPOSITORY_STATUS_BATCH:
logger.warning(
"[get_repository_status_batch][Action] Batch size %s exceeds limit %s. Truncating request.",
len(dashboard_ids),
MAX_REPOSITORY_STATUS_BATCH,
)
dashboard_ids = dashboard_ids[:MAX_REPOSITORY_STATUS_BATCH]
statuses = {}
for dashboard_id in dashboard_ids:
try:
statuses[str(dashboard_id)] = _resolve_repository_status(dashboard_id)
except HTTPException:
statuses[str(dashboard_id)] = {
**_build_no_repo_status_payload(),
"sync_state": "ERROR",
"sync_status": "ERROR",
}
except Exception as e:
logger.error(
f"[get_repository_status_batch][Coherence:Failed] Failed for dashboard {dashboard_id}: {e}"
)
statuses[str(dashboard_id)] = {
**_build_no_repo_status_payload(),
"sync_state": "ERROR",
"sync_status": "ERROR",
}
return RepoStatusBatchResponse(statuses=statuses)
# [/DEF:get_repository_status_batch:Function]
# [DEF:get_repository_diff:Function]
# @PURPOSE: Get Git diff for a dashboard repository.
# @PRE: `dashboard_id` repository exists.
# @PRE: `dashboard_ref` repository exists.
# @POST: Returns the diff text for the specified file or all changes.
# @PARAM: dashboard_id (int)
# @PARAM: dashboard_ref (str)
# @PARAM: file_path (Optional[str])
# @PARAM: staged (bool)
# @RETURN: str
@router.get("/repositories/{dashboard_id}/diff")
@router.get("/repositories/{dashboard_ref}/diff")
async def get_repository_diff(
dashboard_id: int,
dashboard_ref: str,
file_path: Optional[str] = None,
staged: bool = False,
env_id: Optional[str] = None,
config_manager=Depends(get_config_manager),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("get_repository_diff"):
try:
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
diff_text = git_service.get_diff(dashboard_id, file_path, staged)
return diff_text
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=400, detail=str(e))
_handle_unexpected_git_route_error("get_repository_diff", e)
# [/DEF:get_repository_diff:Function]
# [DEF:generate_commit_message:Function]
# @PURPOSE: Generate a suggested commit message using LLM.
# @PRE: Repository for `dashboard_id` is initialized.
# @PRE: Repository for `dashboard_ref` is initialized.
# @POST: Returns a suggested commit message string.
@router.post("/repositories/{dashboard_id}/generate-message")
@router.post("/repositories/{dashboard_ref}/generate-message")
async def generate_commit_message(
dashboard_id: int,
db: Session = Depends(get_db),
dashboard_ref: str,
env_id: Optional[str] = None,
config_manager = Depends(get_config_manager),
db: Session = Depends(get_db),
_ = Depends(has_permission("plugin:git", "EXECUTE"))
):
with belief_scope("generate_commit_message"):
try:
dashboard_id = _resolve_dashboard_id_from_ref(dashboard_ref, config_manager, env_id)
# 1. Get Diff
diff = git_service.get_diff(dashboard_id, staged=True)
if not diff:
@@ -466,9 +999,10 @@ async def generate_commit_message(
)
return {"message": message}
except HTTPException:
raise
except Exception as e:
logger.error(f"Failed to generate commit message: {e}")
raise HTTPException(status_code=400, detail=str(e))
_handle_unexpected_git_route_error("generate_commit_message", e)
# [/DEF:generate_commit_message:Function]
# [/DEF:backend.src.api.routes.git:Module]

View File

@@ -9,7 +9,7 @@
# @INVARIANT: All schemas must be compatible with the FastAPI router.
from pydantic import BaseModel, Field
from typing import List, Optional
from typing import Any, Dict, List, Optional
from datetime import datetime
from src.models.git import GitProvider, GitStatus, SyncStatus
@@ -141,4 +141,93 @@ class RepoInitRequest(BaseModel):
remote_url: str
# [/DEF:RepoInitRequest:Class]
# [/DEF:backend.src.api.routes.git_schemas:Module]
# [DEF:RepoStatusBatchRequest:Class]
# @PURPOSE: Schema for requesting repository statuses for multiple dashboards in a single call.
class RepoStatusBatchRequest(BaseModel):
dashboard_ids: List[int] = Field(default_factory=list, description="Dashboard IDs to resolve repository statuses for")
# [/DEF:RepoStatusBatchRequest:Class]
# [DEF:RepoStatusBatchResponse:Class]
# @PURPOSE: Schema for returning repository statuses keyed by dashboard ID.
class RepoStatusBatchResponse(BaseModel):
statuses: Dict[str, Dict[str, Any]]
# [/DEF:RepoStatusBatchResponse:Class]
# [DEF:GiteaRepoSchema:Class]
# @PURPOSE: Schema describing a Gitea repository.
class GiteaRepoSchema(BaseModel):
name: str
full_name: str
private: bool = False
clone_url: Optional[str] = None
html_url: Optional[str] = None
ssh_url: Optional[str] = None
default_branch: Optional[str] = None
# [/DEF:GiteaRepoSchema:Class]
# [DEF:GiteaRepoCreateRequest:Class]
# @PURPOSE: Request schema for creating a Gitea repository.
class GiteaRepoCreateRequest(BaseModel):
name: str = Field(..., min_length=1, max_length=255)
private: bool = True
description: Optional[str] = None
auto_init: bool = True
default_branch: Optional[str] = "main"
# [/DEF:GiteaRepoCreateRequest:Class]
# [DEF:RemoteRepoSchema:Class]
# @PURPOSE: Provider-agnostic remote repository payload.
class RemoteRepoSchema(BaseModel):
provider: GitProvider
name: str
full_name: str
private: bool = False
clone_url: Optional[str] = None
html_url: Optional[str] = None
ssh_url: Optional[str] = None
default_branch: Optional[str] = None
# [/DEF:RemoteRepoSchema:Class]
# [DEF:RemoteRepoCreateRequest:Class]
# @PURPOSE: Provider-agnostic repository creation request.
class RemoteRepoCreateRequest(BaseModel):
name: str = Field(..., min_length=1, max_length=255)
private: bool = True
description: Optional[str] = None
auto_init: bool = True
default_branch: Optional[str] = "main"
# [/DEF:RemoteRepoCreateRequest:Class]
# [DEF:PromoteRequest:Class]
# @PURPOSE: Request schema for branch promotion workflow.
class PromoteRequest(BaseModel):
from_branch: str = Field(..., min_length=1, max_length=255)
to_branch: str = Field(..., min_length=1, max_length=255)
mode: str = Field(default="mr", pattern="^(mr|direct)$")
title: Optional[str] = None
description: Optional[str] = None
reason: Optional[str] = None
draft: bool = False
remove_source_branch: bool = False
# [/DEF:PromoteRequest:Class]
# [DEF:PromoteResponse:Class]
# @PURPOSE: Response schema for promotion operation result.
class PromoteResponse(BaseModel):
mode: str
from_branch: str
to_branch: str
status: str
url: Optional[str] = None
reference_id: Optional[str] = None
policy_violation: bool = False
# [/DEF:PromoteResponse:Class]
# [/DEF:backend.src.api.routes.git_schemas:Module]

View File

@@ -14,6 +14,7 @@ from ...core.database import get_db
from ...models.dashboard import DashboardMetadata, DashboardSelection
from ...core.superset_client import SupersetClient
from ...core.logger import belief_scope
from ...core.migration.dry_run_orchestrator import MigrationDryRunService
from ...core.mapping_service import IdMappingService
from ...models.mapping import ResourceMapping
@@ -83,6 +84,44 @@ async def execute_migration(
raise HTTPException(status_code=500, detail=f"Failed to create migration task: {str(e)}")
# [/DEF:execute_migration:Function]
# [DEF:dry_run_migration:Function]
# @PURPOSE: Build pre-flight diff and risk summary without applying migration.
# @PRE: Selection and environments are valid.
# @POST: Returns deterministic JSON diff and risk scoring.
@router.post("/migration/dry-run", response_model=Dict[str, Any])
async def dry_run_migration(
selection: DashboardSelection,
config_manager=Depends(get_config_manager),
db: Session = Depends(get_db),
_ = Depends(has_permission("plugin:migration", "EXECUTE"))
):
with belief_scope("dry_run_migration"):
environments = config_manager.get_environments()
env_map = {env.id: env for env in environments}
source_env = env_map.get(selection.source_env_id)
target_env = env_map.get(selection.target_env_id)
if not source_env or not target_env:
raise HTTPException(status_code=400, detail="Invalid source or target environment")
if selection.source_env_id == selection.target_env_id:
raise HTTPException(status_code=400, detail="Source and target environments must be different")
if not selection.selected_ids:
raise HTTPException(status_code=400, detail="No dashboards selected for dry run")
service = MigrationDryRunService()
source_client = SupersetClient(source_env)
target_client = SupersetClient(target_env)
try:
return service.run(
selection=selection,
source_client=source_client,
target_client=target_client,
db=db,
)
except ValueError as exc:
raise HTTPException(status_code=500, detail=str(exc)) from exc
# [/DEF:dry_run_migration:Function]
# [DEF:get_migration_settings:Function]
# @PURPOSE: Get current migration Cron string explicitly.
@router.get("/migration/settings", response_model=Dict[str, str])
@@ -221,4 +260,4 @@ async def trigger_sync_now(
}
# [/DEF:trigger_sync_now:Function]
# [/DEF:backend.src.api.routes.migration:Module]
# [/DEF:backend.src.api.routes.migration:Module]

View File

@@ -62,6 +62,20 @@ def _parse_csv_enum_list(raw: Optional[str], enum_cls, field_name: str) -> List:
# @PRE: authenticated/authorized request and validated query params.
# @POST: returns {items,total,page,page_size,has_next,applied_filters}.
# @POST: deterministic error payload for invalid filters.
#
# @TEST_CONTRACT: ListReportsApi ->
# {
# required_fields: {page: int, page_size: int, sort_by: str, sort_order: str},
# optional_fields: {task_types: str, statuses: str, search: str},
# invariants: [
# "Returns ReportCollection on success",
# "Raises HTTPException 400 for invalid query parameters"
# ]
# }
# @TEST_FIXTURE: valid_list_request -> {"page": 1, "page_size": 20}
# @TEST_EDGE: invalid_task_type_filter -> raises HTTPException(400)
# @TEST_EDGE: malformed_query -> raises HTTPException(400)
# @TEST_INVARIANT: consistent_list_payload -> verifies: [valid_list_request]
@router.get("", response_model=ReportCollection)
async def list_reports(
page: int = Query(1, ge=1),

View File

@@ -31,7 +31,38 @@ class LoggingConfigResponse(BaseModel):
enable_belief_state: bool
# [/DEF:LoggingConfigResponse:Class]
router = APIRouter()
router = APIRouter()
# [DEF:_normalize_superset_env_url:Function]
# @PURPOSE: Canonicalize Superset environment URL to base host/path without trailing /api/v1.
# @PRE: raw_url can be empty.
# @POST: Returns normalized base URL.
def _normalize_superset_env_url(raw_url: str) -> str:
normalized = str(raw_url or "").strip().rstrip("/")
if normalized.lower().endswith("/api/v1"):
normalized = normalized[:-len("/api/v1")]
return normalized.rstrip("/")
# [/DEF:_normalize_superset_env_url:Function]
# [DEF:_validate_superset_connection_fast:Function]
# @PURPOSE: Run lightweight Superset connectivity validation without full pagination scan.
# @PRE: env contains valid URL and credentials.
# @POST: Raises on auth/API failures; returns None on success.
def _validate_superset_connection_fast(env: Environment) -> None:
client = SupersetClient(env)
# 1) Explicit auth check
client.authenticate()
# 2) Single lightweight API call to ensure read access
client.get_dashboards_page(
query={
"page": 0,
"page_size": 1,
"columns": ["id"],
}
)
# [/DEF:_validate_superset_connection_fast:Function]
# [DEF:get_settings:Function]
# @PURPOSE: Retrieves all application settings.
@@ -112,14 +143,18 @@ async def update_storage_settings(
# @PRE: Config manager is available.
# @POST: Returns list of environments.
# @RETURN: List[Environment] - List of environments.
@router.get("/environments", response_model=List[Environment])
async def get_environments(
@router.get("/environments", response_model=List[Environment])
async def get_environments(
config_manager: ConfigManager = Depends(get_config_manager),
_ = Depends(has_permission("admin:settings", "READ"))
):
with belief_scope("get_environments"):
logger.info("[get_environments][Entry] Fetching environments")
return config_manager.get_environments()
):
with belief_scope("get_environments"):
logger.info("[get_environments][Entry] Fetching environments")
environments = config_manager.get_environments()
return [
env.copy(update={"url": _normalize_superset_env_url(env.url)})
for env in environments
]
# [/DEF:get_environments:Function]
# [DEF:add_environment:Function]
@@ -129,21 +164,21 @@ async def get_environments(
# @PARAM: env (Environment) - The environment to add.
# @RETURN: Environment - The added environment.
@router.post("/environments", response_model=Environment)
async def add_environment(
env: Environment,
async def add_environment(
env: Environment,
config_manager: ConfigManager = Depends(get_config_manager),
_ = Depends(has_permission("admin:settings", "WRITE"))
):
with belief_scope("add_environment"):
logger.info(f"[add_environment][Entry] Adding environment {env.id}")
):
with belief_scope("add_environment"):
logger.info(f"[add_environment][Entry] Adding environment {env.id}")
env = env.copy(update={"url": _normalize_superset_env_url(env.url)})
# Validate connection before adding
try:
client = SupersetClient(env)
client.get_dashboards(query={"page_size": 1})
except Exception as e:
logger.error(f"[add_environment][Coherence:Failed] Connection validation failed: {e}")
raise HTTPException(status_code=400, detail=f"Connection validation failed: {e}")
# Validate connection before adding (fast path)
try:
_validate_superset_connection_fast(env)
except Exception as e:
logger.error(f"[add_environment][Coherence:Failed] Connection validation failed: {e}")
raise HTTPException(status_code=400, detail=f"Connection validation failed: {e}")
config_manager.add_environment(env)
return env
@@ -157,28 +192,29 @@ async def add_environment(
# @PARAM: env (Environment) - The updated environment data.
# @RETURN: Environment - The updated environment.
@router.put("/environments/{id}", response_model=Environment)
async def update_environment(
async def update_environment(
id: str,
env: Environment,
config_manager: ConfigManager = Depends(get_config_manager)
):
):
with belief_scope("update_environment"):
logger.info(f"[update_environment][Entry] Updating environment {id}")
# If password is masked, we need the real one for validation
env_to_validate = env.copy(deep=True)
env = env.copy(update={"url": _normalize_superset_env_url(env.url)})
# If password is masked, we need the real one for validation
env_to_validate = env.copy(deep=True)
if env_to_validate.password == "********":
old_env = next((e for e in config_manager.get_environments() if e.id == id), None)
if old_env:
env_to_validate.password = old_env.password
# Validate connection before updating
try:
client = SupersetClient(env_to_validate)
client.get_dashboards(query={"page_size": 1})
except Exception as e:
logger.error(f"[update_environment][Coherence:Failed] Connection validation failed: {e}")
raise HTTPException(status_code=400, detail=f"Connection validation failed: {e}")
# Validate connection before updating (fast path)
try:
_validate_superset_connection_fast(env_to_validate)
except Exception as e:
logger.error(f"[update_environment][Coherence:Failed] Connection validation failed: {e}")
raise HTTPException(status_code=400, detail=f"Connection validation failed: {e}")
if config_manager.update_environment(id, env):
return env
@@ -208,7 +244,7 @@ async def delete_environment(
# @PARAM: id (str) - The ID of the environment to test.
# @RETURN: dict - Success message or error.
@router.post("/environments/{id}/test")
async def test_environment_connection(
async def test_environment_connection(
id: str,
config_manager: ConfigManager = Depends(get_config_manager)
):
@@ -220,15 +256,11 @@ async def test_environment_connection(
if not env:
raise HTTPException(status_code=404, detail=f"Environment {id} not found")
try:
# Initialize client (this will trigger authentication)
client = SupersetClient(env)
# Try a simple request to verify
client.get_dashboards(query={"page_size": 1})
logger.info(f"[test_environment_connection][Coherence:OK] Connection successful for {id}")
return {"status": "success", "message": "Connection successful"}
try:
_validate_superset_connection_fast(env)
logger.info(f"[test_environment_connection][Coherence:OK] Connection successful for {id}")
return {"status": "success", "message": "Connection successful"}
except Exception as e:
logger.error(f"[test_environment_connection][Coherence:Failed] Connection failed for {id}: {e}")
return {"status": "error", "message": str(e)}

View File

@@ -21,7 +21,7 @@ import asyncio
from .dependencies import get_task_manager, get_scheduler_service
from .core.utils.network import NetworkError
from .core.logger import logger, belief_scope
from .api.routes import plugins, tasks, settings, environments, mappings, migration, connections, git, storage, admin, llm, dashboards, datasets, reports, assistant
from .api.routes import plugins, tasks, settings, environments, mappings, migration, connections, git, storage, admin, llm, dashboards, datasets, reports, assistant, clean_release
from .api import auth
# [DEF:App:Global]
@@ -133,6 +133,7 @@ app.include_router(dashboards.router)
app.include_router(datasets.router)
app.include_router(reports.router)
app.include_router(assistant.router, prefix="/api/assistant", tags=["Assistant"])
app.include_router(clean_release.router)
# [DEF:api.include_routers:Action]
@@ -147,6 +148,21 @@ app.include_router(assistant.router, prefix="/api/assistant", tags=["Assistant"]
# @POST: WebSocket connection is managed and logs are streamed until disconnect.
# @TIER: CRITICAL
# @UX_STATE: Connecting -> Streaming -> (Disconnected)
#
# @TEST_CONTRACT: WebSocketLogStreamApi ->
# {
# required_fields: {websocket: WebSocket, task_id: str},
# optional_fields: {source: str, level: str},
# invariants: [
# "Accepts the WebSocket connection",
# "Applies source and level filters correctly to streamed logs",
# "Cleans up subscriptions on disconnect"
# ]
# }
# @TEST_FIXTURE: valid_ws_connection -> {"task_id": "test_1", "source": "plugin"}
# @TEST_EDGE: task_not_found_ws -> closes connection or sends error
# @TEST_EDGE: empty_task_logs -> waits for new logs
# @TEST_INVARIANT: consistent_streaming -> verifies: [valid_ws_connection]
@app.websocket("/ws/logs/{task_id}")
async def websocket_endpoint(
websocket: WebSocket,

View File

@@ -14,6 +14,8 @@ import pytest
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
from src.core.database import Base
# Import all models to ensure they are registered with Base before create_all - must import both auth and mapping to ensure Base knows about all tables
from src.models import mapping, auth, task, report
from src.models.auth import User, Role, Permission, ADGroupMapping
from src.services.auth_service import AuthService
from src.core.auth.repository import AuthRepository
@@ -176,4 +178,94 @@ def test_ad_group_mapping(auth_repo):
assert retrieved_mapping.role_id == role.id
def test_authenticate_user_updates_last_login(auth_service, auth_repo):
"""@SIDE_EFFECT: authenticate_user updates last_login timestamp on success."""
user = User(
username="loginuser",
email="login@example.com",
password_hash=get_password_hash("mypassword"),
auth_source="LOCAL"
)
auth_repo.db.add(user)
auth_repo.db.commit()
assert user.last_login is None
authenticated = auth_service.authenticate_user("loginuser", "mypassword")
assert authenticated is not None
assert authenticated.last_login is not None
def test_authenticate_inactive_user(auth_service, auth_repo):
"""@PRE: User with is_active=False should not authenticate."""
user = User(
username="inactive_user",
email="inactive@example.com",
password_hash=get_password_hash("testpass"),
auth_source="LOCAL",
is_active=False
)
auth_repo.db.add(user)
auth_repo.db.commit()
result = auth_service.authenticate_user("inactive_user", "testpass")
assert result is None
def test_verify_password_empty_hash():
"""@PRE: verify_password with empty/None hash returns False."""
assert verify_password("anypassword", "") is False
assert verify_password("anypassword", None) is False
def test_provision_adfs_user_new(auth_service, auth_repo):
"""@POST: provision_adfs_user creates a new ADFS user with correct roles."""
# Set up a role and AD group mapping
role = Role(name="ADFS_Viewer", description="ADFS viewer role")
auth_repo.db.add(role)
auth_repo.db.commit()
mapping = ADGroupMapping(ad_group="DOMAIN\\Viewers", role_id=role.id)
auth_repo.db.add(mapping)
auth_repo.db.commit()
user_info = {
"upn": "newadfsuser@domain.com",
"email": "newadfsuser@domain.com",
"groups": ["DOMAIN\\Viewers"]
}
user = auth_service.provision_adfs_user(user_info)
assert user is not None
assert user.username == "newadfsuser@domain.com"
assert user.auth_source == "ADFS"
assert user.is_active is True
assert len(user.roles) == 1
assert user.roles[0].name == "ADFS_Viewer"
def test_provision_adfs_user_existing(auth_service, auth_repo):
"""@POST: provision_adfs_user updates roles for existing user."""
# Create existing user
existing = User(
username="existingadfs@domain.com",
email="existingadfs@domain.com",
auth_source="ADFS",
is_active=True
)
auth_repo.db.add(existing)
auth_repo.db.commit()
user_info = {
"upn": "existingadfs@domain.com",
"email": "existingadfs@domain.com",
"groups": []
}
user = auth_service.provision_adfs_user(user_info)
assert user is not None
assert user.username == "existingadfs@domain.com"
assert len(user.roles) == 0 # No matching group mappings
# [/DEF:test_auth:Module]

View File

@@ -30,6 +30,7 @@ class Environment(BaseModel):
url: str
username: str
password: str # Will be masked in UI
stage: str = Field(default="DEV", pattern="^(DEV|PREPROD|PROD)$")
verify_ssl: bool = True
timeout: int = 30
is_default: bool = False

View File

@@ -23,6 +23,21 @@ from src.core.logger import logger, belief_scope
# [DEF:IdMappingService:Class]
# @TIER: CRITICAL
# @PURPOSE: Service handling the cataloging and retrieval of remote Superset Integer IDs.
#
# @TEST_CONTRACT: IdMappingServiceModel ->
# {
# required_fields: {db_session: Session},
# invariants: [
# "sync_environment correctly creates or updates ResourceMapping records",
# "get_remote_id returns an integer or None",
# "get_remote_ids_batch returns a dictionary of valid UUIDs to integers"
# ]
# }
# @TEST_FIXTURE: valid_mapping_service -> {"db_session": "MockSession()"}
# @TEST_EDGE: sync_api_failure -> handles exception gracefully
# @TEST_EDGE: get_remote_id_not_found -> returns None
# @TEST_EDGE: get_batch_empty_list -> returns empty dict
# @TEST_INVARIANT: resilient_fetching -> verifies: [sync_api_failure]
class IdMappingService:
# [DEF:__init__:Function]

View File

@@ -0,0 +1,12 @@
# [DEF:backend.src.core.migration.__init__:Module]
# @TIER: TRIVIAL
# @SEMANTICS: migration, package, exports
# @PURPOSE: Namespace package for migration pre-flight orchestration components.
# @LAYER: Core
from .dry_run_orchestrator import MigrationDryRunService
from .archive_parser import MigrationArchiveParser
__all__ = ["MigrationDryRunService", "MigrationArchiveParser"]
# [/DEF:backend.src.core.migration.__init__:Module]

View File

@@ -0,0 +1,139 @@
# [DEF:backend.src.core.migration.archive_parser:Module]
# @TIER: STANDARD
# @SEMANTICS: migration, zip, parser, yaml, metadata
# @PURPOSE: Parse Superset export ZIP archives into normalized object catalogs for diffing.
# @LAYER: Core
# @RELATION: DEPENDS_ON -> backend.src.core.logger
# @INVARIANT: Parsing is read-only and never mutates archive files.
import json
import tempfile
import zipfile
from pathlib import Path
from typing import Any, Dict, List, Optional
import yaml
from ..logger import logger, belief_scope
# [DEF:MigrationArchiveParser:Class]
# @PURPOSE: Extract normalized dashboards/charts/datasets metadata from ZIP archives.
class MigrationArchiveParser:
# [DEF:extract_objects_from_zip:Function]
# @PURPOSE: Extract object catalogs from Superset archive.
# @PRE: zip_path points to a valid readable ZIP.
# @POST: Returns object lists grouped by resource type.
# @RETURN: Dict[str, List[Dict[str, Any]]]
def extract_objects_from_zip(self, zip_path: str) -> Dict[str, List[Dict[str, Any]]]:
with belief_scope("MigrationArchiveParser.extract_objects_from_zip"):
result: Dict[str, List[Dict[str, Any]]] = {
"dashboards": [],
"charts": [],
"datasets": [],
}
with tempfile.TemporaryDirectory() as temp_dir_str:
temp_dir = Path(temp_dir_str)
with zipfile.ZipFile(zip_path, "r") as zip_file:
zip_file.extractall(temp_dir)
result["dashboards"] = self._collect_yaml_objects(temp_dir, "dashboards")
result["charts"] = self._collect_yaml_objects(temp_dir, "charts")
result["datasets"] = self._collect_yaml_objects(temp_dir, "datasets")
return result
# [/DEF:extract_objects_from_zip:Function]
# [DEF:_collect_yaml_objects:Function]
# @PURPOSE: Read and normalize YAML manifests for one object type.
# @PRE: object_type is one of dashboards/charts/datasets.
# @POST: Returns only valid normalized objects.
def _collect_yaml_objects(self, root_dir: Path, object_type: str) -> List[Dict[str, Any]]:
with belief_scope("MigrationArchiveParser._collect_yaml_objects"):
files = list(root_dir.glob(f"**/{object_type}/**/*.yaml")) + list(root_dir.glob(f"**/{object_type}/*.yaml"))
objects: List[Dict[str, Any]] = []
for file_path in set(files):
try:
with open(file_path, "r") as file_obj:
payload = yaml.safe_load(file_obj) or {}
normalized = self._normalize_object_payload(payload, object_type)
if normalized:
objects.append(normalized)
except Exception as exc:
logger.reflect(
"[MigrationArchiveParser._collect_yaml_objects][REFLECT] skip_invalid_yaml path=%s error=%s",
file_path,
exc,
)
return objects
# [/DEF:_collect_yaml_objects:Function]
# [DEF:_normalize_object_payload:Function]
# @PURPOSE: Convert raw YAML payload to stable diff signature shape.
# @PRE: payload is parsed YAML mapping.
# @POST: Returns normalized descriptor with `uuid`, `title`, and `signature`.
def _normalize_object_payload(self, payload: Dict[str, Any], object_type: str) -> Optional[Dict[str, Any]]:
with belief_scope("MigrationArchiveParser._normalize_object_payload"):
if not isinstance(payload, dict):
return None
uuid = payload.get("uuid")
if not uuid:
return None
if object_type == "dashboards":
title = payload.get("dashboard_title") or payload.get("title")
signature = {
"title": title,
"slug": payload.get("slug"),
"position_json": payload.get("position_json"),
"json_metadata": payload.get("json_metadata"),
"description": payload.get("description"),
"owners": payload.get("owners"),
}
return {
"uuid": str(uuid),
"title": title or f"Dashboard {uuid}",
"signature": json.dumps(signature, sort_keys=True, default=str),
"owners": payload.get("owners") or [],
}
if object_type == "charts":
title = payload.get("slice_name") or payload.get("name")
signature = {
"title": title,
"viz_type": payload.get("viz_type"),
"params": payload.get("params"),
"query_context": payload.get("query_context"),
"datasource_uuid": payload.get("datasource_uuid"),
"dataset_uuid": payload.get("dataset_uuid"),
}
return {
"uuid": str(uuid),
"title": title or f"Chart {uuid}",
"signature": json.dumps(signature, sort_keys=True, default=str),
"dataset_uuid": payload.get("datasource_uuid") or payload.get("dataset_uuid"),
}
if object_type == "datasets":
title = payload.get("table_name") or payload.get("name")
signature = {
"title": title,
"schema": payload.get("schema"),
"database_uuid": payload.get("database_uuid"),
"sql": payload.get("sql"),
"columns": payload.get("columns"),
"metrics": payload.get("metrics"),
}
return {
"uuid": str(uuid),
"title": title or f"Dataset {uuid}",
"signature": json.dumps(signature, sort_keys=True, default=str),
"database_uuid": payload.get("database_uuid"),
}
return None
# [/DEF:_normalize_object_payload:Function]
# [/DEF:MigrationArchiveParser:Class]
# [/DEF:backend.src.core.migration.archive_parser:Module]

View File

@@ -0,0 +1,235 @@
# [DEF:backend.src.core.migration.dry_run_orchestrator:Module]
# @TIER: STANDARD
# @SEMANTICS: migration, dry_run, diff, risk, superset
# @PURPOSE: Compute pre-flight migration diff and risk scoring without apply.
# @LAYER: Core
# @RELATION: DEPENDS_ON -> backend.src.core.superset_client
# @RELATION: DEPENDS_ON -> backend.src.core.migration_engine
# @RELATION: DEPENDS_ON -> backend.src.core.migration.archive_parser
# @RELATION: DEPENDS_ON -> backend.src.core.migration.risk_assessor
# @INVARIANT: Dry run is informative only and must not mutate target environment.
from datetime import datetime, timezone
import json
from typing import Any, Dict, List
from sqlalchemy.orm import Session
from ...models.dashboard import DashboardSelection
from ...models.mapping import DatabaseMapping
from ..logger import logger, belief_scope
from .archive_parser import MigrationArchiveParser
from .risk_assessor import build_risks, score_risks
from ..migration_engine import MigrationEngine
from ..superset_client import SupersetClient
from ..utils.fileio import create_temp_file
# [DEF:MigrationDryRunService:Class]
# @PURPOSE: Build deterministic diff/risk payload for migration pre-flight.
class MigrationDryRunService:
# [DEF:__init__:Function]
# @PURPOSE: Wire parser dependency for archive object extraction.
# @PRE: parser can be omitted to use default implementation.
# @POST: Service is ready to calculate dry-run payload.
def __init__(self, parser: MigrationArchiveParser | None = None):
self.parser = parser or MigrationArchiveParser()
# [/DEF:__init__:Function]
# [DEF:run:Function]
# @PURPOSE: Execute full dry-run computation for selected dashboards.
# @PRE: source/target clients are authenticated and selection validated by caller.
# @POST: Returns JSON-serializable pre-flight payload with summary, diff and risk.
# @SIDE_EFFECT: Reads source export archives and target metadata via network.
def run(
self,
selection: DashboardSelection,
source_client: SupersetClient,
target_client: SupersetClient,
db: Session,
) -> Dict[str, Any]:
with belief_scope("MigrationDryRunService.run"):
logger.explore("[MigrationDryRunService.run][EXPLORE] starting dry-run pipeline")
engine = MigrationEngine()
db_mapping = self._load_db_mapping(db, selection) if selection.replace_db_config else {}
transformed = {"dashboards": {}, "charts": {}, "datasets": {}}
dashboards_preview = source_client.get_dashboards_summary()
selected_preview = {
item["id"]: item
for item in dashboards_preview
if item.get("id") in selection.selected_ids
}
for dashboard_id in selection.selected_ids:
exported_content, _ = source_client.export_dashboard(int(dashboard_id))
with create_temp_file(content=exported_content, suffix=".zip") as source_zip:
with create_temp_file(suffix=".zip") as transformed_zip:
success = engine.transform_zip(
str(source_zip),
str(transformed_zip),
db_mapping,
strip_databases=False,
target_env_id=selection.target_env_id,
fix_cross_filters=selection.fix_cross_filters,
)
if not success:
raise ValueError(f"Failed to transform export archive for dashboard {dashboard_id}")
extracted = self.parser.extract_objects_from_zip(str(transformed_zip))
self._accumulate_objects(transformed, extracted)
source_objects = {key: list(value.values()) for key, value in transformed.items()}
target_objects = self._build_target_signatures(target_client)
diff = {
"dashboards": self._build_object_diff(source_objects["dashboards"], target_objects["dashboards"]),
"charts": self._build_object_diff(source_objects["charts"], target_objects["charts"]),
"datasets": self._build_object_diff(source_objects["datasets"], target_objects["datasets"]),
}
risk = self._build_risks(source_objects, target_objects, diff, target_client)
summary = {
"dashboards": {action: len(diff["dashboards"][action]) for action in ("create", "update", "delete")},
"charts": {action: len(diff["charts"][action]) for action in ("create", "update", "delete")},
"datasets": {action: len(diff["datasets"][action]) for action in ("create", "update", "delete")},
"selected_dashboards": len(selection.selected_ids),
}
selected_titles = [
selected_preview[dash_id]["title"]
for dash_id in selection.selected_ids
if dash_id in selected_preview
]
logger.reason("[MigrationDryRunService.run][REASON] dry-run payload assembled")
return {
"generated_at": datetime.now(timezone.utc).isoformat(),
"selection": selection.model_dump(),
"selected_dashboard_titles": selected_titles,
"diff": diff,
"summary": summary,
"risk": score_risks(risk),
}
# [/DEF:run:Function]
# [DEF:_load_db_mapping:Function]
# @PURPOSE: Resolve UUID mapping for optional DB config replacement.
def _load_db_mapping(self, db: Session, selection: DashboardSelection) -> Dict[str, str]:
rows = db.query(DatabaseMapping).filter(
DatabaseMapping.source_env_id == selection.source_env_id,
DatabaseMapping.target_env_id == selection.target_env_id,
).all()
return {row.source_db_uuid: row.target_db_uuid for row in rows}
# [/DEF:_load_db_mapping:Function]
# [DEF:_accumulate_objects:Function]
# @PURPOSE: Merge extracted resources by UUID to avoid duplicates.
def _accumulate_objects(self, target: Dict[str, Dict[str, Dict[str, Any]]], source: Dict[str, List[Dict[str, Any]]]) -> None:
for object_type in ("dashboards", "charts", "datasets"):
for item in source.get(object_type, []):
uuid = item.get("uuid")
if uuid:
target[object_type][str(uuid)] = item
# [/DEF:_accumulate_objects:Function]
# [DEF:_index_by_uuid:Function]
# @PURPOSE: Build UUID-index map for normalized resources.
def _index_by_uuid(self, objects: List[Dict[str, Any]]) -> Dict[str, Dict[str, Any]]:
indexed: Dict[str, Dict[str, Any]] = {}
for obj in objects:
uuid = obj.get("uuid")
if uuid:
indexed[str(uuid)] = obj
return indexed
# [/DEF:_index_by_uuid:Function]
# [DEF:_build_object_diff:Function]
# @PURPOSE: Compute create/update/delete buckets by UUID+signature.
def _build_object_diff(self, source_objects: List[Dict[str, Any]], target_objects: List[Dict[str, Any]]) -> Dict[str, List[Dict[str, Any]]]:
target_index = self._index_by_uuid(target_objects)
created: List[Dict[str, Any]] = []
updated: List[Dict[str, Any]] = []
deleted: List[Dict[str, Any]] = []
for source_obj in source_objects:
source_uuid = str(source_obj.get("uuid"))
target_obj = target_index.get(source_uuid)
if not target_obj:
created.append({"uuid": source_uuid, "title": source_obj.get("title")})
continue
if source_obj.get("signature") != target_obj.get("signature"):
updated.append({
"uuid": source_uuid,
"title": source_obj.get("title"),
"target_title": target_obj.get("title"),
})
return {"create": created, "update": updated, "delete": deleted}
# [/DEF:_build_object_diff:Function]
# [DEF:_build_target_signatures:Function]
# @PURPOSE: Pull target metadata and normalize it into comparable signatures.
def _build_target_signatures(self, client: SupersetClient) -> Dict[str, List[Dict[str, Any]]]:
_, dashboards = client.get_dashboards(query={
"columns": ["uuid", "dashboard_title", "slug", "position_json", "json_metadata", "description", "owners"],
})
_, datasets = client.get_datasets(query={
"columns": ["uuid", "table_name", "schema", "database_uuid", "sql", "columns", "metrics"],
})
_, charts = client.get_charts(query={
"columns": ["uuid", "slice_name", "viz_type", "params", "query_context", "datasource_uuid", "dataset_uuid"],
})
return {
"dashboards": [{
"uuid": str(item.get("uuid")),
"title": item.get("dashboard_title"),
"owners": item.get("owners") or [],
"signature": json.dumps({
"title": item.get("dashboard_title"),
"slug": item.get("slug"),
"position_json": item.get("position_json"),
"json_metadata": item.get("json_metadata"),
"description": item.get("description"),
"owners": item.get("owners"),
}, sort_keys=True, default=str),
} for item in dashboards if item.get("uuid")],
"datasets": [{
"uuid": str(item.get("uuid")),
"title": item.get("table_name"),
"database_uuid": item.get("database_uuid"),
"signature": json.dumps({
"title": item.get("table_name"),
"schema": item.get("schema"),
"database_uuid": item.get("database_uuid"),
"sql": item.get("sql"),
"columns": item.get("columns"),
"metrics": item.get("metrics"),
}, sort_keys=True, default=str),
} for item in datasets if item.get("uuid")],
"charts": [{
"uuid": str(item.get("uuid")),
"title": item.get("slice_name") or item.get("name"),
"dataset_uuid": item.get("datasource_uuid") or item.get("dataset_uuid"),
"signature": json.dumps({
"title": item.get("slice_name") or item.get("name"),
"viz_type": item.get("viz_type"),
"params": item.get("params"),
"query_context": item.get("query_context"),
"datasource_uuid": item.get("datasource_uuid"),
"dataset_uuid": item.get("dataset_uuid"),
}, sort_keys=True, default=str),
} for item in charts if item.get("uuid")],
}
# [/DEF:_build_target_signatures:Function]
# [DEF:_build_risks:Function]
# @PURPOSE: Build risk items for missing datasource, broken refs, overwrite, owner mismatch.
def _build_risks(
self,
source_objects: Dict[str, List[Dict[str, Any]]],
target_objects: Dict[str, List[Dict[str, Any]]],
diff: Dict[str, Dict[str, List[Dict[str, Any]]]],
target_client: SupersetClient,
) -> List[Dict[str, Any]]:
return build_risks(source_objects, target_objects, diff, target_client)
# [/DEF:_build_risks:Function]
# [/DEF:MigrationDryRunService:Class]
# [/DEF:backend.src.core.migration.dry_run_orchestrator:Module]

View File

@@ -0,0 +1,119 @@
# [DEF:backend.src.core.migration.risk_assessor:Module]
# @TIER: STANDARD
# @SEMANTICS: migration, dry_run, risk, scoring
# @PURPOSE: Risk evaluation helpers for migration pre-flight reporting.
# @LAYER: Core
# @RELATION: USED_BY -> backend.src.core.migration.dry_run_orchestrator
from typing import Any, Dict, List
from ..superset_client import SupersetClient
# [DEF:index_by_uuid:Function]
# @PURPOSE: Build UUID-index from normalized objects.
def index_by_uuid(objects: List[Dict[str, Any]]) -> Dict[str, Dict[str, Any]]:
indexed: Dict[str, Dict[str, Any]] = {}
for obj in objects:
uuid = obj.get("uuid")
if uuid:
indexed[str(uuid)] = obj
return indexed
# [/DEF:index_by_uuid:Function]
# [DEF:extract_owner_identifiers:Function]
# @PURPOSE: Normalize owner payloads for stable comparison.
def extract_owner_identifiers(owners: Any) -> List[str]:
if not isinstance(owners, list):
return []
ids: List[str] = []
for owner in owners:
if isinstance(owner, dict):
if owner.get("username"):
ids.append(str(owner["username"]))
elif owner.get("id") is not None:
ids.append(str(owner["id"]))
elif owner is not None:
ids.append(str(owner))
return sorted(set(ids))
# [/DEF:extract_owner_identifiers:Function]
# [DEF:build_risks:Function]
# @PURPOSE: Build risk list from computed diffs and target catalog state.
def build_risks(
source_objects: Dict[str, List[Dict[str, Any]]],
target_objects: Dict[str, List[Dict[str, Any]]],
diff: Dict[str, Dict[str, List[Dict[str, Any]]]],
target_client: SupersetClient,
) -> List[Dict[str, Any]]:
risks: List[Dict[str, Any]] = []
for object_type in ("dashboards", "charts", "datasets"):
for item in diff[object_type]["update"]:
risks.append({
"code": "overwrite_existing",
"severity": "medium",
"object_type": object_type[:-1],
"object_uuid": item["uuid"],
"message": f"Object will be updated in target: {item.get('title') or item['uuid']}",
})
target_dataset_uuids = set(index_by_uuid(target_objects["datasets"]).keys())
_, target_databases = target_client.get_databases(query={"columns": ["uuid"]})
target_database_uuids = {str(item.get("uuid")) for item in target_databases if item.get("uuid")}
for dataset in source_objects["datasets"]:
db_uuid = dataset.get("database_uuid")
if db_uuid and str(db_uuid) not in target_database_uuids:
risks.append({
"code": "missing_datasource",
"severity": "high",
"object_type": "dataset",
"object_uuid": dataset.get("uuid"),
"message": f"Target datasource is missing for dataset {dataset.get('title') or dataset.get('uuid')}",
})
for chart in source_objects["charts"]:
ds_uuid = chart.get("dataset_uuid")
if ds_uuid and str(ds_uuid) not in target_dataset_uuids:
risks.append({
"code": "breaking_reference",
"severity": "high",
"object_type": "chart",
"object_uuid": chart.get("uuid"),
"message": f"Chart references dataset not found on target: {ds_uuid}",
})
source_dash = index_by_uuid(source_objects["dashboards"])
target_dash = index_by_uuid(target_objects["dashboards"])
for item in diff["dashboards"]["update"]:
source_obj = source_dash.get(item["uuid"])
target_obj = target_dash.get(item["uuid"])
if not source_obj or not target_obj:
continue
source_owners = extract_owner_identifiers(source_obj.get("owners"))
target_owners = extract_owner_identifiers(target_obj.get("owners"))
if source_owners and target_owners and source_owners != target_owners:
risks.append({
"code": "owner_mismatch",
"severity": "low",
"object_type": "dashboard",
"object_uuid": item["uuid"],
"message": f"Owner mismatch for dashboard {item.get('title') or item['uuid']}",
})
return risks
# [/DEF:build_risks:Function]
# [DEF:score_risks:Function]
# @PURPOSE: Aggregate risk list into score and level.
def score_risks(risk_items: List[Dict[str, Any]]) -> Dict[str, Any]:
weights = {"high": 25, "medium": 10, "low": 5}
score = min(100, sum(weights.get(item.get("severity", "low"), 5) for item in risk_items))
level = "low" if score < 25 else "medium" if score < 60 else "high"
return {"score": score, "level": level, "items": risk_items}
# [/DEF:score_risks:Function]
# [/DEF:backend.src.core.migration.risk_assessor:Module]

View File

@@ -14,7 +14,7 @@ import json
import re
import zipfile
from pathlib import Path
from typing import Dict, List, Optional, Tuple, Union, cast
from typing import Any, Dict, List, Optional, Tuple, Union, cast
from requests import Response
from datetime import datetime
from .logger import logger as app_logger, belief_scope
@@ -87,7 +87,18 @@ class SupersetClient:
app_logger.info("[get_dashboards][Enter] Fetching dashboards.")
validated_query = self._validate_query_params(query or {})
if 'columns' not in validated_query:
validated_query['columns'] = ["slug", "id", "changed_on_utc", "dashboard_title", "published"]
validated_query['columns'] = [
"slug",
"id",
"url",
"changed_on_utc",
"dashboard_title",
"published",
"created_by",
"changed_by",
"changed_by_name",
"owners",
]
paginated_data = self._fetch_all_pages(
endpoint="/dashboard/",
@@ -98,6 +109,42 @@ class SupersetClient:
return total_count, paginated_data
# [/DEF:get_dashboards:Function]
# [DEF:get_dashboards_page:Function]
# @PURPOSE: Fetches a single dashboards page from Superset without iterating all pages.
# @PARAM: query (Optional[Dict]) - Query with page/page_size and optional columns.
# @PRE: Client is authenticated.
# @POST: Returns total count and one page of dashboards.
# @RETURN: Tuple[int, List[Dict]]
def get_dashboards_page(self, query: Optional[Dict] = None) -> Tuple[int, List[Dict]]:
with belief_scope("get_dashboards_page"):
validated_query = self._validate_query_params(query or {})
if "columns" not in validated_query:
validated_query["columns"] = [
"slug",
"id",
"url",
"changed_on_utc",
"dashboard_title",
"published",
"created_by",
"changed_by",
"changed_by_name",
"owners",
]
response_json = cast(
Dict[str, Any],
self.network.request(
method="GET",
endpoint="/dashboard/",
params={"q": json.dumps(validated_query)},
),
)
result = response_json.get("result", [])
total_count = response_json.get("count", len(result))
return total_count, result
# [/DEF:get_dashboards_page:Function]
# [DEF:get_dashboards_summary:Function]
# @PURPOSE: Fetches dashboard metadata optimized for the grid.
# @PRE: Client is authenticated.
@@ -105,23 +152,171 @@ class SupersetClient:
# @RETURN: List[Dict]
def get_dashboards_summary(self) -> List[Dict]:
with belief_scope("SupersetClient.get_dashboards_summary"):
query = {
"columns": ["id", "dashboard_title", "changed_on_utc", "published"]
}
# Rely on list endpoint default projection to stay compatible
# across Superset versions and preserve owners in one request.
query: Dict[str, Any] = {}
_, dashboards = self.get_dashboards(query=query)
# Map fields to DashboardMetadata schema
result = []
for dash in dashboards:
owners = self._extract_owner_labels(dash.get("owners"))
# No per-dashboard detail requests here: keep list endpoint O(1).
if not owners:
owners = self._extract_owner_labels(
[dash.get("created_by"), dash.get("changed_by")],
)
result.append({
"id": dash.get("id"),
"slug": dash.get("slug"),
"title": dash.get("dashboard_title"),
"url": dash.get("url"),
"last_modified": dash.get("changed_on_utc"),
"status": "published" if dash.get("published") else "draft"
"status": "published" if dash.get("published") else "draft",
"created_by": self._extract_user_display(
None,
dash.get("created_by"),
),
"modified_by": self._extract_user_display(
dash.get("changed_by_name"),
dash.get("changed_by"),
),
"owners": owners,
})
return result
# [/DEF:get_dashboards_summary:Function]
# [DEF:get_dashboards_summary_page:Function]
# @PURPOSE: Fetches one page of dashboard metadata optimized for the grid.
# @PARAM: page (int) - 1-based page number from API route contract.
# @PARAM: page_size (int) - Number of items per page.
# @PRE: page >= 1 and page_size > 0.
# @POST: Returns mapped summaries and total dashboard count.
# @RETURN: Tuple[int, List[Dict]]
def get_dashboards_summary_page(
self,
page: int,
page_size: int,
search: Optional[str] = None,
) -> Tuple[int, List[Dict]]:
with belief_scope("SupersetClient.get_dashboards_summary_page"):
query: Dict[str, Any] = {
"page": max(page - 1, 0),
"page_size": page_size,
}
normalized_search = (search or "").strip()
if normalized_search:
# Superset list API supports filter objects with `opr` operator.
# `ct` -> contains (ILIKE on most Superset backends).
query["filters"] = [
{
"col": "dashboard_title",
"opr": "ct",
"value": normalized_search,
}
]
total_count, dashboards = self.get_dashboards_page(query=query)
result = []
for dash in dashboards:
owners = self._extract_owner_labels(dash.get("owners"))
if not owners:
owners = self._extract_owner_labels(
[dash.get("created_by"), dash.get("changed_by")],
)
result.append({
"id": dash.get("id"),
"slug": dash.get("slug"),
"title": dash.get("dashboard_title"),
"url": dash.get("url"),
"last_modified": dash.get("changed_on_utc"),
"status": "published" if dash.get("published") else "draft",
"created_by": self._extract_user_display(
None,
dash.get("created_by"),
),
"modified_by": self._extract_user_display(
dash.get("changed_by_name"),
dash.get("changed_by"),
),
"owners": owners,
})
return total_count, result
# [/DEF:get_dashboards_summary_page:Function]
# [DEF:_extract_owner_labels:Function]
# @PURPOSE: Normalize dashboard owners payload to stable display labels.
# @PRE: owners payload can be scalar, object or list.
# @POST: Returns deduplicated non-empty owner labels preserving order.
# @RETURN: List[str]
def _extract_owner_labels(self, owners_payload: Any) -> List[str]:
if owners_payload is None:
return []
owners_list: List[Any]
if isinstance(owners_payload, list):
owners_list = owners_payload
else:
owners_list = [owners_payload]
normalized: List[str] = []
for owner in owners_list:
label: Optional[str] = None
if isinstance(owner, dict):
label = self._extract_user_display(None, owner)
else:
label = self._sanitize_user_text(owner)
if label and label not in normalized:
normalized.append(label)
return normalized
# [/DEF:_extract_owner_labels:Function]
# [DEF:_extract_user_display:Function]
# @PURPOSE: Normalize user payload to a stable display name.
# @PRE: user payload can be string, dict or None.
# @POST: Returns compact non-empty display value or None.
# @RETURN: Optional[str]
def _extract_user_display(self, preferred_value: Optional[str], user_payload: Optional[Dict]) -> Optional[str]:
preferred = self._sanitize_user_text(preferred_value)
if preferred:
return preferred
if isinstance(user_payload, dict):
full_name = self._sanitize_user_text(user_payload.get("full_name"))
if full_name:
return full_name
first_name = self._sanitize_user_text(user_payload.get("first_name")) or ""
last_name = self._sanitize_user_text(user_payload.get("last_name")) or ""
combined = " ".join(part for part in [first_name, last_name] if part).strip()
if combined:
return combined
username = self._sanitize_user_text(user_payload.get("username"))
if username:
return username
email = self._sanitize_user_text(user_payload.get("email"))
if email:
return email
return None
# [/DEF:_extract_user_display:Function]
# [DEF:_sanitize_user_text:Function]
# @PURPOSE: Convert scalar value to non-empty user-facing text.
# @PRE: value can be any scalar type.
# @POST: Returns trimmed string or None.
# @RETURN: Optional[str]
def _sanitize_user_text(self, value: Optional[Union[str, int]]) -> Optional[str]:
if value is None:
return None
normalized = str(value).strip()
if not normalized:
return None
return normalized
# [/DEF:_sanitize_user_text:Function]
# [DEF:get_dashboard:Function]
# @PURPOSE: Fetches a single dashboard by ID.
# @PRE: Client is authenticated and dashboard_id exists.
@@ -336,6 +531,25 @@ class SupersetClient:
}
# [/DEF:get_dashboard_detail:Function]
# [DEF:get_charts:Function]
# @PURPOSE: Fetches all charts with pagination support.
# @PARAM: query (Optional[Dict]) - Optional query params/columns/filters.
# @PRE: Client is authenticated.
# @POST: Returns total count and charts list.
# @RETURN: Tuple[int, List[Dict]]
def get_charts(self, query: Optional[Dict] = None) -> Tuple[int, List[Dict]]:
with belief_scope("get_charts"):
validated_query = self._validate_query_params(query or {})
if "columns" not in validated_query:
validated_query["columns"] = ["id", "uuid", "slice_name", "viz_type"]
paginated_data = self._fetch_all_pages(
endpoint="/chart/",
pagination_options={"base_query": validated_query, "results_field": "result"},
)
return len(paginated_data), paginated_data
# [/DEF:get_charts:Function]
# [DEF:_extract_chart_ids_from_layout:Function]
# @PURPOSE: Traverses dashboard layout metadata and extracts chart IDs from common keys.
# @PRE: payload can be dict/list/scalar.

View File

@@ -19,6 +19,20 @@ from ..logger import belief_scope
# @TIER: CRITICAL
# @INVARIANT: logger is always a valid TaskLogger instance.
# @UX_STATE: Idle -> Active -> Complete
#
# @TEST_CONTRACT: TaskContextInit ->
# {
# required_fields: {task_id: str, add_log_fn: Callable, params: dict},
# optional_fields: {default_source: str},
# invariants: [
# "task_id matches initialized logger's task_id",
# "logger is a valid TaskLogger instance"
# ]
# }
# @TEST_FIXTURE: valid_context -> {"task_id": "123", "add_log_fn": lambda *args: None, "params": {"k": "v"}, "default_source": "plugin"}
# @TEST_EDGE: missing_task_id -> raises TypeError
# @TEST_EDGE: missing_add_log_fn -> raises TypeError
# @TEST_INVARIANT: logger_initialized -> verifies: [valid_context]
class TaskContext:
"""
Execution context provided to plugins during task execution.

View File

@@ -39,17 +39,21 @@ from ..logger import logger, belief_scope, should_log_task_level
# @INVARIANT: Task IDs are unique within the registry.
# @INVARIANT: Each task has exactly one status at any time.
# @INVARIANT: Log entries are never deleted after being added to a task.
# @TEST_CONTRACT: TaskManager -> {
# required_fields: {plugin_id: str, params: dict},
# optional_fields: {user_id: str},
# invariants: ["Task IDs are unique within the registry", "Each task has exactly one status at any time"]
#
# @TEST_CONTRACT: TaskManagerModel ->
# {
# required_fields: {plugin_loader: PluginLoader},
# invariants: [
# "Tasks are persisted immediately upon creation",
# "Running tasks use a thread pool or asyncio event loop based on executor type",
# "Log flushing runs on a background thread"
# ]
# }
# @TEST_FIXTURE: create_valid_task -> {"plugin_id": "migration_plugin", "params": {"source": "A", "target": "B"}}
# @TEST_EDGE: missing_required_field -> {"plugin_id": null}
# @TEST_EDGE: empty_response -> {"params": {}}
# @TEST_EDGE: invalid_type -> {"params": "string_instead_of_dict"}
# @TEST_EDGE: external_failure -> {"plugin_not_found": true}
# @TEST_INVARIANT: single_status -> verifies: [create_valid_task, external_failure]
# @TEST_FIXTURE: valid_manager -> {"plugin_loader": "MockPluginLoader()"}
# @TEST_EDGE: create_task_invalid_plugin -> raises ValueError
# @TEST_EDGE: create_task_invalid_params -> raises ValueError
# @TEST_INVARIANT: lifecycle_management -> verifies: [valid_manager]
class TaskManager:
"""
Manages the lifecycle of tasks, including their creation, execution, and state tracking.
"""

View File

@@ -45,6 +45,14 @@ class LogLevel(str, Enum):
# @PURPOSE: A Pydantic model representing a single, structured log entry associated with a task.
# @TIER: CRITICAL
# @INVARIANT: Each log entry has a unique timestamp and source.
#
# @TEST_CONTRACT: LogEntryModel ->
# {
# required_fields: {message: str},
# optional_fields: {timestamp: datetime, level: str, source: str, context: dict, metadata: dict}
# }
# @TEST_FIXTURE: valid_log_entry -> {"message": "Plugin initialized"}
# @TEST_EDGE: empty_message -> {"message": ""}
class LogEntry(BaseModel):
timestamp: datetime = Field(default_factory=datetime.utcnow)
level: str = Field(default="INFO")

View File

@@ -24,6 +24,20 @@ from ..logger import logger, belief_scope
# @SEMANTICS: persistence, service, database, sqlalchemy
# @PURPOSE: Provides methods to save and load tasks from the tasks.db database using SQLAlchemy.
# @INVARIANT: Persistence must handle potentially missing task fields natively.
#
# @TEST_CONTRACT: TaskPersistenceService ->
# {
# required_fields: {},
# invariants: [
# "persist_task creates or updates a record",
# "load_tasks retrieves valid Task instances",
# "delete_tasks correctly removes records from the database"
# ]
# }
# @TEST_FIXTURE: valid_task_persistence -> {"task_id": "123", "status": "PENDING"}
# @TEST_EDGE: persist_invalid_task_type -> raises Exception
# @TEST_EDGE: load_corrupt_json_params -> handled gracefully
# @TEST_INVARIANT: accurate_round_trip -> verifies: [valid_task_persistence, load_corrupt_json_params]
class TaskPersistenceService:
# [DEF:_json_load_if_needed:Function]
# @PURPOSE: Safely load JSON strings from DB if necessary
@@ -245,6 +259,19 @@ class TaskPersistenceService:
# @TIER: CRITICAL
# @RELATION: DEPENDS_ON -> TaskLogRecord
# @INVARIANT: Log entries are batch-inserted for performance.
#
# @TEST_CONTRACT: TaskLogPersistenceService ->
# {
# required_fields: {},
# invariants: [
# "add_logs efficiently saves logs to the database",
# "get_logs retrieves properly filtered LogEntry objects"
# ]
# }
# @TEST_FIXTURE: valid_log_batch -> {"task_id": "123", "logs": [{"level": "INFO", "message": "msg"}]}
# @TEST_EDGE: empty_log_list -> no-op behavior
# @TEST_EDGE: add_logs_db_error -> rollback and log error
# @TEST_INVARIANT: accurate_log_aggregation -> verifies: [valid_log_batch]
class TaskLogPersistenceService:
"""
Service for persisting and querying task logs.

View File

@@ -15,8 +15,21 @@ from typing import Dict, Any, Optional, Callable
# @PURPOSE: A wrapper around TaskManager._add_log that carries task_id and source context.
# @TIER: CRITICAL
# @INVARIANT: All log calls include the task_id and source.
# @TEST_DATA: task_logger -> {"task_id": "test_123", "source": "test_plugin"}
# @UX_STATE: Idle -> Logging -> (system records log)
#
# @TEST_CONTRACT: TaskLoggerModel ->
# {
# required_fields: {task_id: str, add_log_fn: Callable},
# optional_fields: {source: str},
# invariants: [
# "All specific log methods (info, error) delegate to _log",
# "with_source creates a new logger with the same task_id"
# ]
# }
# @TEST_FIXTURE: valid_task_logger -> {"task_id": "test_123", "add_log_fn": lambda *args: None, "source": "test_plugin"}
# @TEST_EDGE: missing_task_id -> raises TypeError
# @TEST_EDGE: invalid_add_log_fn -> raises TypeError
# @TEST_INVARIANT: consistent_delegation -> verifies: [valid_task_logger]
class TaskLogger:
"""
A dedicated logger for tasks that automatically tags logs with source attribution.

View File

@@ -101,7 +101,8 @@ class APIClient:
def __init__(self, config: Dict[str, Any], verify_ssl: bool = True, timeout: int = DEFAULT_TIMEOUT):
with belief_scope("__init__"):
app_logger.info("[APIClient.__init__][Entry] Initializing APIClient.")
self.base_url: str = config.get("base_url", "")
self.base_url: str = self._normalize_base_url(config.get("base_url", ""))
self.api_base_url: str = f"{self.base_url}/api/v1"
self.auth = config.get("auth")
self.request_settings = {"verify_ssl": verify_ssl, "timeout": timeout}
self.session = self._init_session()
@@ -156,6 +157,34 @@ class APIClient:
return session
# [/DEF:_init_session:Function]
# [DEF:_normalize_base_url:Function]
# @PURPOSE: Normalize Superset environment URL to base host/path without trailing slash and /api/v1 suffix.
# @PRE: raw_url can be empty.
# @POST: Returns canonical base URL suitable for building API endpoints.
# @RETURN: str
def _normalize_base_url(self, raw_url: str) -> str:
normalized = str(raw_url or "").strip().rstrip("/")
if normalized.lower().endswith("/api/v1"):
normalized = normalized[:-len("/api/v1")]
return normalized.rstrip("/")
# [/DEF:_normalize_base_url:Function]
# [DEF:_build_api_url:Function]
# @PURPOSE: Build absolute Superset API URL for endpoint using canonical /api/v1 base.
# @PRE: endpoint is relative path or absolute URL.
# @POST: Returns full URL without accidental duplicate slashes.
# @RETURN: str
def _build_api_url(self, endpoint: str) -> str:
normalized_endpoint = str(endpoint or "").strip()
if normalized_endpoint.startswith("http://") or normalized_endpoint.startswith("https://"):
return normalized_endpoint
if not normalized_endpoint.startswith("/"):
normalized_endpoint = f"/{normalized_endpoint}"
if normalized_endpoint.startswith("/api/v1/") or normalized_endpoint == "/api/v1":
return f"{self.base_url}{normalized_endpoint}"
return f"{self.api_base_url}{normalized_endpoint}"
# [/DEF:_build_api_url:Function]
# [DEF:authenticate:Function]
# @PURPOSE: Выполняет аутентификацию в Superset API и получает access и CSRF токены.
# @PRE: self.auth and self.base_url must be valid.
@@ -166,7 +195,7 @@ class APIClient:
with belief_scope("authenticate"):
app_logger.info("[authenticate][Enter] Authenticating to %s", self.base_url)
try:
login_url = f"{self.base_url}/security/login"
login_url = f"{self.api_base_url}/security/login"
# Log the payload keys and values (masking password)
masked_auth = {k: ("******" if k == "password" else v) for k, v in self.auth.items()}
app_logger.info(f"[authenticate][Debug] Login URL: {login_url}")
@@ -180,7 +209,7 @@ class APIClient:
response.raise_for_status()
access_token = response.json()["access_token"]
csrf_url = f"{self.base_url}/security/csrf_token/"
csrf_url = f"{self.api_base_url}/security/csrf_token/"
csrf_response = self.session.get(csrf_url, headers={"Authorization": f"Bearer {access_token}"}, timeout=self.request_settings["timeout"])
csrf_response.raise_for_status()
@@ -224,7 +253,7 @@ class APIClient:
# @RETURN: `requests.Response` если `raw_response=True`, иначе `dict`.
# @THROW: SupersetAPIError, NetworkError и их подклассы.
def request(self, method: str, endpoint: str, headers: Optional[Dict] = None, raw_response: bool = False, **kwargs) -> Union[requests.Response, Dict[str, Any]]:
full_url = f"{self.base_url}{endpoint}"
full_url = self._build_api_url(endpoint)
_headers = self.headers.copy()
if headers:
_headers.update(headers)
@@ -288,7 +317,7 @@ class APIClient:
# @THROW: SupersetAPIError, NetworkError, TypeError.
def upload_file(self, endpoint: str, file_info: Dict[str, Any], extra_data: Optional[Dict] = None, timeout: Optional[int] = None) -> Dict:
with belief_scope("upload_file"):
full_url = f"{self.base_url}{endpoint}"
full_url = self._build_api_url(endpoint)
_headers = self.headers.copy()
_headers.pop('Content-Type', None)

View File

@@ -14,20 +14,21 @@ from .core.config_manager import ConfigManager
from .core.scheduler import SchedulerService
from .services.resource_service import ResourceService
from .services.mapping_service import MappingService
from .services.clean_release.repository import CleanReleaseRepository
from .core.database import init_db, get_auth_db
from .core.logger import logger
from .core.auth.jwt import decode_token
from .core.auth.repository import AuthRepository
from .models.auth import User
# Initialize singletons
# Use absolute path relative to this file to ensure plugins are found regardless of CWD
project_root = Path(__file__).parent.parent.parent
config_path = project_root / "config.json"
# Initialize database before services that use persisted configuration.
init_db()
config_manager = ConfigManager(config_path=str(config_path))
# Initialize singletons
# Use absolute path relative to this file to ensure plugins are found regardless of CWD
project_root = Path(__file__).parent.parent.parent
config_path = project_root / "config.json"
# Initialize database before services that use persisted configuration.
init_db()
config_manager = ConfigManager(config_path=str(config_path))
# [DEF:get_config_manager:Function]
# @PURPOSE: Dependency injector for ConfigManager.
@@ -54,6 +55,9 @@ logger.info("SchedulerService initialized")
resource_service = ResourceService()
logger.info("ResourceService initialized")
clean_release_repository = CleanReleaseRepository()
logger.info("CleanReleaseRepository initialized")
# [DEF:get_plugin_loader:Function]
# @PURPOSE: Dependency injector for PluginLoader.
# @PRE: Global plugin_loader must be initialized.
@@ -104,6 +108,16 @@ def get_mapping_service() -> MappingService:
return MappingService(config_manager)
# [/DEF:get_mapping_service:Function]
# [DEF:get_clean_release_repository:Function]
# @PURPOSE: Dependency injector for CleanReleaseRepository.
# @PRE: Global clean_release_repository must be initialized.
# @POST: Returns shared CleanReleaseRepository instance.
# @RETURN: CleanReleaseRepository - Shared clean release repository instance.
def get_clean_release_repository() -> CleanReleaseRepository:
return clean_release_repository
# [/DEF:get_clean_release_repository:Function]
# [DEF:oauth2_scheme:Variable]
# @PURPOSE: OAuth2 password bearer scheme for token extraction.
oauth2_scheme = OAuth2PasswordBearer(tokenUrl="/api/auth/login")

View File

@@ -0,0 +1,319 @@
# [DEF:backend.src.models.clean_release:Module]
# @TIER: CRITICAL
# @SEMANTICS: clean-release, models, lifecycle, policy, manifest, compliance
# @PURPOSE: Define clean release domain entities and validation contracts for enterprise compliance flow.
# @LAYER: Domain
# @RELATION: BINDS_TO -> specs/023-clean-repo-enterprise/data-model.md
# @INVARIANT: Enterprise-clean policy always forbids external sources.
from __future__ import annotations
from datetime import datetime
from enum import Enum
from typing import List, Optional
from pydantic import BaseModel, Field, model_validator
# [DEF:ReleaseCandidateStatus:Class]
# @PURPOSE: Lifecycle states for release candidate.
class ReleaseCandidateStatus(str, Enum):
DRAFT = "draft"
PREPARED = "prepared"
COMPLIANT = "compliant"
BLOCKED = "blocked"
RELEASED = "released"
# [/DEF:ReleaseCandidateStatus:Class]
# [DEF:ProfileType:Class]
# @PURPOSE: Supported profile identifiers.
class ProfileType(str, Enum):
ENTERPRISE_CLEAN = "enterprise-clean"
DEVELOPMENT = "development"
# [/DEF:ProfileType:Class]
# [DEF:ClassificationType:Class]
# @PURPOSE: Manifest classification outcomes for artifacts.
class ClassificationType(str, Enum):
REQUIRED_SYSTEM = "required-system"
ALLOWED = "allowed"
EXCLUDED_PROHIBITED = "excluded-prohibited"
# [/DEF:ClassificationType:Class]
# [DEF:RegistryStatus:Class]
# @PURPOSE: Registry lifecycle status.
class RegistryStatus(str, Enum):
ACTIVE = "active"
INACTIVE = "inactive"
# [/DEF:RegistryStatus:Class]
# [DEF:CheckFinalStatus:Class]
# @PURPOSE: Final status for compliance check run.
class CheckFinalStatus(str, Enum):
RUNNING = "running"
COMPLIANT = "compliant"
BLOCKED = "blocked"
FAILED = "failed"
# [/DEF:CheckFinalStatus:Class]
# [DEF:ExecutionMode:Class]
# @PURPOSE: Execution channel for compliance checks.
class ExecutionMode(str, Enum):
TUI = "tui"
CI = "ci"
# [/DEF:ExecutionMode:Class]
# [DEF:CheckStageName:Class]
# @PURPOSE: Mandatory check stages.
class CheckStageName(str, Enum):
DATA_PURITY = "data_purity"
INTERNAL_SOURCES_ONLY = "internal_sources_only"
NO_EXTERNAL_ENDPOINTS = "no_external_endpoints"
MANIFEST_CONSISTENCY = "manifest_consistency"
# [/DEF:CheckStageName:Class]
# [DEF:CheckStageStatus:Class]
# @PURPOSE: Stage-level execution status.
class CheckStageStatus(str, Enum):
PASS = "pass"
FAIL = "fail"
SKIPPED = "skipped"
# [/DEF:CheckStageStatus:Class]
# [DEF:ViolationCategory:Class]
# @PURPOSE: Normalized compliance violation categories.
class ViolationCategory(str, Enum):
DATA_PURITY = "data-purity"
EXTERNAL_SOURCE = "external-source"
MANIFEST_INTEGRITY = "manifest-integrity"
POLICY_CONFLICT = "policy-conflict"
OPERATIONAL_RISK = "operational-risk"
# [/DEF:ViolationCategory:Class]
# [DEF:ViolationSeverity:Class]
# @PURPOSE: Severity levels for violation triage.
class ViolationSeverity(str, Enum):
CRITICAL = "critical"
HIGH = "high"
MEDIUM = "medium"
LOW = "low"
# [/DEF:ViolationSeverity:Class]
# [DEF:ReleaseCandidate:Class]
# @PURPOSE: Candidate metadata for clean-release workflow.
# @PRE: candidate_id, source_snapshot_ref are non-empty.
# @POST: Model instance is valid for lifecycle transitions.
class ReleaseCandidate(BaseModel):
candidate_id: str
version: str
profile: ProfileType
created_at: datetime
created_by: str
source_snapshot_ref: str
status: ReleaseCandidateStatus = ReleaseCandidateStatus.DRAFT
@model_validator(mode="after")
def _validate_non_empty(self):
if not self.candidate_id.strip():
raise ValueError("candidate_id must be non-empty")
if not self.source_snapshot_ref.strip():
raise ValueError("source_snapshot_ref must be non-empty")
return self
# [/DEF:ReleaseCandidate:Class]
# [DEF:CleanProfilePolicy:Class]
# @PURPOSE: Policy contract for artifact/source decisions.
class CleanProfilePolicy(BaseModel):
policy_id: str
policy_version: str
active: bool
prohibited_artifact_categories: List[str] = Field(default_factory=list)
required_system_categories: List[str] = Field(default_factory=list)
external_source_forbidden: bool = True
internal_source_registry_ref: str
effective_from: datetime
effective_to: Optional[datetime] = None
profile: ProfileType = ProfileType.ENTERPRISE_CLEAN
@model_validator(mode="after")
def _validate_policy(self):
if self.profile == ProfileType.ENTERPRISE_CLEAN:
if not self.external_source_forbidden:
raise ValueError("enterprise-clean policy requires external_source_forbidden=true")
if not self.prohibited_artifact_categories:
raise ValueError("enterprise-clean policy requires prohibited_artifact_categories")
if not self.internal_source_registry_ref.strip():
raise ValueError("internal_source_registry_ref must be non-empty")
return self
# [/DEF:CleanProfilePolicy:Class]
# [DEF:ResourceSourceEntry:Class]
# @PURPOSE: One internal source definition.
class ResourceSourceEntry(BaseModel):
source_id: str
host: str
protocol: str
purpose: str
allowed_paths: List[str] = Field(default_factory=list)
enabled: bool = True
# [/DEF:ResourceSourceEntry:Class]
# [DEF:ResourceSourceRegistry:Class]
# @PURPOSE: Allowlist of internal sources.
class ResourceSourceRegistry(BaseModel):
registry_id: str
name: str
entries: List[ResourceSourceEntry]
updated_at: datetime
updated_by: str
status: RegistryStatus = RegistryStatus.ACTIVE
@model_validator(mode="after")
def _validate_registry(self):
if not self.entries:
raise ValueError("registry entries cannot be empty")
if self.status == RegistryStatus.ACTIVE and not any(e.enabled for e in self.entries):
raise ValueError("active registry must include at least one enabled entry")
return self
# [/DEF:ResourceSourceRegistry:Class]
# [DEF:ManifestItem:Class]
# @PURPOSE: One artifact entry in manifest.
class ManifestItem(BaseModel):
path: str
category: str
classification: ClassificationType
reason: str
checksum: Optional[str] = None
# [/DEF:ManifestItem:Class]
# [DEF:ManifestSummary:Class]
# @PURPOSE: Aggregate counters for manifest decisions.
class ManifestSummary(BaseModel):
included_count: int = Field(ge=0)
excluded_count: int = Field(ge=0)
prohibited_detected_count: int = Field(ge=0)
# [/DEF:ManifestSummary:Class]
# [DEF:DistributionManifest:Class]
# @PURPOSE: Deterministic release composition for audit.
class DistributionManifest(BaseModel):
manifest_id: str
candidate_id: str
policy_id: str
generated_at: datetime
generated_by: str
items: List[ManifestItem]
summary: ManifestSummary
deterministic_hash: str
@model_validator(mode="after")
def _validate_counts(self):
if self.summary.included_count + self.summary.excluded_count != len(self.items):
raise ValueError("manifest summary counts must match items size")
return self
# [/DEF:DistributionManifest:Class]
# [DEF:CheckStageResult:Class]
# @PURPOSE: Per-stage compliance result.
class CheckStageResult(BaseModel):
stage: CheckStageName
status: CheckStageStatus
details: Optional[str] = None
duration_ms: Optional[int] = Field(default=None, ge=0)
# [/DEF:CheckStageResult:Class]
# [DEF:ComplianceCheckRun:Class]
# @PURPOSE: One execution run of compliance pipeline.
class ComplianceCheckRun(BaseModel):
check_run_id: str
candidate_id: str
policy_id: str
started_at: datetime
finished_at: Optional[datetime] = None
final_status: CheckFinalStatus = CheckFinalStatus.RUNNING
triggered_by: str
execution_mode: ExecutionMode
checks: List[CheckStageResult] = Field(default_factory=list)
@model_validator(mode="after")
def _validate_terminal_integrity(self):
if self.final_status == CheckFinalStatus.COMPLIANT:
mandatory = {c.stage: c.status for c in self.checks}
required = {
CheckStageName.DATA_PURITY,
CheckStageName.INTERNAL_SOURCES_ONLY,
CheckStageName.NO_EXTERNAL_ENDPOINTS,
CheckStageName.MANIFEST_CONSISTENCY,
}
if not required.issubset(mandatory.keys()):
raise ValueError("compliant run requires all mandatory stages")
if any(mandatory[s] != CheckStageStatus.PASS for s in required):
raise ValueError("compliant run requires PASS on all mandatory stages")
return self
# [/DEF:ComplianceCheckRun:Class]
# [DEF:ComplianceViolation:Class]
# @PURPOSE: Normalized violation row for triage and blocking decisions.
class ComplianceViolation(BaseModel):
violation_id: str
check_run_id: str
category: ViolationCategory
severity: ViolationSeverity
location: str
evidence: Optional[str] = None
remediation: str
blocked_release: bool
detected_at: datetime
@model_validator(mode="after")
def _validate_violation(self):
if self.category == ViolationCategory.EXTERNAL_SOURCE and not self.blocked_release:
raise ValueError("external-source violation must block release")
if self.severity == ViolationSeverity.CRITICAL and not self.remediation.strip():
raise ValueError("critical violation requires remediation")
return self
# [/DEF:ComplianceViolation:Class]
# [DEF:ComplianceReport:Class]
# @PURPOSE: Final report payload for operator and audit systems.
class ComplianceReport(BaseModel):
report_id: str
check_run_id: str
candidate_id: str
generated_at: datetime
final_status: CheckFinalStatus
operator_summary: str
structured_payload_ref: str
violations_count: int = Field(ge=0)
blocking_violations_count: int = Field(ge=0)
@model_validator(mode="after")
def _validate_report_counts(self):
if self.blocking_violations_count > self.violations_count:
raise ValueError("blocking_violations_count cannot exceed violations_count")
if self.final_status == CheckFinalStatus.BLOCKED and self.blocking_violations_count <= 0:
raise ValueError("blocked report requires blocking violations")
return self
# [/DEF:ComplianceReport:Class]
# [/DEF:backend.src.models.clean_release:Module]

View File

@@ -47,6 +47,19 @@ class ReportStatus(str, Enum):
# @INVARIANT: The properties accurately describe error state.
# @SEMANTICS: error, context, payload
# @PURPOSE: Error and recovery context for failed/partial reports.
#
# @TEST_CONTRACT: ErrorContextModel ->
# {
# required_fields: {
# message: str
# },
# optional_fields: {
# code: str,
# next_actions: list[str]
# }
# }
# @TEST_FIXTURE: basic_error -> {"message": "Connection timeout", "code": "ERR_504", "next_actions": ["retry"]}
# @TEST_EDGE: missing_message -> {"code": "ERR_504"}
class ErrorContext(BaseModel):
code: Optional[str] = None
message: str
@@ -59,6 +72,36 @@ class ErrorContext(BaseModel):
# @INVARIANT: Must represent canonical task record attributes.
# @SEMANTICS: report, model, summary
# @PURPOSE: Canonical normalized report envelope for one task execution.
#
# @TEST_CONTRACT: TaskReportModel ->
# {
# required_fields: {
# report_id: str,
# task_id: str,
# task_type: TaskType,
# status: ReportStatus,
# updated_at: datetime,
# summary: str
# },
# invariants: [
# "report_id is a non-empty string",
# "task_id is a non-empty string",
# "summary is a non-empty string"
# ]
# }
# @TEST_FIXTURE: valid_task_report ->
# {
# report_id: "rep-123",
# task_id: "task-456",
# task_type: "migration",
# status: "success",
# updated_at: "2026-02-26T12:00:00Z",
# summary: "Migration completed successfully"
# }
# @TEST_EDGE: empty_report_id -> {"report_id": " ", "task_id": "task-456", "task_type": "migration", "status": "success", "updated_at": "2026-02-26T12:00:00Z", "summary": "Done"}
# @TEST_EDGE: empty_summary -> {"report_id": "rep-123", "task_id": "task-456", "task_type": "migration", "status": "success", "updated_at": "2026-02-26T12:00:00Z", "summary": ""}
# @TEST_EDGE: invalid_task_type -> {"report_id": "rep-123", "task_id": "task-456", "task_type": "invalid_type", "status": "success", "updated_at": "2026-02-26T12:00:00Z", "summary": "Done"}
# @TEST_INVARIANT: non_empty_validators -> verifies: [empty_report_id, empty_summary]
class TaskReport(BaseModel):
report_id: str
task_id: str
@@ -85,6 +128,25 @@ class TaskReport(BaseModel):
# @INVARIANT: Time and pagination queries are mutually consistent.
# @SEMANTICS: query, filter, search
# @PURPOSE: Query object for server-side report filtering, sorting, and pagination.
#
# @TEST_CONTRACT: ReportQueryModel ->
# {
# optional_fields: {
# page: int, page_size: int, task_types: list[TaskType], statuses: list[ReportStatus],
# time_from: datetime, time_to: datetime, search: str, sort_by: str, sort_order: str
# },
# invariants: [
# "page >= 1", "1 <= page_size <= 100",
# "sort_by in {'updated_at', 'status', 'task_type'}",
# "sort_order in {'asc', 'desc'}",
# "time_from <= time_to if both exist"
# ]
# }
# @TEST_FIXTURE: valid_query -> {"page": 1, "page_size":20, "sort_by": "updated_at", "sort_order": "desc"}
# @TEST_EDGE: invalid_page_size_large -> {"page_size": 150}
# @TEST_EDGE: invalid_sort_by -> {"sort_by": "unknown_field"}
# @TEST_EDGE: invalid_time_range -> {"time_from": "2026-02-26T12:00:00Z", "time_to": "2026-02-25T12:00:00Z"}
# @TEST_INVARIANT: attribute_constraints_enforced -> verifies: [invalid_page_size_large, invalid_sort_by, invalid_time_range]
class ReportQuery(BaseModel):
page: int = Field(default=1, ge=1)
page_size: int = Field(default=20, ge=1, le=100)
@@ -124,6 +186,16 @@ class ReportQuery(BaseModel):
# @INVARIANT: Represents paginated data correctly.
# @SEMANTICS: collection, pagination
# @PURPOSE: Paginated collection of normalized task reports.
#
# @TEST_CONTRACT: ReportCollectionModel ->
# {
# required_fields: {
# items: list[TaskReport], total: int, page: int, page_size: int, has_next: bool, applied_filters: ReportQuery
# },
# invariants: ["total >= 0", "page >= 1", "page_size >= 1"]
# }
# @TEST_FIXTURE: empty_collection -> {"items": [], "total": 0, "page": 1, "page_size": 20, "has_next": False, "applied_filters": {}}
# @TEST_EDGE: negative_total -> {"items": [], "total": -5, "page": 1, "page_size": 20, "has_next": False, "applied_filters": {}}
class ReportCollection(BaseModel):
items: List[TaskReport]
total: int = Field(ge=0)
@@ -139,6 +211,14 @@ class ReportCollection(BaseModel):
# @INVARIANT: Incorporates a report and logs correctly.
# @SEMANTICS: view, detail, logs
# @PURPOSE: Detailed report representation including diagnostics and recovery actions.
#
# @TEST_CONTRACT: ReportDetailViewModel ->
# {
# required_fields: {report: TaskReport},
# optional_fields: {timeline: list[dict], diagnostics: dict, next_actions: list[str]}
# }
# @TEST_FIXTURE: valid_detail -> {"report": {"report_id": "rep-1", "task_id": "task-1", "task_type": "backup", "status": "success", "updated_at": "2026-02-26T12:00:00Z", "summary": "Done"}}
# @TEST_EDGE: missing_report -> {}
class ReportDetailView(BaseModel):
report: TaskReport
timeline: List[Dict[str, Any]] = Field(default_factory=list)

View File

@@ -39,6 +39,61 @@ class TaskRecord(Base):
# @TIER: CRITICAL
# @RELATION: DEPENDS_ON -> TaskRecord
# @INVARIANT: Each log entry belongs to exactly one task.
#
# @TEST_CONTRACT: TaskLogCreate ->
# {
# required_fields: {
# task_id: str,
# timestamp: datetime,
# level: str,
# source: str,
# message: str
# },
# optional_fields: {
# metadata_json: str,
# id: int
# },
# invariants: [
# "task_id matches an existing TaskRecord.id"
# ]
# }
#
# @TEST_FIXTURE: basic_info_log ->
# {
# task_id: "00000000-0000-0000-0000-000000000000",
# timestamp: "2026-02-26T12:00:00Z",
# level: "INFO",
# source: "system",
# message: "Task initialization complete"
# }
#
# @TEST_EDGE: missing_required_field ->
# {
# timestamp: "2026-02-26T12:00:00Z",
# level: "ERROR",
# source: "system",
# message: "Missing task_id"
# }
#
# @TEST_EDGE: invalid_type ->
# {
# task_id: "00000000-0000-0000-0000-000000000000",
# timestamp: "2026-02-26T12:00:00Z",
# level: 500,
# source: "system",
# message: "Integer level"
# }
#
# @TEST_EDGE: empty_message ->
# {
# task_id: "00000000-0000-0000-0000-000000000000",
# timestamp: "2026-02-26T12:00:00Z",
# level: "DEBUG",
# source: "system",
# message: ""
# }
#
# @TEST_INVARIANT: exact_one_task_association -> verifies: [basic_info_log, missing_required_field]
class TaskLogRecord(Base):
__tablename__ = "task_logs"

View File

@@ -0,0 +1,38 @@
# [DEF:backend.src.scripts.clean_release_tui:Module]
# @TIER: CRITICAL
# @SEMANTICS: tui, clean-release, ncurses, operator-flow, placeholder
# @PURPOSE: Provide clean release TUI entrypoint placeholder for phased implementation.
# @LAYER: UI
# @RELATION: BINDS_TO -> specs/023-clean-repo-enterprise/ux_reference.md
# @INVARIANT: Entry point is executable and does not mutate release data in placeholder mode.
# @PRE: Python runtime is available.
# @POST: Placeholder message is emitted and process exits with success.
# @UX_STATE: READY -> Displays profile hints and allowed internal sources
# @UX_STATE: RUNNING -> Triggered by operator action (F5), check in progress
# @UX_STATE: BLOCKED -> Violations are displayed with remediation hints
# @UX_FEEDBACK: Console lines provide immediate operator guidance
# @UX_RECOVERY: Operator re-runs check after remediation from the same screen
# @TEST_CONTRACT: TuiEntrypointInput -> ExitCodeInt
# @TEST_SCENARIO: startup_ready_state -> main prints READY and returns 0
# @TEST_FIXTURE: tui_placeholder -> INLINE_JSON
# @TEST_EDGE: stdout_unavailable -> process returns non-zero via runtime exception propagation
# @TEST_EDGE: interrupted_execution -> user interruption terminates process
# @TEST_EDGE: invalid_terminal -> fallback text output remains deterministic
# @TEST_INVARIANT: placeholder_no_mutation -> VERIFIED_BY: [startup_ready_state]
def main() -> int:
print("Enterprise Clean Release Validator (TUI placeholder)")
print("Allowed Internal Sources:")
print(" - repo.intra.company.local")
print(" - artifacts.intra.company.local")
print(" - pypi.intra.company.local")
print("Status: READY")
print("Use F5 to run check; BLOCKED state will show external-source violation details.")
return 0
if __name__ == "__main__":
raise SystemExit(main())
# [/DEF:backend.src.scripts.clean_release_tui:Module]

View File

@@ -10,7 +10,7 @@
},
"changed_by_name": "Superset Admin",
"changed_on": "2026-02-10T13:39:35.945662",
"changed_on_delta_humanized": "15 days ago",
"changed_on_delta_humanized": "16 days ago",
"charts": [
"TA-0001-001 test_chart"
],
@@ -19,7 +19,7 @@
"id": 1,
"last_name": "Admin"
},
"created_on_delta_humanized": "15 days ago",
"created_on_delta_humanized": "16 days ago",
"css": null,
"dashboard_title": "TA-0001 Test dashboard",
"id": 13,
@@ -54,7 +54,7 @@
"last_name": "Admin"
},
"changed_on": "2026-02-10T13:38:26.175551",
"changed_on_humanized": "15 days ago",
"changed_on_humanized": "16 days ago",
"column_formats": {},
"columns": [
{
@@ -424,7 +424,7 @@
"last_name": "Admin"
},
"created_on": "2026-02-10T13:38:26.050436",
"created_on_humanized": "15 days ago",
"created_on_humanized": "16 days ago",
"database": {
"allow_multi_catalog": false,
"backend": "postgresql",

View File

@@ -33,22 +33,43 @@ async def test_get_dashboards_with_status():
]
# Mock tasks
mock_task = MagicMock()
mock_task.id = "task-123"
mock_task.status = "SUCCESS"
mock_task.params = {"resource_id": "dashboard-1"}
mock_task.created_at = datetime.now()
task_prod_old = MagicMock()
task_prod_old.id = "task-123"
task_prod_old.plugin_id = "llm_dashboard_validation"
task_prod_old.status = "SUCCESS"
task_prod_old.params = {"dashboard_id": "1", "environment_id": "prod"}
task_prod_old.started_at = datetime(2024, 1, 1, 10, 0, 0)
task_prod_new = MagicMock()
task_prod_new.id = "task-124"
task_prod_new.plugin_id = "llm_dashboard_validation"
task_prod_new.status = "TaskStatus.FAILED"
task_prod_new.params = {"dashboard_id": "1", "environment_id": "prod"}
task_prod_new.result = {"status": "FAIL"}
task_prod_new.started_at = datetime(2024, 1, 1, 12, 0, 0)
task_other_env = MagicMock()
task_other_env.id = "task-200"
task_other_env.plugin_id = "llm_dashboard_validation"
task_other_env.status = "SUCCESS"
task_other_env.params = {"dashboard_id": "1", "environment_id": "stage"}
task_other_env.started_at = datetime(2024, 1, 1, 13, 0, 0)
env = MagicMock()
env.id = "prod"
result = await service.get_dashboards_with_status(env, [mock_task])
result = await service.get_dashboards_with_status(
env,
[task_prod_old, task_prod_new, task_other_env],
)
assert len(result) == 2
assert result[0]["id"] == 1
assert "git_status" in result[0]
assert "last_task" in result[0]
assert result[0]["last_task"]["task_id"] == "task-123"
assert result[0]["last_task"]["task_id"] == "task-124"
assert result[0]["last_task"]["status"] == "FAILED"
assert result[0]["last_task"]["validation_status"] == "FAIL"
# [/DEF:test_get_dashboards_with_status:Function]
@@ -145,7 +166,9 @@ def test_get_git_status_for_dashboard_no_repo():
result = service._get_git_status_for_dashboard(123)
assert result is None
assert result is not None
assert result['sync_status'] == 'NO_REPO'
assert result['has_repo'] is False
# [/DEF:test_get_git_status_for_dashboard_no_repo:Function]
@@ -212,4 +235,38 @@ def test_extract_resource_name_from_task():
# [/DEF:test_extract_resource_name_from_task:Function]
# [/DEF:backend.src.services.__tests__.test_resource_service:Module]
# [DEF:test_get_last_task_for_resource_empty_tasks:Function]
# @TEST: _get_last_task_for_resource returns None for empty tasks list
# @PRE: tasks is empty list
# @POST: Returns None
def test_get_last_task_for_resource_empty_tasks():
from src.services.resource_service import ResourceService
service = ResourceService()
result = service._get_last_task_for_resource("dashboard-1", [])
assert result is None
# [/DEF:test_get_last_task_for_resource_empty_tasks:Function]
# [DEF:test_get_last_task_for_resource_no_match:Function]
# @TEST: _get_last_task_for_resource returns None when no tasks match resource_id
# @PRE: tasks list has no matching resource_id
# @POST: Returns None
def test_get_last_task_for_resource_no_match():
from src.services.resource_service import ResourceService
service = ResourceService()
task = MagicMock()
task.id = "task-999"
task.status = "SUCCESS"
task.params = {"resource_id": "dashboard-99"}
task.created_at = datetime(2024, 1, 1, 10, 0, 0)
result = service._get_last_task_for_resource("dashboard-1", [task])
assert result is None
# [/DEF:test_get_last_task_for_resource_no_match:Function]
# [/DEF:backend.src.services.__tests__.test_resource_service:Module]

View File

@@ -0,0 +1,20 @@
# [DEF:backend.src.services.clean_release:Module]
# @TIER: STANDARD
# @SEMANTICS: clean-release, services, package, initialization
# @PURPOSE: Initialize clean release service package and provide explicit module exports.
# @LAYER: Domain
# @RELATION: EXPORTS -> policy_engine, manifest_builder, preparation_service, source_isolation, compliance_orchestrator, report_builder, repository, stages, audit_service
# @INVARIANT: Package import must not execute runtime side effects beyond symbol export setup.
__all__ = [
"policy_engine",
"manifest_builder",
"preparation_service",
"source_isolation",
"compliance_orchestrator",
"report_builder",
"repository",
"stages",
"audit_service",
]
# [/DEF:backend.src.services.clean_release:Module]

View File

@@ -0,0 +1,85 @@
# [DEF:backend.tests.services.clean_release.test_compliance_orchestrator:Module]
# @TIER: STANDARD
# @SEMANTICS: tests, clean-release, orchestrator, stage-state-machine
# @PURPOSE: Validate compliance orchestrator stage transitions and final status derivation.
# @LAYER: Domain
# @RELATION: TESTS -> backend.src.services.clean_release.compliance_orchestrator
# @INVARIANT: Failed mandatory stage forces BLOCKED terminal status.
from unittest.mock import patch
import pytest
from src.models.clean_release import (
CheckFinalStatus,
CheckStageName,
CheckStageResult,
CheckStageStatus,
)
from src.services.clean_release.compliance_orchestrator import CleanComplianceOrchestrator
from src.services.clean_release.report_builder import ComplianceReportBuilder
from src.services.clean_release.repository import CleanReleaseRepository
# [DEF:test_orchestrator_stage_failure_blocks_release:Function]
# @PURPOSE: Verify mandatory stage failure forces BLOCKED final status.
def test_orchestrator_stage_failure_blocks_release():
repository = CleanReleaseRepository()
orchestrator = CleanComplianceOrchestrator(repository)
run = orchestrator.start_check_run(
candidate_id="2026.03.03-rc1",
policy_id="policy-enterprise-clean-v1",
triggered_by="tester",
execution_mode="tui",
)
run = orchestrator.execute_stages(
run,
forced_results=[
CheckStageResult(stage=CheckStageName.DATA_PURITY, status=CheckStageStatus.PASS, details="ok"),
CheckStageResult(stage=CheckStageName.INTERNAL_SOURCES_ONLY, status=CheckStageStatus.PASS, details="ok"),
CheckStageResult(stage=CheckStageName.NO_EXTERNAL_ENDPOINTS, status=CheckStageStatus.FAIL, details="external"),
CheckStageResult(stage=CheckStageName.MANIFEST_CONSISTENCY, status=CheckStageStatus.PASS, details="ok"),
],
)
run = orchestrator.finalize_run(run)
assert run.final_status == CheckFinalStatus.BLOCKED
# [/DEF:test_orchestrator_stage_failure_blocks_release:Function]
# [DEF:test_orchestrator_missing_stage_result:Function]
# @PURPOSE: Verify incomplete mandatory stage set cannot end as COMPLIANT and results in FAILED.
def test_orchestrator_missing_stage_result():
repository = CleanReleaseRepository()
orchestrator = CleanComplianceOrchestrator(repository)
run = orchestrator.start_check_run("cand-1", "pol-1", "tester", "tui")
run = orchestrator.execute_stages(
run,
forced_results=[CheckStageResult(stage=CheckStageName.DATA_PURITY, status=CheckStageStatus.PASS, details="ok")],
)
run = orchestrator.finalize_run(run)
assert run.final_status == CheckFinalStatus.FAILED
# [/DEF:test_orchestrator_missing_stage_result:Function]
# [DEF:test_orchestrator_report_generation_error:Function]
# @PURPOSE: Verify downstream report errors do not mutate orchestrator final status.
def test_orchestrator_report_generation_error():
repository = CleanReleaseRepository()
orchestrator = CleanComplianceOrchestrator(repository)
run = orchestrator.start_check_run("cand-1", "pol-1", "tester", "tui")
run = orchestrator.finalize_run(run)
assert run.final_status == CheckFinalStatus.FAILED
with patch.object(ComplianceReportBuilder, "build_report_payload", side_effect=ValueError("Report error")):
builder = ComplianceReportBuilder(repository)
with pytest.raises(ValueError, match="Report error"):
builder.build_report_payload(run, [])
assert run.final_status == CheckFinalStatus.FAILED
# [/DEF:test_orchestrator_report_generation_error:Function]
# [/DEF:backend.tests.services.clean_release.test_compliance_orchestrator:Module]

View File

@@ -0,0 +1,92 @@
# [DEF:backend.tests.services.clean_release.test_report_builder:Module]
# @TIER: STANDARD
# @SEMANTICS: tests, clean-release, report-builder, counters
# @PURPOSE: Validate compliance report builder counter integrity and blocked-run constraints.
# @LAYER: Domain
# @RELATION: TESTS -> backend.src.services.clean_release.report_builder
# @INVARIANT: blocked run requires at least one blocking violation.
from datetime import datetime, timezone
import pytest
from src.models.clean_release import (
CheckFinalStatus,
ComplianceCheckRun,
ComplianceViolation,
ExecutionMode,
ViolationCategory,
ViolationSeverity,
)
from src.services.clean_release.report_builder import ComplianceReportBuilder
from src.services.clean_release.repository import CleanReleaseRepository
# [DEF:_terminal_run:Function]
# @PURPOSE: Build terminal/non-terminal run fixtures for report builder tests.
def _terminal_run(status: CheckFinalStatus) -> ComplianceCheckRun:
return ComplianceCheckRun(
check_run_id="check-1",
candidate_id="2026.03.03-rc1",
policy_id="policy-enterprise-clean-v1",
started_at=datetime.now(timezone.utc),
finished_at=datetime.now(timezone.utc),
final_status=status,
triggered_by="tester",
execution_mode=ExecutionMode.TUI,
checks=[],
)
# [/DEF:_terminal_run:Function]
# [DEF:_blocking_violation:Function]
# @PURPOSE: Build a blocking violation fixture for blocked report scenarios.
def _blocking_violation() -> ComplianceViolation:
return ComplianceViolation(
violation_id="viol-1",
check_run_id="check-1",
category=ViolationCategory.EXTERNAL_SOURCE,
severity=ViolationSeverity.CRITICAL,
location="pypi.org",
remediation="replace",
blocked_release=True,
detected_at=datetime.now(timezone.utc),
)
# [/DEF:_blocking_violation:Function]
# [DEF:test_report_builder_blocked_requires_blocking_violations:Function]
# @PURPOSE: Verify BLOCKED run requires at least one blocking violation.
def test_report_builder_blocked_requires_blocking_violations():
builder = ComplianceReportBuilder(CleanReleaseRepository())
run = _terminal_run(CheckFinalStatus.BLOCKED)
with pytest.raises(ValueError):
builder.build_report_payload(run, [])
# [/DEF:test_report_builder_blocked_requires_blocking_violations:Function]
# [DEF:test_report_builder_counter_consistency:Function]
# @PURPOSE: Verify violations counters remain consistent for blocking payload.
def test_report_builder_counter_consistency():
builder = ComplianceReportBuilder(CleanReleaseRepository())
run = _terminal_run(CheckFinalStatus.BLOCKED)
report = builder.build_report_payload(run, [_blocking_violation()])
assert report.violations_count == 1
assert report.blocking_violations_count == 1
# [/DEF:test_report_builder_counter_consistency:Function]
# [DEF:test_missing_operator_summary:Function]
# @PURPOSE: Validate non-terminal run prevents operator summary/report generation.
def test_missing_operator_summary():
builder = ComplianceReportBuilder(CleanReleaseRepository())
run = _terminal_run(CheckFinalStatus.RUNNING)
with pytest.raises(ValueError) as exc:
builder.build_report_payload(run, [])
assert "Cannot build report for non-terminal run" in str(exc.value)
# [/DEF:test_missing_operator_summary:Function]
# [/DEF:backend.tests.services.clean_release.test_report_builder:Module]

View File

@@ -0,0 +1,24 @@
# [DEF:backend.src.services.clean_release.audit_service:Module]
# @TIER: STANDARD
# @SEMANTICS: clean-release, audit, lifecycle, logging
# @PURPOSE: Provide lightweight audit hooks for clean release preparation/check/report lifecycle.
# @LAYER: Infra
# @RELATION: DEPENDS_ON -> backend.src.core.logger
# @INVARIANT: Audit hooks are append-only log actions.
from __future__ import annotations
from ...core.logger import logger
def audit_preparation(candidate_id: str, status: str) -> None:
logger.info(f"[REASON] clean-release preparation candidate={candidate_id} status={status}")
def audit_check_run(check_run_id: str, final_status: str) -> None:
logger.info(f"[REFLECT] clean-release check_run={check_run_id} final_status={final_status}")
def audit_report(report_id: str, candidate_id: str) -> None:
logger.info(f"[EXPLORE] clean-release report_id={report_id} candidate={candidate_id}")
# [/DEF:backend.src.services.clean_release.audit_service:Module]

View File

@@ -0,0 +1,66 @@
# [DEF:backend.src.services.clean_release.compliance_orchestrator:Module]
# @TIER: CRITICAL
# @SEMANTICS: clean-release, orchestrator, compliance-gate, stages
# @PURPOSE: Execute mandatory clean compliance stages and produce final COMPLIANT/BLOCKED/FAILED outcome.
# @LAYER: Domain
# @RELATION: DEPENDS_ON -> backend.src.services.clean_release.stages
# @RELATION: DEPENDS_ON -> backend.src.services.clean_release.report_builder
# @RELATION: DEPENDS_ON -> backend.src.services.clean_release.repository
# @INVARIANT: COMPLIANT is impossible when any mandatory stage fails.
# @TEST_CONTRACT: ComplianceCheckRun -> ComplianceCheckRun
# @TEST_FIXTURE: compliant_candidate -> file:backend/tests/fixtures/clean_release/fixtures_clean_release.json
# @TEST_EDGE: stage_failure_blocks_release -> Mandatory stage returns FAIL and final status becomes BLOCKED
# @TEST_EDGE: missing_stage_result -> Finalization with incomplete/empty mandatory stage set must not produce COMPLIANT
# @TEST_EDGE: report_generation_error -> Downstream reporting failure does not alter orchestrator status derivation contract
# @TEST_INVARIANT: compliant_requires_all_mandatory_pass -> VERIFIED_BY: [stage_failure_blocks_release]
from __future__ import annotations
from datetime import datetime, timezone
from typing import List, Optional
from uuid import uuid4
from ...models.clean_release import (
CheckFinalStatus,
CheckStageName,
CheckStageResult,
CheckStageStatus,
ComplianceCheckRun,
)
from .repository import CleanReleaseRepository
from .stages import MANDATORY_STAGE_ORDER, derive_final_status
class CleanComplianceOrchestrator:
def __init__(self, repository: CleanReleaseRepository):
self.repository = repository
def start_check_run(self, candidate_id: str, policy_id: str, triggered_by: str, execution_mode: str) -> ComplianceCheckRun:
check_run = ComplianceCheckRun(
check_run_id=f"check-{uuid4()}",
candidate_id=candidate_id,
policy_id=policy_id,
started_at=datetime.now(timezone.utc),
final_status=CheckFinalStatus.RUNNING,
triggered_by=triggered_by,
execution_mode=execution_mode,
checks=[],
)
return self.repository.save_check_run(check_run)
def execute_stages(self, check_run: ComplianceCheckRun, forced_results: Optional[List[CheckStageResult]] = None) -> ComplianceCheckRun:
if forced_results is not None:
check_run.checks = forced_results
else:
check_run.checks = [
CheckStageResult(stage=stage, status=CheckStageStatus.PASS, details="auto-pass")
for stage in MANDATORY_STAGE_ORDER
]
return self.repository.save_check_run(check_run)
def finalize_run(self, check_run: ComplianceCheckRun) -> ComplianceCheckRun:
final_status = derive_final_status(check_run.checks)
check_run.final_status = final_status
check_run.finished_at = datetime.now(timezone.utc)
return self.repository.save_check_run(check_run)
# [/DEF:backend.src.services.clean_release.compliance_orchestrator:Module]

View File

@@ -0,0 +1,89 @@
# [DEF:backend.src.services.clean_release.manifest_builder:Module]
# @TIER: STANDARD
# @SEMANTICS: clean-release, manifest, deterministic-hash, summary
# @PURPOSE: Build deterministic distribution manifest from classified artifact input.
# @LAYER: Domain
# @RELATION: DEPENDS_ON -> backend.src.models.clean_release
# @INVARIANT: Equal semantic artifact sets produce identical deterministic hash values.
from __future__ import annotations
import hashlib
import json
from datetime import datetime, timezone
from typing import Iterable, List, Dict, Any
from ...models.clean_release import (
ClassificationType,
DistributionManifest,
ManifestItem,
ManifestSummary,
)
def _stable_hash_payload(candidate_id: str, policy_id: str, items: List[ManifestItem]) -> str:
serialized = [
{
"path": item.path,
"category": item.category,
"classification": item.classification.value,
"reason": item.reason,
"checksum": item.checksum,
}
for item in sorted(items, key=lambda i: (i.path, i.category, i.classification.value, i.reason, i.checksum or ""))
]
payload = {
"candidate_id": candidate_id,
"policy_id": policy_id,
"items": serialized,
}
digest = hashlib.sha256(json.dumps(payload, ensure_ascii=False, sort_keys=True).encode("utf-8")).hexdigest()
return digest
# [DEF:build_distribution_manifest:Function]
# @PURPOSE: Build DistributionManifest with deterministic hash and validated counters.
# @PRE: artifacts list contains normalized classification values.
# @POST: Returns DistributionManifest with summary counts matching items cardinality.
def build_distribution_manifest(
manifest_id: str,
candidate_id: str,
policy_id: str,
generated_by: str,
artifacts: Iterable[Dict[str, Any]],
) -> DistributionManifest:
items = [
ManifestItem(
path=a["path"],
category=a["category"],
classification=ClassificationType(a["classification"]),
reason=a["reason"],
checksum=a.get("checksum"),
)
for a in artifacts
]
included_count = sum(1 for item in items if item.classification in {ClassificationType.REQUIRED_SYSTEM, ClassificationType.ALLOWED})
excluded_count = sum(1 for item in items if item.classification == ClassificationType.EXCLUDED_PROHIBITED)
prohibited_detected_count = excluded_count
summary = ManifestSummary(
included_count=included_count,
excluded_count=excluded_count,
prohibited_detected_count=prohibited_detected_count,
)
deterministic_hash = _stable_hash_payload(candidate_id, policy_id, items)
return DistributionManifest(
manifest_id=manifest_id,
candidate_id=candidate_id,
policy_id=policy_id,
generated_at=datetime.now(timezone.utc),
generated_by=generated_by,
items=items,
summary=summary,
deterministic_hash=deterministic_hash,
)
# [/DEF:build_distribution_manifest:Function]
# [/DEF:backend.src.services.clean_release.manifest_builder:Module]

View File

@@ -0,0 +1,141 @@
# [DEF:backend.src.services.clean_release.policy_engine:Module]
# @TIER: CRITICAL
# @SEMANTICS: clean-release, policy, classification, source-isolation
# @PURPOSE: Evaluate artifact/source policies for enterprise clean profile with deterministic outcomes.
# @LAYER: Domain
# @RELATION: DEPENDS_ON -> backend.src.models.clean_release.CleanProfilePolicy
# @RELATION: DEPENDS_ON -> backend.src.models.clean_release.ResourceSourceRegistry
# @INVARIANT: Enterprise-clean policy always treats non-registry sources as violations.
from __future__ import annotations
from dataclasses import dataclass
from typing import Dict, Iterable, List, Tuple
from ...core.logger import belief_scope, logger
from ...models.clean_release import CleanProfilePolicy, ResourceSourceRegistry
@dataclass
class PolicyValidationResult:
ok: bool
blocking_reasons: List[str]
@dataclass
class SourceValidationResult:
ok: bool
violation: Dict | None
# [DEF:CleanPolicyEngine:Class]
# @PRE: Active policy exists and is internally consistent.
# @POST: Deterministic classification and source validation are available.
# @TEST_CONTRACT: CandidateEvaluationInput -> PolicyValidationResult|SourceValidationResult
# @TEST_SCENARIO: policy_valid -> Enterprise clean policy with matching registry returns ok=True
# @TEST_FIXTURE: policy_enterprise_clean -> file:backend/tests/fixtures/clean_release/fixtures_clean_release.json
# @TEST_EDGE: missing_registry_ref -> policy has empty internal_source_registry_ref
# @TEST_EDGE: conflicting_registry -> policy registry ref does not match registry id
# @TEST_EDGE: external_endpoint -> endpoint not present in enabled internal registry entries
# @TEST_INVARIANT: deterministic_classification -> VERIFIED_BY: [policy_valid]
class CleanPolicyEngine:
def __init__(self, policy: CleanProfilePolicy, registry: ResourceSourceRegistry):
self.policy = policy
self.registry = registry
def validate_policy(self) -> PolicyValidationResult:
with belief_scope("clean_policy_engine.validate_policy"):
logger.reason("Validating enterprise-clean policy and internal registry consistency")
reasons: List[str] = []
if not self.policy.active:
reasons.append("Policy must be active")
if not self.policy.internal_source_registry_ref.strip():
reasons.append("Policy missing internal_source_registry_ref")
if self.policy.profile.value == "enterprise-clean" and not self.policy.prohibited_artifact_categories:
reasons.append("Enterprise policy requires prohibited artifact categories")
if self.policy.profile.value == "enterprise-clean" and not self.policy.external_source_forbidden:
reasons.append("Enterprise policy requires external_source_forbidden=true")
if self.registry.registry_id != self.policy.internal_source_registry_ref:
reasons.append("Policy registry ref does not match provided registry")
if not self.registry.entries:
reasons.append("Registry must contain entries")
logger.reflect(f"Policy validation completed. blocking_reasons={len(reasons)}")
return PolicyValidationResult(ok=len(reasons) == 0, blocking_reasons=reasons)
def classify_artifact(self, artifact: Dict) -> str:
category = (artifact.get("category") or "").strip()
if category in self.policy.required_system_categories:
logger.reason(f"Artifact category '{category}' classified as required-system")
return "required-system"
if category in self.policy.prohibited_artifact_categories:
logger.reason(f"Artifact category '{category}' classified as excluded-prohibited")
return "excluded-prohibited"
logger.reflect(f"Artifact category '{category}' classified as allowed")
return "allowed"
def validate_resource_source(self, endpoint: str) -> SourceValidationResult:
with belief_scope("clean_policy_engine.validate_resource_source"):
if not endpoint:
logger.explore("Empty endpoint detected; treating as blocking external-source violation")
return SourceValidationResult(
ok=False,
violation={
"category": "external-source",
"location": "<empty-endpoint>",
"remediation": "Replace with approved internal server",
"blocked_release": True,
},
)
allowed_hosts = {entry.host for entry in self.registry.entries if entry.enabled}
normalized = endpoint.strip().lower()
if normalized in allowed_hosts:
logger.reason(f"Endpoint '{normalized}' is present in internal allowlist")
return SourceValidationResult(ok=True, violation=None)
logger.explore(f"Endpoint '{endpoint}' is outside internal allowlist")
return SourceValidationResult(
ok=False,
violation={
"category": "external-source",
"location": endpoint,
"remediation": "Replace with approved internal server",
"blocked_release": True,
},
)
def evaluate_candidate(self, artifacts: Iterable[Dict], sources: Iterable[str]) -> Tuple[List[Dict], List[Dict]]:
with belief_scope("clean_policy_engine.evaluate_candidate"):
logger.reason("Evaluating candidate artifacts and resource sources against enterprise policy")
classified: List[Dict] = []
violations: List[Dict] = []
for artifact in artifacts:
classification = self.classify_artifact(artifact)
enriched = dict(artifact)
enriched["classification"] = classification
if classification == "excluded-prohibited":
violations.append(
{
"category": "data-purity",
"location": artifact.get("path", "<unknown-path>"),
"remediation": "Remove prohibited content",
"blocked_release": True,
}
)
classified.append(enriched)
for source in sources:
source_result = self.validate_resource_source(source)
if not source_result.ok and source_result.violation:
violations.append(source_result.violation)
logger.reflect(
f"Candidate evaluation finished. artifacts={len(classified)} violations={len(violations)}"
)
return classified, violations
# [/DEF:CleanPolicyEngine:Class]
# [/DEF:backend.src.services.clean_release.policy_engine:Module]

View File

@@ -0,0 +1,67 @@
# [DEF:backend.src.services.clean_release.preparation_service:Module]
# @TIER: STANDARD
# @SEMANTICS: clean-release, preparation, manifest, policy-evaluation
# @PURPOSE: Prepare release candidate by policy evaluation and deterministic manifest creation.
# @LAYER: Domain
# @RELATION: DEPENDS_ON -> backend.src.services.clean_release.policy_engine
# @RELATION: DEPENDS_ON -> backend.src.services.clean_release.manifest_builder
# @RELATION: DEPENDS_ON -> backend.src.services.clean_release.repository
# @INVARIANT: Candidate preparation always persists manifest and candidate status deterministically.
from __future__ import annotations
from datetime import datetime, timezone
from typing import Dict, Iterable
from .manifest_builder import build_distribution_manifest
from .policy_engine import CleanPolicyEngine
from .repository import CleanReleaseRepository
from ...models.clean_release import ReleaseCandidateStatus
def prepare_candidate(
repository: CleanReleaseRepository,
candidate_id: str,
artifacts: Iterable[Dict],
sources: Iterable[str],
operator_id: str,
) -> Dict:
candidate = repository.get_candidate(candidate_id)
if candidate is None:
raise ValueError(f"Candidate not found: {candidate_id}")
policy = repository.get_active_policy()
if policy is None:
raise ValueError("Active clean policy not found")
registry = repository.get_registry(policy.internal_source_registry_ref)
if registry is None:
raise ValueError("Registry not found for active policy")
engine = CleanPolicyEngine(policy=policy, registry=registry)
validation = engine.validate_policy()
if not validation.ok:
raise ValueError(f"Invalid policy: {validation.blocking_reasons}")
classified, violations = engine.evaluate_candidate(artifacts=artifacts, sources=sources)
manifest = build_distribution_manifest(
manifest_id=f"manifest-{candidate_id}",
candidate_id=candidate_id,
policy_id=policy.policy_id,
generated_by=operator_id,
artifacts=classified,
)
repository.save_manifest(manifest)
candidate.status = ReleaseCandidateStatus.BLOCKED if violations else ReleaseCandidateStatus.PREPARED
repository.save_candidate(candidate)
return {
"candidate_id": candidate_id,
"status": candidate.status.value,
"manifest_id": manifest.manifest_id,
"violations": violations,
"prepared_at": datetime.now(timezone.utc).isoformat(),
}
# [/DEF:backend.src.services.clean_release.preparation_service:Module]

View File

@@ -0,0 +1,60 @@
# [DEF:backend.src.services.clean_release.report_builder:Module]
# @TIER: CRITICAL
# @SEMANTICS: clean-release, report, audit, counters, violations
# @PURPOSE: Build and persist compliance reports with consistent counter invariants.
# @LAYER: Domain
# @RELATION: DEPENDS_ON -> backend.src.models.clean_release
# @RELATION: DEPENDS_ON -> backend.src.services.clean_release.repository
# @INVARIANT: blocking_violations_count never exceeds violations_count.
# @TEST_CONTRACT: ComplianceCheckRun,List[ComplianceViolation] -> ComplianceReport
# @TEST_FIXTURE: blocked_with_two_violations -> file:backend/tests/fixtures/clean_release/fixtures_clean_release.json
# @TEST_EDGE: empty_violations_for_blocked -> BLOCKED run with zero blocking violations raises ValueError
# @TEST_EDGE: counter_mismatch -> blocking counter cannot exceed total violations counter
# @TEST_EDGE: missing_operator_summary -> non-terminal run prevents report creation and summary generation
# @TEST_INVARIANT: blocking_count_le_total_count -> VERIFIED_BY: [counter_mismatch, empty_violations_for_blocked]
from __future__ import annotations
from datetime import datetime, timezone
from uuid import uuid4
from typing import List
from ...models.clean_release import CheckFinalStatus, ComplianceCheckRun, ComplianceReport, ComplianceViolation
from .repository import CleanReleaseRepository
class ComplianceReportBuilder:
def __init__(self, repository: CleanReleaseRepository):
self.repository = repository
def build_report_payload(self, check_run: ComplianceCheckRun, violations: List[ComplianceViolation]) -> ComplianceReport:
if check_run.final_status == CheckFinalStatus.RUNNING:
raise ValueError("Cannot build report for non-terminal run")
violations_count = len(violations)
blocking_violations_count = sum(1 for v in violations if v.blocked_release)
if check_run.final_status == CheckFinalStatus.BLOCKED and blocking_violations_count <= 0:
raise ValueError("Blocked run requires at least one blocking violation")
summary = (
"Compliance passed with no blocking violations"
if check_run.final_status == CheckFinalStatus.COMPLIANT
else f"Blocked with {blocking_violations_count} blocking violation(s)"
)
return ComplianceReport(
report_id=f"CCR-{uuid4()}",
check_run_id=check_run.check_run_id,
candidate_id=check_run.candidate_id,
generated_at=datetime.now(timezone.utc),
final_status=check_run.final_status,
operator_summary=summary,
structured_payload_ref=f"inmemory://check-runs/{check_run.check_run_id}/report",
violations_count=violations_count,
blocking_violations_count=blocking_violations_count,
)
def persist_report(self, report: ComplianceReport) -> ComplianceReport:
return self.repository.save_report(report)
# [/DEF:backend.src.services.clean_release.report_builder:Module]

View File

@@ -0,0 +1,89 @@
# [DEF:backend.src.services.clean_release.repository:Module]
# @TIER: STANDARD
# @SEMANTICS: clean-release, repository, persistence, in-memory
# @PURPOSE: Provide repository adapter for clean release entities with deterministic access methods.
# @LAYER: Infra
# @RELATION: DEPENDS_ON -> backend.src.models.clean_release
# @INVARIANT: Repository operations are side-effect free outside explicit save/update calls.
from __future__ import annotations
from dataclasses import dataclass, field
from typing import Dict, List, Optional
from ...models.clean_release import (
CleanProfilePolicy,
ComplianceCheckRun,
ComplianceReport,
ComplianceViolation,
DistributionManifest,
ReleaseCandidate,
ResourceSourceRegistry,
)
@dataclass
class CleanReleaseRepository:
candidates: Dict[str, ReleaseCandidate] = field(default_factory=dict)
policies: Dict[str, CleanProfilePolicy] = field(default_factory=dict)
registries: Dict[str, ResourceSourceRegistry] = field(default_factory=dict)
manifests: Dict[str, DistributionManifest] = field(default_factory=dict)
check_runs: Dict[str, ComplianceCheckRun] = field(default_factory=dict)
reports: Dict[str, ComplianceReport] = field(default_factory=dict)
violations: Dict[str, ComplianceViolation] = field(default_factory=dict)
def save_candidate(self, candidate: ReleaseCandidate) -> ReleaseCandidate:
self.candidates[candidate.candidate_id] = candidate
return candidate
def get_candidate(self, candidate_id: str) -> Optional[ReleaseCandidate]:
return self.candidates.get(candidate_id)
def save_policy(self, policy: CleanProfilePolicy) -> CleanProfilePolicy:
self.policies[policy.policy_id] = policy
return policy
def get_policy(self, policy_id: str) -> Optional[CleanProfilePolicy]:
return self.policies.get(policy_id)
def get_active_policy(self) -> Optional[CleanProfilePolicy]:
for policy in self.policies.values():
if policy.active:
return policy
return None
def save_registry(self, registry: ResourceSourceRegistry) -> ResourceSourceRegistry:
self.registries[registry.registry_id] = registry
return registry
def get_registry(self, registry_id: str) -> Optional[ResourceSourceRegistry]:
return self.registries.get(registry_id)
def save_manifest(self, manifest: DistributionManifest) -> DistributionManifest:
self.manifests[manifest.manifest_id] = manifest
return manifest
def get_manifest(self, manifest_id: str) -> Optional[DistributionManifest]:
return self.manifests.get(manifest_id)
def save_check_run(self, check_run: ComplianceCheckRun) -> ComplianceCheckRun:
self.check_runs[check_run.check_run_id] = check_run
return check_run
def get_check_run(self, check_run_id: str) -> Optional[ComplianceCheckRun]:
return self.check_runs.get(check_run_id)
def save_report(self, report: ComplianceReport) -> ComplianceReport:
self.reports[report.report_id] = report
return report
def get_report(self, report_id: str) -> Optional[ComplianceReport]:
return self.reports.get(report_id)
def save_violation(self, violation: ComplianceViolation) -> ComplianceViolation:
self.violations[violation.violation_id] = violation
return violation
def get_violations_by_check_run(self, check_run_id: str) -> List[ComplianceViolation]:
return [v for v in self.violations.values() if v.check_run_id == check_run_id]
# [/DEF:backend.src.services.clean_release.repository:Module]

View File

@@ -0,0 +1,33 @@
# [DEF:backend.src.services.clean_release.source_isolation:Module]
# @TIER: STANDARD
# @SEMANTICS: clean-release, source-isolation, internal-only, validation
# @PURPOSE: Validate that all resource endpoints belong to the approved internal source registry.
# @LAYER: Domain
# @RELATION: DEPENDS_ON -> backend.src.models.clean_release.ResourceSourceRegistry
# @INVARIANT: Any endpoint outside enabled registry entries is treated as external-source violation.
from __future__ import annotations
from typing import Dict, Iterable, List
from ...models.clean_release import ResourceSourceRegistry
def validate_internal_sources(registry: ResourceSourceRegistry, endpoints: Iterable[str]) -> Dict:
allowed_hosts = {entry.host.strip().lower() for entry in registry.entries if entry.enabled}
violations: List[Dict] = []
for endpoint in endpoints:
normalized = (endpoint or "").strip().lower()
if not normalized or normalized not in allowed_hosts:
violations.append(
{
"category": "external-source",
"location": endpoint or "<empty-endpoint>",
"remediation": "Replace with approved internal server",
"blocked_release": True,
}
)
return {"ok": len(violations) == 0, "violations": violations}
# [/DEF:backend.src.services.clean_release.source_isolation:Module]

View File

@@ -0,0 +1,59 @@
# [DEF:backend.src.services.clean_release.stages:Module]
# @TIER: STANDARD
# @SEMANTICS: clean-release, compliance, stages, state-machine
# @PURPOSE: Define compliance stage order and helper functions for deterministic run-state evaluation.
# @LAYER: Domain
# @RELATION: DEPENDS_ON -> backend.src.models.clean_release
# @INVARIANT: Stage order remains deterministic for all compliance runs.
from __future__ import annotations
from typing import Dict, Iterable, List
from ...models.clean_release import CheckFinalStatus, CheckStageName, CheckStageResult, CheckStageStatus
MANDATORY_STAGE_ORDER: List[CheckStageName] = [
CheckStageName.DATA_PURITY,
CheckStageName.INTERNAL_SOURCES_ONLY,
CheckStageName.NO_EXTERNAL_ENDPOINTS,
CheckStageName.MANIFEST_CONSISTENCY,
]
# [DEF:stage_result_map:Function]
# @PURPOSE: Convert stage result list to dictionary by stage name.
# @PRE: stage_results may be empty or contain unique stage names.
# @POST: Returns stage->status dictionary for downstream evaluation.
def stage_result_map(stage_results: Iterable[CheckStageResult]) -> Dict[CheckStageName, CheckStageStatus]:
return {result.stage: result.status for result in stage_results}
# [/DEF:stage_result_map:Function]
# [DEF:missing_mandatory_stages:Function]
# @PURPOSE: Identify mandatory stages that are absent from run results.
# @PRE: stage_status_map contains zero or more known stage statuses.
# @POST: Returns ordered list of missing mandatory stages.
def missing_mandatory_stages(stage_status_map: Dict[CheckStageName, CheckStageStatus]) -> List[CheckStageName]:
return [stage for stage in MANDATORY_STAGE_ORDER if stage not in stage_status_map]
# [/DEF:missing_mandatory_stages:Function]
# [DEF:derive_final_status:Function]
# @PURPOSE: Derive final run status from stage results with deterministic blocking behavior.
# @PRE: Stage statuses correspond to compliance checks.
# @POST: Returns one of COMPLIANT/BLOCKED/FAILED according to mandatory stage outcomes.
def derive_final_status(stage_results: Iterable[CheckStageResult]) -> CheckFinalStatus:
status_map = stage_result_map(stage_results)
missing = missing_mandatory_stages(status_map)
if missing:
return CheckFinalStatus.FAILED
for stage in MANDATORY_STAGE_ORDER:
if status_map.get(stage) == CheckStageStatus.FAIL:
return CheckFinalStatus.BLOCKED
if status_map.get(stage) == CheckStageStatus.SKIPPED:
return CheckFinalStatus.FAILED
return CheckFinalStatus.COMPLIANT
# [/DEF:derive_final_status:Function]
# [/DEF:backend.src.services.clean_release.stages:Module]

View File

@@ -1,22 +1,33 @@
# [DEF:backend.src.services.git_service:Module]
#
# @TIER: STANDARD
# @SEMANTICS: git, service, gitpython, repository, version_control
# @PURPOSE: Core Git logic using GitPython to manage dashboard repositories.
# @LAYER: Service
# @RELATION: INHERITS_FROM -> None
# @RELATION: USED_BY -> src.api.routes.git
# @RELATION: USED_BY -> src.plugins.git_plugin
# @RELATION: DEPENDS_ON -> src.core.database.SessionLocal
# @RELATION: DEPENDS_ON -> src.models.config.AppConfigRecord
# @RELATION: DEPENDS_ON -> src.models.git.GitRepository
#
# @INVARIANT: All Git operations must be performed on a valid local directory.
import os
import httpx
import re
import shutil
from git import Repo
from fastapi import HTTPException
from typing import List
from typing import Any, Dict, List, Optional
from datetime import datetime
from pathlib import Path
from urllib.parse import quote, urlparse
from src.core.logger import logger, belief_scope
from src.models.git import GitProvider
from src.models.git import GitRepository
from src.models.config import AppConfigRecord
from src.core.database import SessionLocal
# [DEF:GitService:Class]
# @PURPOSE: Wrapper for GitPython operations with semantic logging and error handling.
@@ -32,28 +43,164 @@ class GitService:
# @POST: GitService is initialized; base_path directory exists.
def __init__(self, base_path: str = "git_repos"):
with belief_scope("GitService.__init__"):
# Resolve relative to the backend directory
# Path(__file__) is backend/src/services/git_service.py
# parents[2] is backend/
from pathlib import Path
backend_root = Path(__file__).parents[2]
self.base_path = str((backend_root / base_path).resolve())
self.legacy_base_path = str((backend_root / "git_repos").resolve())
self.base_path = self._resolve_base_path(base_path)
if not os.path.exists(self.base_path):
os.makedirs(self.base_path)
# [/DEF:__init__:Function]
# [DEF:_resolve_base_path:Function]
# @PURPOSE: Resolve base repository directory from explicit argument or global storage settings.
# @PRE: base_path is a string path.
# @POST: Returns absolute path for Git repositories root.
# @RETURN: str
def _resolve_base_path(self, base_path: str) -> str:
# Resolve relative to backend directory for backward compatibility.
backend_root = Path(__file__).parents[2]
fallback_path = str((backend_root / base_path).resolve())
if base_path != "git_repos":
return fallback_path
try:
session = SessionLocal()
try:
config_row = session.query(AppConfigRecord).filter(AppConfigRecord.id == "global").first()
finally:
session.close()
payload = (config_row.payload if config_row and config_row.payload else {}) if config_row else {}
storage_cfg = payload.get("settings", {}).get("storage", {}) if isinstance(payload, dict) else {}
root_path = str(storage_cfg.get("root_path", "")).strip()
repo_path = str(storage_cfg.get("repo_path", "")).strip()
if not root_path:
return fallback_path
project_root = Path(__file__).parents[3]
root = Path(root_path)
if not root.is_absolute():
root = (project_root / root).resolve()
repo_root = Path(repo_path) if repo_path else Path("repositorys")
if repo_root.is_absolute():
return str(repo_root.resolve())
return str((root / repo_root).resolve())
except Exception as e:
logger.warning(f"[_resolve_base_path][Coherence:Failed] Falling back to default path: {e}")
return fallback_path
# [/DEF:_resolve_base_path:Function]
# [DEF:_normalize_repo_key:Function]
# @PURPOSE: Convert user/dashboard-provided key to safe filesystem directory name.
# @PRE: repo_key can be None/empty.
# @POST: Returns normalized non-empty key.
# @RETURN: str
def _normalize_repo_key(self, repo_key: Optional[str]) -> str:
raw_key = str(repo_key or "").strip().lower()
normalized = re.sub(r"[^a-z0-9._-]+", "-", raw_key).strip("._-")
return normalized or "dashboard"
# [/DEF:_normalize_repo_key:Function]
# [DEF:_update_repo_local_path:Function]
# @PURPOSE: Persist repository local_path in GitRepository table when record exists.
# @PRE: dashboard_id is valid integer.
# @POST: local_path is updated for existing record.
# @RETURN: None
def _update_repo_local_path(self, dashboard_id: int, local_path: str) -> None:
try:
session = SessionLocal()
try:
db_repo = (
session.query(GitRepository)
.filter(GitRepository.dashboard_id == int(dashboard_id))
.first()
)
if db_repo:
db_repo.local_path = local_path
session.commit()
finally:
session.close()
except Exception as e:
logger.warning(f"[_update_repo_local_path][Coherence:Failed] {e}")
# [/DEF:_update_repo_local_path:Function]
# [DEF:_migrate_repo_directory:Function]
# @PURPOSE: Move legacy repository directory to target path and sync DB metadata.
# @PRE: source_path exists.
# @POST: Repository content available at target_path.
# @RETURN: str
def _migrate_repo_directory(self, dashboard_id: int, source_path: str, target_path: str) -> str:
source_abs = os.path.abspath(source_path)
target_abs = os.path.abspath(target_path)
if source_abs == target_abs:
return source_abs
if os.path.exists(target_abs):
logger.warning(
f"[_migrate_repo_directory][Action] Target already exists, keeping source path: {target_abs}"
)
return source_abs
Path(target_abs).parent.mkdir(parents=True, exist_ok=True)
try:
os.replace(source_abs, target_abs)
except OSError:
shutil.move(source_abs, target_abs)
self._update_repo_local_path(dashboard_id, target_abs)
logger.info(
f"[_migrate_repo_directory][Coherence:OK] Repository migrated for dashboard {dashboard_id}: {source_abs} -> {target_abs}"
)
return target_abs
# [/DEF:_migrate_repo_directory:Function]
# [DEF:_get_repo_path:Function]
# @PURPOSE: Resolves the local filesystem path for a dashboard's repository.
# @PARAM: dashboard_id (int)
# @PARAM: repo_key (Optional[str]) - Slug-like key used when DB local_path is absent.
# @PRE: dashboard_id is an integer.
# @POST: Returns the absolute or relative path to the dashboard's repo.
# @POST: Returns DB-local_path when present, otherwise base_path/<normalized repo_key>.
# @RETURN: str
def _get_repo_path(self, dashboard_id: int) -> str:
def _get_repo_path(self, dashboard_id: int, repo_key: Optional[str] = None) -> str:
with belief_scope("GitService._get_repo_path"):
if dashboard_id is None:
raise ValueError("dashboard_id cannot be None")
return os.path.join(self.base_path, str(dashboard_id))
fallback_key = repo_key if repo_key is not None else str(dashboard_id)
normalized_key = self._normalize_repo_key(fallback_key)
target_path = os.path.join(self.base_path, normalized_key)
try:
session = SessionLocal()
try:
db_repo = (
session.query(GitRepository)
.filter(GitRepository.dashboard_id == int(dashboard_id))
.first()
)
finally:
session.close()
if db_repo and db_repo.local_path:
db_path = os.path.abspath(db_repo.local_path)
if os.path.exists(db_path):
if (
os.path.abspath(self.base_path) != os.path.abspath(self.legacy_base_path)
and db_path.startswith(os.path.abspath(self.legacy_base_path) + os.sep)
):
return self._migrate_repo_directory(dashboard_id, db_path, target_path)
return db_path
except Exception as e:
logger.warning(f"[_get_repo_path][Coherence:Failed] Could not resolve local_path from DB: {e}")
legacy_id_path = os.path.join(self.legacy_base_path, str(dashboard_id))
if os.path.exists(legacy_id_path) and not os.path.exists(target_path):
return self._migrate_repo_directory(dashboard_id, legacy_id_path, target_path)
if os.path.exists(target_path):
self._update_repo_local_path(dashboard_id, target_path)
return target_path
# [/DEF:_get_repo_path:Function]
# [DEF:init_repo:Function]
@@ -61,12 +208,14 @@ class GitService:
# @PARAM: dashboard_id (int)
# @PARAM: remote_url (str)
# @PARAM: pat (str) - Personal Access Token for authentication.
# @PARAM: repo_key (Optional[str]) - Slug-like key for deterministic folder naming on first init.
# @PRE: dashboard_id is int, remote_url is valid Git URL, pat is provided.
# @POST: Repository is cloned or opened at the local path.
# @RETURN: Repo - GitPython Repo object.
def init_repo(self, dashboard_id: int, remote_url: str, pat: str) -> Repo:
def init_repo(self, dashboard_id: int, remote_url: str, pat: str, repo_key: Optional[str] = None) -> Repo:
with belief_scope("GitService.init_repo"):
repo_path = self._get_repo_path(dashboard_id)
repo_path = self._get_repo_path(dashboard_id, repo_key=repo_key or str(dashboard_id))
Path(repo_path).parent.mkdir(parents=True, exist_ok=True)
# Inject PAT into remote URL if needed
if pat and "://" in remote_url:
@@ -251,12 +400,21 @@ class GitService:
try:
current_branch = repo.active_branch
logger.info(f"[push_changes][Action] Pushing branch {current_branch.name} to origin")
# Using a timeout for network operations
push_info = origin.push(refspec=f'{current_branch.name}:{current_branch.name}')
for info in push_info:
if info.flags & info.ERROR:
logger.error(f"[push_changes][Coherence:Failed] Error pushing ref {info.remote_ref_string}: {info.summary}")
raise Exception(f"Git push error for {info.remote_ref_string}: {info.summary}")
tracking_branch = None
try:
tracking_branch = current_branch.tracking_branch()
except Exception:
tracking_branch = None
# First push for a new branch must set upstream, otherwise future pull fails.
if tracking_branch is None:
repo.git.push("--set-upstream", "origin", f"{current_branch.name}:{current_branch.name}")
else:
push_info = origin.push(refspec=f'{current_branch.name}:{current_branch.name}')
for info in push_info:
if info.flags & info.ERROR:
logger.error(f"[push_changes][Coherence:Failed] Error pushing ref {info.remote_ref_string}: {info.summary}")
raise Exception(f"Git push error for {info.remote_ref_string}: {info.summary}")
except Exception as e:
logger.error(f"[push_changes][Coherence:Failed] Failed to push changes: {e}")
raise HTTPException(status_code=500, detail=f"Git push failed: {str(e)}")
@@ -271,8 +429,17 @@ class GitService:
repo = self.get_repo(dashboard_id)
try:
origin = repo.remote(name='origin')
logger.info("[pull_changes][Action] Pulling changes from origin")
fetch_info = origin.pull()
current_branch = repo.active_branch.name
remote_ref = f"origin/{current_branch}"
has_remote_branch = any(ref.name == remote_ref for ref in repo.refs)
if not has_remote_branch:
raise HTTPException(
status_code=409,
detail=f"Remote branch '{current_branch}' does not exist yet. Push this branch first.",
)
logger.info(f"[pull_changes][Action] Pulling changes from origin/{current_branch}")
fetch_info = origin.pull(current_branch)
for info in fetch_info:
if info.flags & info.ERROR:
logger.error(f"[pull_changes][Coherence:Failed] Error pulling ref {info.ref}: {info.note}")
@@ -280,6 +447,8 @@ class GitService:
except ValueError:
logger.error(f"[pull_changes][Coherence:Failed] Remote 'origin' not found for dashboard {dashboard_id}")
raise HTTPException(status_code=400, detail="Remote 'origin' not configured")
except HTTPException:
raise
except Exception as e:
logger.error(f"[pull_changes][Coherence:Failed] Failed to pull changes: {e}")
raise HTTPException(status_code=500, detail=f"Git pull failed: {str(e)}")
@@ -302,12 +471,62 @@ class GitService:
except (ValueError, Exception):
has_commits = False
current_branch = repo.active_branch.name
tracking_branch = None
has_upstream = False
ahead_count = 0
behind_count = 0
try:
tracking_branch = repo.active_branch.tracking_branch()
has_upstream = tracking_branch is not None
except Exception:
tracking_branch = None
has_upstream = False
if has_upstream and tracking_branch is not None:
try:
# Commits present locally but not in upstream.
ahead_count = sum(
1 for _ in repo.iter_commits(f"{tracking_branch.name}..{current_branch}")
)
# Commits present in upstream but not local.
behind_count = sum(
1 for _ in repo.iter_commits(f"{current_branch}..{tracking_branch.name}")
)
except Exception:
ahead_count = 0
behind_count = 0
is_dirty = repo.is_dirty(untracked_files=True)
untracked_files = repo.untracked_files
modified_files = [item.a_path for item in repo.index.diff(None)]
staged_files = [item.a_path for item in repo.index.diff("HEAD")] if has_commits else []
is_diverged = ahead_count > 0 and behind_count > 0
if is_diverged:
sync_state = "DIVERGED"
elif behind_count > 0:
sync_state = "BEHIND_REMOTE"
elif ahead_count > 0:
sync_state = "AHEAD_REMOTE"
elif is_dirty or modified_files or staged_files or untracked_files:
sync_state = "CHANGES"
else:
sync_state = "SYNCED"
return {
"is_dirty": repo.is_dirty(untracked_files=True),
"untracked_files": repo.untracked_files,
"modified_files": [item.a_path for item in repo.index.diff(None)],
"staged_files": [item.a_path for item in repo.index.diff("HEAD")] if has_commits else [],
"current_branch": repo.active_branch.name
"is_dirty": is_dirty,
"untracked_files": untracked_files,
"modified_files": modified_files,
"staged_files": staged_files,
"current_branch": current_branch,
"upstream_branch": tracking_branch.name if tracking_branch is not None else None,
"has_upstream": has_upstream,
"ahead_count": ahead_count,
"behind_count": behind_count,
"is_diverged": is_diverged,
"sync_state": sync_state,
}
# [/DEF:get_status:Function]
@@ -410,5 +629,565 @@ class GitService:
return False
# [/DEF:test_connection:Function]
# [DEF:_normalize_git_server_url:Function]
# @PURPOSE: Normalize Git server URL for provider API calls.
# @PRE: raw_url is non-empty.
# @POST: Returns URL without trailing slash.
# @RETURN: str
def _normalize_git_server_url(self, raw_url: str) -> str:
normalized = (raw_url or "").strip()
if not normalized:
raise HTTPException(status_code=400, detail="Git server URL is required")
return normalized.rstrip("/")
# [/DEF:_normalize_git_server_url:Function]
# [DEF:_gitea_headers:Function]
# @PURPOSE: Build Gitea API authorization headers.
# @PRE: pat is provided.
# @POST: Returns headers with token auth.
# @RETURN: Dict[str, str]
def _gitea_headers(self, pat: str) -> Dict[str, str]:
token = (pat or "").strip()
if not token:
raise HTTPException(status_code=400, detail="Git PAT is required for Gitea operations")
return {
"Authorization": f"token {token}",
"Content-Type": "application/json",
"Accept": "application/json",
}
# [/DEF:_gitea_headers:Function]
# [DEF:_gitea_request:Function]
# @PURPOSE: Execute HTTP request against Gitea API with stable error mapping.
# @PRE: method and endpoint are valid.
# @POST: Returns decoded JSON payload.
# @RETURN: Any
async def _gitea_request(
self,
method: str,
server_url: str,
pat: str,
endpoint: str,
payload: Optional[Dict[str, Any]] = None,
) -> Any:
base_url = self._normalize_git_server_url(server_url)
url = f"{base_url}/api/v1{endpoint}"
headers = self._gitea_headers(pat)
try:
async with httpx.AsyncClient(timeout=20.0) as client:
response = await client.request(
method=method,
url=url,
headers=headers,
json=payload,
)
except Exception as e:
logger.error(f"[gitea_request][Coherence:Failed] Network error: {e}")
raise HTTPException(status_code=503, detail=f"Gitea API is unavailable: {str(e)}")
if response.status_code >= 400:
detail = response.text
try:
parsed = response.json()
detail = parsed.get("message") or parsed.get("error") or detail
except Exception:
pass
logger.error(
f"[gitea_request][Coherence:Failed] method={method} endpoint={endpoint} status={response.status_code} detail={detail}"
)
raise HTTPException(
status_code=response.status_code,
detail=f"Gitea API error: {detail}",
)
if response.status_code == 204:
return None
return response.json()
# [/DEF:_gitea_request:Function]
# [DEF:get_gitea_current_user:Function]
# @PURPOSE: Resolve current Gitea user for PAT.
# @PRE: server_url and pat are valid.
# @POST: Returns current username.
# @RETURN: str
async def get_gitea_current_user(self, server_url: str, pat: str) -> str:
payload = await self._gitea_request("GET", server_url, pat, "/user")
username = payload.get("login") or payload.get("username")
if not username:
raise HTTPException(status_code=500, detail="Failed to resolve Gitea username")
return str(username)
# [/DEF:get_gitea_current_user:Function]
# [DEF:list_gitea_repositories:Function]
# @PURPOSE: List repositories visible to authenticated Gitea user.
# @PRE: server_url and pat are valid.
# @POST: Returns repository list from Gitea.
# @RETURN: List[dict]
async def list_gitea_repositories(self, server_url: str, pat: str) -> List[dict]:
payload = await self._gitea_request(
"GET",
server_url,
pat,
"/user/repos?limit=100&page=1",
)
if not isinstance(payload, list):
return []
return payload
# [/DEF:list_gitea_repositories:Function]
# [DEF:create_gitea_repository:Function]
# @PURPOSE: Create repository in Gitea for authenticated user.
# @PRE: name is non-empty and PAT has repo creation permission.
# @POST: Returns created repository payload.
# @RETURN: dict
async def create_gitea_repository(
self,
server_url: str,
pat: str,
name: str,
private: bool = True,
description: Optional[str] = None,
auto_init: bool = True,
default_branch: Optional[str] = "main",
) -> Dict[str, Any]:
payload = {
"name": name,
"private": bool(private),
"auto_init": bool(auto_init),
}
if description:
payload["description"] = description
if default_branch:
payload["default_branch"] = default_branch
created = await self._gitea_request(
"POST",
server_url,
pat,
"/user/repos",
payload=payload,
)
if not isinstance(created, dict):
raise HTTPException(status_code=500, detail="Unexpected Gitea response while creating repository")
return created
# [/DEF:create_gitea_repository:Function]
# [DEF:delete_gitea_repository:Function]
# @PURPOSE: Delete repository in Gitea.
# @PRE: owner and repo_name are non-empty.
# @POST: Repository deleted on Gitea server.
async def delete_gitea_repository(
self,
server_url: str,
pat: str,
owner: str,
repo_name: str,
) -> None:
if not owner or not repo_name:
raise HTTPException(status_code=400, detail="owner and repo_name are required")
await self._gitea_request(
"DELETE",
server_url,
pat,
f"/repos/{owner}/{repo_name}",
)
# [/DEF:delete_gitea_repository:Function]
# [DEF:create_github_repository:Function]
# @PURPOSE: Create repository in GitHub or GitHub Enterprise.
# @PRE: PAT has repository create permission.
# @POST: Returns created repository payload.
# @RETURN: dict
async def create_github_repository(
self,
server_url: str,
pat: str,
name: str,
private: bool = True,
description: Optional[str] = None,
auto_init: bool = True,
default_branch: Optional[str] = "main",
) -> Dict[str, Any]:
base_url = self._normalize_git_server_url(server_url)
if "github.com" in base_url:
api_url = "https://api.github.com/user/repos"
else:
api_url = f"{base_url}/api/v3/user/repos"
headers = {
"Authorization": f"token {pat.strip()}",
"Content-Type": "application/json",
"Accept": "application/vnd.github+json",
}
payload: Dict[str, Any] = {
"name": name,
"private": bool(private),
"auto_init": bool(auto_init),
}
if description:
payload["description"] = description
# GitHub API does not reliably support setting default branch on create without template/import.
if default_branch:
payload["default_branch"] = default_branch
try:
async with httpx.AsyncClient(timeout=20.0) as client:
response = await client.post(api_url, headers=headers, json=payload)
except Exception as e:
raise HTTPException(status_code=503, detail=f"GitHub API is unavailable: {str(e)}")
if response.status_code >= 400:
detail = response.text
try:
parsed = response.json()
detail = parsed.get("message") or detail
except Exception:
pass
raise HTTPException(status_code=response.status_code, detail=f"GitHub API error: {detail}")
return response.json()
# [/DEF:create_github_repository:Function]
# [DEF:create_gitlab_repository:Function]
# @PURPOSE: Create repository(project) in GitLab.
# @PRE: PAT has api scope.
# @POST: Returns created repository payload.
# @RETURN: dict
async def create_gitlab_repository(
self,
server_url: str,
pat: str,
name: str,
private: bool = True,
description: Optional[str] = None,
auto_init: bool = True,
default_branch: Optional[str] = "main",
) -> Dict[str, Any]:
base_url = self._normalize_git_server_url(server_url)
api_url = f"{base_url}/api/v4/projects"
headers = {
"PRIVATE-TOKEN": pat.strip(),
"Content-Type": "application/json",
"Accept": "application/json",
}
payload: Dict[str, Any] = {
"name": name,
"visibility": "private" if private else "public",
"initialize_with_readme": bool(auto_init),
}
if description:
payload["description"] = description
if default_branch:
payload["default_branch"] = default_branch
try:
async with httpx.AsyncClient(timeout=20.0) as client:
response = await client.post(api_url, headers=headers, json=payload)
except Exception as e:
raise HTTPException(status_code=503, detail=f"GitLab API is unavailable: {str(e)}")
if response.status_code >= 400:
detail = response.text
try:
parsed = response.json()
if isinstance(parsed, dict):
detail = parsed.get("message") or detail
except Exception:
pass
raise HTTPException(status_code=response.status_code, detail=f"GitLab API error: {detail}")
data = response.json()
# Normalize clone URL key to keep route response stable.
if "clone_url" not in data:
data["clone_url"] = data.get("http_url_to_repo")
if "html_url" not in data:
data["html_url"] = data.get("web_url")
if "ssh_url" not in data:
data["ssh_url"] = data.get("ssh_url_to_repo")
if "full_name" not in data:
data["full_name"] = data.get("path_with_namespace") or data.get("name")
return data
# [/DEF:create_gitlab_repository:Function]
# [DEF:_parse_remote_repo_identity:Function]
# @PURPOSE: Parse owner/repo from remote URL for Git server API operations.
# @PRE: remote_url is a valid git URL.
# @POST: Returns owner/repo tokens.
# @RETURN: Dict[str, str]
def _parse_remote_repo_identity(self, remote_url: str) -> Dict[str, str]:
normalized = str(remote_url or "").strip()
if not normalized:
raise HTTPException(status_code=400, detail="Repository remote_url is empty")
if normalized.startswith("git@"):
# git@host:owner/repo.git
path = normalized.split(":", 1)[1] if ":" in normalized else ""
else:
parsed = urlparse(normalized)
path = parsed.path or ""
path = path.strip("/")
if path.endswith(".git"):
path = path[:-4]
parts = [segment for segment in path.split("/") if segment]
if len(parts) < 2:
raise HTTPException(status_code=400, detail=f"Cannot parse repository owner/name from remote URL: {remote_url}")
owner = parts[0]
repo = parts[-1]
namespace = "/".join(parts[:-1])
return {
"owner": owner,
"repo": repo,
"namespace": namespace,
"full_name": f"{namespace}/{repo}",
}
# [/DEF:_parse_remote_repo_identity:Function]
# [DEF:_derive_server_url_from_remote:Function]
# @PURPOSE: Build API base URL from remote repository URL without credentials.
# @PRE: remote_url may be any git URL.
# @POST: Returns normalized http(s) base URL or None when derivation is impossible.
# @RETURN: Optional[str]
def _derive_server_url_from_remote(self, remote_url: str) -> Optional[str]:
normalized = str(remote_url or "").strip()
if not normalized or normalized.startswith("git@"):
return None
parsed = urlparse(normalized)
if parsed.scheme not in {"http", "https"}:
return None
if not parsed.hostname:
return None
netloc = parsed.hostname
if parsed.port:
netloc = f"{netloc}:{parsed.port}"
return f"{parsed.scheme}://{netloc}".rstrip("/")
# [/DEF:_derive_server_url_from_remote:Function]
# [DEF:promote_direct_merge:Function]
# @PURPOSE: Perform direct merge between branches in local repo and push target branch.
# @PRE: Repository exists and both branches are valid.
# @POST: Target branch contains merged changes from source branch.
# @RETURN: Dict[str, Any]
def promote_direct_merge(
self,
dashboard_id: int,
from_branch: str,
to_branch: str,
) -> Dict[str, Any]:
with belief_scope("GitService.promote_direct_merge"):
if not from_branch or not to_branch:
raise HTTPException(status_code=400, detail="from_branch and to_branch are required")
repo = self.get_repo(dashboard_id)
source = from_branch.strip()
target = to_branch.strip()
if source == target:
raise HTTPException(status_code=400, detail="from_branch and to_branch must be different")
try:
origin = repo.remote(name="origin")
except ValueError:
raise HTTPException(status_code=400, detail="Remote 'origin' not configured")
try:
origin.fetch()
# Ensure local source branch exists.
if source not in [head.name for head in repo.heads]:
if f"origin/{source}" in [ref.name for ref in repo.refs]:
repo.git.checkout("-b", source, f"origin/{source}")
else:
raise HTTPException(status_code=404, detail=f"Source branch '{source}' not found")
# Ensure local target branch exists and is checked out.
if target in [head.name for head in repo.heads]:
repo.git.checkout(target)
elif f"origin/{target}" in [ref.name for ref in repo.refs]:
repo.git.checkout("-b", target, f"origin/{target}")
else:
raise HTTPException(status_code=404, detail=f"Target branch '{target}' not found")
# Bring target up to date and merge source into target.
try:
origin.pull(target)
except Exception:
pass
repo.git.merge(source, "--no-ff", "-m", f"chore(flow): promote {source} -> {target}")
origin.push(refspec=f"{target}:{target}")
except HTTPException:
raise
except Exception as e:
message = str(e)
if "CONFLICT" in message.upper():
raise HTTPException(status_code=409, detail=f"Merge conflict during direct promote: {message}")
raise HTTPException(status_code=500, detail=f"Direct promote failed: {message}")
return {
"mode": "direct",
"from_branch": source,
"to_branch": target,
"status": "merged",
}
# [/DEF:promote_direct_merge:Function]
# [DEF:create_gitea_pull_request:Function]
# @PURPOSE: Create pull request in Gitea.
# @PRE: Config and remote URL are valid.
# @POST: Returns normalized PR metadata.
# @RETURN: Dict[str, Any]
async def create_gitea_pull_request(
self,
server_url: str,
pat: str,
remote_url: str,
from_branch: str,
to_branch: str,
title: str,
description: Optional[str] = None,
) -> Dict[str, Any]:
identity = self._parse_remote_repo_identity(remote_url)
payload = {
"title": title,
"head": from_branch,
"base": to_branch,
"body": description or "",
}
endpoint = f"/repos/{identity['namespace']}/{identity['repo']}/pulls"
try:
data = await self._gitea_request(
"POST",
server_url,
pat,
endpoint,
payload=payload,
)
except HTTPException as exc:
fallback_url = self._derive_server_url_from_remote(remote_url)
normalized_primary = self._normalize_git_server_url(server_url)
if exc.status_code != 404 or not fallback_url or fallback_url == normalized_primary:
raise
logger.warning(
"[create_gitea_pull_request][Action] Primary Gitea URL not found, retrying with remote host: %s",
fallback_url,
)
data = await self._gitea_request(
"POST",
fallback_url,
pat,
endpoint,
payload=payload,
)
return {
"id": data.get("number") or data.get("id"),
"url": data.get("html_url") or data.get("url"),
"status": data.get("state") or "open",
}
# [/DEF:create_gitea_pull_request:Function]
# [DEF:create_github_pull_request:Function]
# @PURPOSE: Create pull request in GitHub or GitHub Enterprise.
# @PRE: Config and remote URL are valid.
# @POST: Returns normalized PR metadata.
# @RETURN: Dict[str, Any]
async def create_github_pull_request(
self,
server_url: str,
pat: str,
remote_url: str,
from_branch: str,
to_branch: str,
title: str,
description: Optional[str] = None,
draft: bool = False,
) -> Dict[str, Any]:
identity = self._parse_remote_repo_identity(remote_url)
base_url = self._normalize_git_server_url(server_url)
if "github.com" in base_url:
api_url = f"https://api.github.com/repos/{identity['namespace']}/{identity['repo']}/pulls"
else:
api_url = f"{base_url}/api/v3/repos/{identity['namespace']}/{identity['repo']}/pulls"
headers = {
"Authorization": f"token {pat.strip()}",
"Content-Type": "application/json",
"Accept": "application/vnd.github+json",
}
payload = {
"title": title,
"head": from_branch,
"base": to_branch,
"body": description or "",
"draft": bool(draft),
}
try:
async with httpx.AsyncClient(timeout=20.0) as client:
response = await client.post(api_url, headers=headers, json=payload)
except Exception as e:
raise HTTPException(status_code=503, detail=f"GitHub API is unavailable: {str(e)}")
if response.status_code >= 400:
detail = response.text
try:
detail = response.json().get("message") or detail
except Exception:
pass
raise HTTPException(status_code=response.status_code, detail=f"GitHub API error: {detail}")
data = response.json()
return {
"id": data.get("number") or data.get("id"),
"url": data.get("html_url") or data.get("url"),
"status": data.get("state") or "open",
}
# [/DEF:create_github_pull_request:Function]
# [DEF:create_gitlab_merge_request:Function]
# @PURPOSE: Create merge request in GitLab.
# @PRE: Config and remote URL are valid.
# @POST: Returns normalized MR metadata.
# @RETURN: Dict[str, Any]
async def create_gitlab_merge_request(
self,
server_url: str,
pat: str,
remote_url: str,
from_branch: str,
to_branch: str,
title: str,
description: Optional[str] = None,
remove_source_branch: bool = False,
) -> Dict[str, Any]:
identity = self._parse_remote_repo_identity(remote_url)
base_url = self._normalize_git_server_url(server_url)
project_id = quote(identity["full_name"], safe="")
api_url = f"{base_url}/api/v4/projects/{project_id}/merge_requests"
headers = {
"PRIVATE-TOKEN": pat.strip(),
"Content-Type": "application/json",
"Accept": "application/json",
}
payload = {
"source_branch": from_branch,
"target_branch": to_branch,
"title": title,
"description": description or "",
"remove_source_branch": bool(remove_source_branch),
}
try:
async with httpx.AsyncClient(timeout=20.0) as client:
response = await client.post(api_url, headers=headers, json=payload)
except Exception as e:
raise HTTPException(status_code=503, detail=f"GitLab API is unavailable: {str(e)}")
if response.status_code >= 400:
detail = response.text
try:
parsed = response.json()
if isinstance(parsed, dict):
detail = parsed.get("message") or detail
except Exception:
pass
raise HTTPException(status_code=response.status_code, detail=f"GitLab API error: {detail}")
data = response.json()
return {
"id": data.get("iid") or data.get("id"),
"url": data.get("web_url") or data.get("url"),
"status": data.get("state") or "opened",
}
# [/DEF:create_gitlab_merge_request:Function]
# [/DEF:GitService:Class]
# [/DEF:backend.src.services.git_service:Module]
# [/DEF:backend.src.services.git_service:Module]

View File

@@ -18,6 +18,18 @@ import os
# @TIER: CRITICAL
# @PURPOSE: Handles encryption and decryption of sensitive data like API keys.
# @INVARIANT: Uses a secret key from environment or a default one (fallback only for dev).
#
# @TEST_CONTRACT: EncryptionManagerModel ->
# {
# required_fields: {},
# invariants: [
# "encrypted data can be decrypted back to the original string"
# ]
# }
# @TEST_FIXTURE: basic_encryption_cycle -> {"data": "my_secret_key"}
# @TEST_EDGE: decrypt_invalid_data -> raises Exception
# @TEST_EDGE: empty_string_encryption -> {"data": ""}
# @TEST_INVARIANT: symmetric_encryption -> verifies: [basic_encryption_cycle, empty_string_encryption]
class EncryptionManager:
# [DEF:EncryptionManager.__init__:Function]
# @PURPOSE: Initialize the encryption manager with a Fernet key.

View File

@@ -113,6 +113,20 @@ def extract_error_context(task: Task, report_status: ReportStatus) -> Optional[E
# @POST: Returns TaskReport with required fields and deterministic fallback behavior.
# @PARAM: task (Task) - Source task.
# @RETURN: TaskReport - Canonical normalized report.
#
# @TEST_CONTRACT: NormalizeTaskReport ->
# {
# required_fields: {task: Task},
# invariants: [
# "Returns a valid TaskReport object",
# "Maps TaskStatus to ReportStatus deterministically",
# "Extracts ErrorContext for FAILED/PARTIAL tasks"
# ]
# }
# @TEST_FIXTURE: valid_task -> {"task": "MockTask(id='1', plugin_id='superset-migration', status=TaskStatus.SUCCESS)"}
# @TEST_EDGE: task_with_error -> {"task": "MockTask(status=TaskStatus.FAILED, logs=[LogEntry(level='ERROR', message='Failed')])"}
# @TEST_EDGE: unknown_plugin_type -> {"task": "MockTask(plugin_id='unknown-plugin', status=TaskStatus.PENDING)"}
# @TEST_INVARIANT: deterministic_normalization -> verifies: [valid_task, task_with_error, unknown_plugin_type]
def normalize_task_report(task: Task) -> TaskReport:
with belief_scope("normalize_task_report"):
task_type = resolve_task_type(task.plugin_id)

View File

@@ -26,6 +26,19 @@ from .normalizer import normalize_task_report
# @PRE: TaskManager dependency is initialized.
# @POST: Provides deterministic list/detail report responses.
# @INVARIANT: Service methods are read-only over task history source.
#
# @TEST_CONTRACT: ReportsServiceModel ->
# {
# required_fields: {task_manager: TaskManager},
# invariants: [
# "list_reports returns a matching ReportCollection",
# "get_report_detail returns a valid ReportDetailView or None"
# ]
# }
# @TEST_FIXTURE: valid_service -> {"task_manager": "MockTaskManager()"}
# @TEST_EDGE: empty_task_list -> returns empty ReportCollection
# @TEST_EDGE: report_not_found -> get_report_detail returns None
# @TEST_INVARIANT: consistent_pagination -> verifies: [valid_service]
class ReportsService:
# [DEF:__init__:Function]
# @TIER: CRITICAL

View File

@@ -71,6 +71,17 @@ TASK_TYPE_PROFILES: Dict[TaskType, Dict[str, Any]] = {
# @POST: Always returns one of TaskType enum values.
# @PARAM: plugin_id (Optional[str]) - Source plugin/task identifier from task record.
# @RETURN: TaskType - Resolved canonical type or UNKNOWN fallback.
#
# @TEST_CONTRACT: ResolveTaskType ->
# {
# required_fields: {plugin_id: str},
# invariants: ["returns TaskType.UNKNOWN for missing/unmapped plugin_id"]
# }
# @TEST_FIXTURE: valid_plugin -> {"plugin_id": "superset-migration"}
# @TEST_EDGE: empty_plugin -> {"plugin_id": ""}
# @TEST_EDGE: none_plugin -> {"plugin_id": None}
# @TEST_EDGE: unknown_plugin -> {"plugin_id": "invalid-plugin"}
# @TEST_INVARIANT: fallback_to_unknown -> verifies: [empty_plugin, none_plugin, unknown_plugin]
def resolve_task_type(plugin_id: Optional[str]) -> TaskType:
with belief_scope("resolve_task_type"):
normalized = (plugin_id or "").strip()
@@ -86,6 +97,15 @@ def resolve_task_type(plugin_id: Optional[str]) -> TaskType:
# @POST: Returns a profile dict and never raises for unknown types.
# @PARAM: task_type (TaskType) - Canonical task type.
# @RETURN: Dict[str, Any] - Profile metadata used by normalization and UI contracts.
#
# @TEST_CONTRACT: GetTypeProfile ->
# {
# required_fields: {task_type: TaskType},
# invariants: ["returns a valid metadata dictionary even for UNKNOWN"]
# }
# @TEST_FIXTURE: valid_profile -> {"task_type": "migration"}
# @TEST_EDGE: missing_profile -> {"task_type": "some_new_type"}
# @TEST_INVARIANT: always_returns_dict -> verifies: [valid_profile, missing_profile]
def get_type_profile(task_type: TaskType) -> Dict[str, Any]:
with belief_scope("get_type_profile"):
return TASK_TYPE_PROFILES.get(task_type, TASK_TYPE_PROFILES[TaskType.UNKNOWN])

View File

@@ -10,6 +10,7 @@
# [SECTION: IMPORTS]
from typing import List, Dict, Optional, Any
from datetime import datetime
from ..core.superset_client import SupersetClient
from ..core.task_manager.models import Task
from ..services.git_service import GitService
@@ -39,11 +40,12 @@ class ResourceService:
# @RETURN: List[Dict] - Dashboards with git_status and last_task fields
# @RELATION: CALLS -> SupersetClient.get_dashboards_summary
# @RELATION: CALLS -> self._get_git_status_for_dashboard
# @RELATION: CALLS -> self._get_last_task_for_resource
# @RELATION: CALLS -> self._get_last_llm_task_for_dashboard
async def get_dashboards_with_status(
self,
env: Any,
tasks: Optional[List[Task]] = None
tasks: Optional[List[Task]] = None,
include_git_status: bool = True,
) -> List[Dict[str, Any]]:
with belief_scope("get_dashboards_with_status", f"env={env.id}"):
client = SupersetClient(env)
@@ -56,14 +58,18 @@ class ResourceService:
dashboard_dict = dashboard
dashboard_id = dashboard_dict.get('id')
# Get Git status if repo exists
git_status = self._get_git_status_for_dashboard(dashboard_id)
dashboard_dict['git_status'] = git_status
# Git status can be skipped for list endpoints and loaded lazily on UI side.
if include_git_status:
git_status = self._get_git_status_for_dashboard(dashboard_id)
dashboard_dict['git_status'] = git_status
else:
dashboard_dict['git_status'] = None
# Get last task status
last_task = self._get_last_task_for_resource(
f"dashboard-{dashboard_id}",
tasks
# Show status of the latest LLM validation for this dashboard.
last_task = self._get_last_llm_task_for_dashboard(
dashboard_id,
env.id,
tasks,
)
dashboard_dict['last_task'] = last_task
@@ -72,6 +78,157 @@ class ResourceService:
logger.info(f"[ResourceService][Coherence:OK] Fetched {len(result)} dashboards with status")
return result
# [/DEF:get_dashboards_with_status:Function]
# [DEF:get_dashboards_page_with_status:Function]
# @PURPOSE: Fetch one dashboard page from environment and enrich only that page with status metadata.
# @PRE: env is valid; page >= 1; page_size > 0.
# @POST: Returns page items plus total counters without scanning all pages locally.
# @PARAM: env (Environment) - Source environment.
# @PARAM: tasks (Optional[List[Task]]) - Tasks for latest LLM status.
# @PARAM: page (int) - 1-based page number.
# @PARAM: page_size (int) - Page size.
# @RETURN: Dict[str, Any] - {"dashboards": List[Dict], "total": int, "total_pages": int}
async def get_dashboards_page_with_status(
self,
env: Any,
tasks: Optional[List[Task]] = None,
page: int = 1,
page_size: int = 10,
search: Optional[str] = None,
include_git_status: bool = True,
) -> Dict[str, Any]:
with belief_scope(
"get_dashboards_page_with_status",
f"env={env.id}, page={page}, page_size={page_size}, search={search}",
):
client = SupersetClient(env)
total, dashboards_page = client.get_dashboards_summary_page(
page=page,
page_size=page_size,
search=search,
)
result = []
for dashboard in dashboards_page:
dashboard_dict = dashboard
dashboard_id = dashboard_dict.get("id")
if include_git_status:
dashboard_dict["git_status"] = self._get_git_status_for_dashboard(dashboard_id)
else:
dashboard_dict["git_status"] = None
dashboard_dict["last_task"] = self._get_last_llm_task_for_dashboard(
dashboard_id,
env.id,
tasks,
)
result.append(dashboard_dict)
total_pages = (total + page_size - 1) // page_size if total > 0 else 1
logger.info(
"[ResourceService][Coherence:OK] Fetched dashboards page %s/%s (%s items, total=%s)",
page,
total_pages,
len(result),
total,
)
return {
"dashboards": result,
"total": total,
"total_pages": total_pages,
}
# [/DEF:get_dashboards_page_with_status:Function]
# [DEF:_get_last_llm_task_for_dashboard:Function]
# @PURPOSE: Get most recent LLM validation task for a dashboard in an environment
# @PRE: dashboard_id is a valid integer identifier
# @POST: Returns the newest llm_dashboard_validation task summary or None
# @PARAM: dashboard_id (int) - The dashboard ID
# @PARAM: env_id (Optional[str]) - Environment ID to match task params
# @PARAM: tasks (Optional[List[Task]]) - List of tasks to search
# @RETURN: Optional[Dict] - Task summary with task_id and status
def _get_last_llm_task_for_dashboard(
self,
dashboard_id: int,
env_id: Optional[str],
tasks: Optional[List[Task]] = None,
) -> Optional[Dict[str, Any]]:
if not tasks:
return None
dashboard_id_str = str(dashboard_id)
matched_tasks = []
for task in tasks:
if getattr(task, "plugin_id", None) != "llm_dashboard_validation":
continue
params = getattr(task, "params", {}) or {}
if str(params.get("dashboard_id")) != dashboard_id_str:
continue
if env_id is not None:
task_env = params.get("environment_id") or params.get("env")
if str(task_env) != str(env_id):
continue
matched_tasks.append(task)
if not matched_tasks:
return None
def _task_time(task_obj: Any) -> datetime:
return (
getattr(task_obj, "started_at", None)
or getattr(task_obj, "finished_at", None)
or getattr(task_obj, "created_at", None)
or datetime.min
)
last_task = max(matched_tasks, key=_task_time)
raw_result = getattr(last_task, "result", None)
validation_status = None
if isinstance(raw_result, dict):
validation_status = self._normalize_validation_status(raw_result.get("status"))
return {
"task_id": str(getattr(last_task, "id", "")),
"status": self._normalize_task_status(getattr(last_task, "status", "")),
"validation_status": validation_status,
}
# [/DEF:_get_last_llm_task_for_dashboard:Function]
# [DEF:_normalize_task_status:Function]
# @PURPOSE: Normalize task status to stable uppercase values for UI/API projections
# @PRE: raw_status can be enum or string
# @POST: Returns uppercase status without enum class prefix
# @PARAM: raw_status (Any) - Raw task status object/value
# @RETURN: str - Normalized status token
def _normalize_task_status(self, raw_status: Any) -> str:
if raw_status is None:
return ""
value = getattr(raw_status, "value", raw_status)
status_text = str(value).strip()
if "." in status_text:
status_text = status_text.split(".")[-1]
return status_text.upper()
# [/DEF:_normalize_task_status:Function]
# [DEF:_normalize_validation_status:Function]
# @PURPOSE: Normalize LLM validation status to PASS/FAIL/WARN/UNKNOWN
# @PRE: raw_status can be any scalar type
# @POST: Returns normalized validation status token or None
# @PARAM: raw_status (Any) - Raw validation status from task result
# @RETURN: Optional[str] - PASS|FAIL|WARN|UNKNOWN
def _normalize_validation_status(self, raw_status: Any) -> Optional[str]:
if raw_status is None:
return None
status_text = str(raw_status).strip().upper()
if status_text in {"PASS", "FAIL", "WARN"}:
return status_text
return "UNKNOWN"
# [/DEF:_normalize_validation_status:Function]
# [DEF:get_datasets_with_status:Function]
# @PURPOSE: Fetch datasets from environment with mapping progress and last task status

View File

@@ -0,0 +1,111 @@
# [DEF:backend.tests.api.routes.test_clean_release_api:Module]
# @TIER: STANDARD
# @SEMANTICS: tests, api, clean-release, checks, reports
# @PURPOSE: Contract tests for clean release checks and reports endpoints.
# @LAYER: Domain
# @RELATION: TESTS -> backend.src.api.routes.clean_release
# @INVARIANT: API returns deterministic payload shapes for checks and reports.
from datetime import datetime, timezone
from fastapi.testclient import TestClient
from src.app import app
from src.dependencies import get_clean_release_repository
from src.models.clean_release import (
CleanProfilePolicy,
ProfileType,
ReleaseCandidate,
ReleaseCandidateStatus,
ResourceSourceEntry,
ResourceSourceRegistry,
)
from src.services.clean_release.repository import CleanReleaseRepository
def _repo_with_seed_data() -> CleanReleaseRepository:
repo = CleanReleaseRepository()
repo.save_candidate(
ReleaseCandidate(
candidate_id="2026.03.03-rc1",
version="2026.03.03",
profile=ProfileType.ENTERPRISE_CLEAN,
created_at=datetime.now(timezone.utc),
created_by="tester",
source_snapshot_ref="git:abc123",
status=ReleaseCandidateStatus.PREPARED,
)
)
repo.save_registry(
ResourceSourceRegistry(
registry_id="registry-internal-v1",
name="Internal",
entries=[
ResourceSourceEntry(
source_id="src-1",
host="repo.intra.company.local",
protocol="https",
purpose="artifact-repo",
enabled=True,
)
],
updated_at=datetime.now(timezone.utc),
updated_by="tester",
status="active",
)
)
repo.save_policy(
CleanProfilePolicy(
policy_id="policy-enterprise-clean-v1",
policy_version="1.0.0",
active=True,
prohibited_artifact_categories=["test-data"],
required_system_categories=["system-init"],
external_source_forbidden=True,
internal_source_registry_ref="registry-internal-v1",
effective_from=datetime.now(timezone.utc),
profile=ProfileType.ENTERPRISE_CLEAN,
)
)
return repo
def test_start_check_and_get_status_contract():
repo = _repo_with_seed_data()
app.dependency_overrides[get_clean_release_repository] = lambda: repo
try:
client = TestClient(app)
start = client.post(
"/api/clean-release/checks",
json={
"candidate_id": "2026.03.03-rc1",
"profile": "enterprise-clean",
"execution_mode": "tui",
"triggered_by": "tester",
},
)
assert start.status_code == 202
payload = start.json()
assert set(["check_run_id", "candidate_id", "status", "started_at"]).issubset(payload.keys())
check_run_id = payload["check_run_id"]
status_resp = client.get(f"/api/clean-release/checks/{check_run_id}")
assert status_resp.status_code == 200
status_payload = status_resp.json()
assert status_payload["check_run_id"] == check_run_id
assert "final_status" in status_payload
assert "checks" in status_payload
finally:
app.dependency_overrides.clear()
def test_get_report_not_found_returns_404():
repo = _repo_with_seed_data()
app.dependency_overrides[get_clean_release_repository] = lambda: repo
try:
client = TestClient(app)
resp = client.get("/api/clean-release/reports/unknown-report")
assert resp.status_code == 404
finally:
app.dependency_overrides.clear()

View File

@@ -0,0 +1,97 @@
# [DEF:backend.tests.api.routes.test_clean_release_source_policy:Module]
# @TIER: STANDARD
# @SEMANTICS: tests, api, clean-release, source-policy
# @PURPOSE: Validate API behavior for source isolation violations in clean release preparation.
# @LAYER: Domain
# @RELATION: TESTS -> backend.src.api.routes.clean_release
# @INVARIANT: External endpoints must produce blocking violation entries.
from datetime import datetime, timezone
from fastapi.testclient import TestClient
from src.app import app
from src.dependencies import get_clean_release_repository
from src.models.clean_release import (
CleanProfilePolicy,
ProfileType,
ReleaseCandidate,
ReleaseCandidateStatus,
ResourceSourceEntry,
ResourceSourceRegistry,
)
from src.services.clean_release.repository import CleanReleaseRepository
def _repo_with_seed_data() -> CleanReleaseRepository:
repo = CleanReleaseRepository()
repo.save_candidate(
ReleaseCandidate(
candidate_id="2026.03.03-rc1",
version="2026.03.03",
profile=ProfileType.ENTERPRISE_CLEAN,
created_at=datetime.now(timezone.utc),
created_by="tester",
source_snapshot_ref="git:abc123",
status=ReleaseCandidateStatus.DRAFT,
)
)
repo.save_registry(
ResourceSourceRegistry(
registry_id="registry-internal-v1",
name="Internal",
entries=[
ResourceSourceEntry(
source_id="src-1",
host="repo.intra.company.local",
protocol="https",
purpose="artifact-repo",
enabled=True,
)
],
updated_at=datetime.now(timezone.utc),
updated_by="tester",
status="active",
)
)
repo.save_policy(
CleanProfilePolicy(
policy_id="policy-enterprise-clean-v1",
policy_version="1.0.0",
active=True,
prohibited_artifact_categories=["test-data"],
required_system_categories=["system-init"],
external_source_forbidden=True,
internal_source_registry_ref="registry-internal-v1",
effective_from=datetime.now(timezone.utc),
profile=ProfileType.ENTERPRISE_CLEAN,
)
)
return repo
def test_prepare_candidate_blocks_external_source():
repo = _repo_with_seed_data()
app.dependency_overrides[get_clean_release_repository] = lambda: repo
try:
client = TestClient(app)
response = client.post(
"/api/clean-release/candidates/prepare",
json={
"candidate_id": "2026.03.03-rc1",
"artifacts": [
{"path": "cfg/system.yaml", "category": "system-init", "reason": "required"}
],
"sources": ["repo.intra.company.local", "pypi.org"],
"operator_id": "release-manager",
},
)
assert response.status_code == 200
data = response.json()
assert data["status"] == "blocked"
assert any(v["category"] == "external-source" for v in data["violations"])
finally:
app.dependency_overrides.clear()

View File

@@ -0,0 +1,62 @@
# [DEF:backend.tests.core.migration.test_archive_parser:Module]
#
# @TIER: STANDARD
# @PURPOSE: Unit tests for MigrationArchiveParser ZIP extraction contract.
# @LAYER: Domain
# @RELATION: VERIFIES -> backend.src.core.migration.archive_parser
#
import os
import sys
import tempfile
import zipfile
from pathlib import Path
import yaml
backend_dir = str(Path(__file__).parent.parent.parent.parent.resolve())
if backend_dir not in sys.path:
sys.path.insert(0, backend_dir)
from src.core.migration.archive_parser import MigrationArchiveParser
def test_extract_objects_from_zip_collects_all_types():
parser = MigrationArchiveParser()
with tempfile.TemporaryDirectory() as td:
td_path = Path(td)
zip_path = td_path / "objects.zip"
src_dir = td_path / "src"
(src_dir / "dashboards").mkdir(parents=True)
(src_dir / "charts").mkdir(parents=True)
(src_dir / "datasets").mkdir(parents=True)
with open(src_dir / "dashboards" / "dash.yaml", "w") as file_obj:
yaml.dump({"uuid": "dash-u1", "dashboard_title": "D1", "json_metadata": "{}"}, file_obj)
with open(src_dir / "charts" / "chart.yaml", "w") as file_obj:
yaml.dump({"uuid": "chart-u1", "slice_name": "C1", "viz_type": "bar"}, file_obj)
with open(src_dir / "datasets" / "dataset.yaml", "w") as file_obj:
yaml.dump({"uuid": "ds-u1", "table_name": "orders", "database_uuid": "db-u1"}, file_obj)
with zipfile.ZipFile(zip_path, "w") as zip_obj:
for root, _, files in os.walk(src_dir):
for file_name in files:
file_path = Path(root) / file_name
zip_obj.write(file_path, file_path.relative_to(src_dir))
extracted = parser.extract_objects_from_zip(str(zip_path))
if len(extracted["dashboards"]) != 1:
raise AssertionError("dashboards extraction size mismatch")
if extracted["dashboards"][0]["uuid"] != "dash-u1":
raise AssertionError("dashboard uuid mismatch")
if len(extracted["charts"]) != 1:
raise AssertionError("charts extraction size mismatch")
if extracted["charts"][0]["uuid"] != "chart-u1":
raise AssertionError("chart uuid mismatch")
if len(extracted["datasets"]) != 1:
raise AssertionError("datasets extraction size mismatch")
if extracted["datasets"][0]["uuid"] != "ds-u1":
raise AssertionError("dataset uuid mismatch")
# [/DEF:backend.tests.core.migration.test_archive_parser:Module]

View File

@@ -0,0 +1,110 @@
# [DEF:backend.tests.core.migration.test_dry_run_orchestrator:Module]
#
# @TIER: STANDARD
# @PURPOSE: Unit tests for MigrationDryRunService diff and risk computation contracts.
# @LAYER: Domain
# @RELATION: VERIFIES -> backend.src.core.migration.dry_run_orchestrator
#
import json
import sys
from pathlib import Path
from unittest.mock import MagicMock, patch
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
from sqlalchemy.pool import StaticPool
backend_dir = str(Path(__file__).parent.parent.parent.parent.resolve())
if backend_dir not in sys.path:
sys.path.insert(0, backend_dir)
from src.core.migration.dry_run_orchestrator import MigrationDryRunService
from src.models.dashboard import DashboardSelection
from src.models.mapping import Base
def _load_fixture() -> dict:
fixture_path = Path(__file__).parents[2] / "fixtures" / "migration_dry_run_fixture.json"
return json.loads(fixture_path.read_text())
def _make_session():
engine = create_engine(
"sqlite:///:memory:",
connect_args={"check_same_thread": False},
poolclass=StaticPool,
)
Base.metadata.create_all(engine)
Session = sessionmaker(bind=engine)
return Session()
def test_migration_dry_run_service_builds_diff_and_risk():
# @TEST_CONTRACT: dry_run_result_contract -> {
# required_fields: {diff: object, summary: object, risk: object},
# invariants: ["risk.score >= 0", "summary.selected_dashboards == len(selection.selected_ids)"]
# }
# @TEST_FIXTURE: migration_dry_run_fixture -> backend/tests/fixtures/migration_dry_run_fixture.json
# @TEST_EDGE: missing_target_datasource -> fixture.transformed_zip_objects.datasets[0].database_uuid
# @TEST_EDGE: breaking_reference -> fixture.transformed_zip_objects.charts[0].dataset_uuid
fixture = _load_fixture()
db = _make_session()
selection = DashboardSelection(
selected_ids=[42],
source_env_id="src",
target_env_id="tgt",
replace_db_config=False,
fix_cross_filters=True,
)
source_client = MagicMock()
source_client.get_dashboards_summary.return_value = fixture["source_dashboard_summary"]
source_client.export_dashboard.return_value = (b"PK\x03\x04", "source.zip")
target_client = MagicMock()
target_client.get_dashboards.return_value = (
len(fixture["target"]["dashboards"]),
fixture["target"]["dashboards"],
)
target_client.get_datasets.return_value = (
len(fixture["target"]["datasets"]),
fixture["target"]["datasets"],
)
target_client.get_charts.return_value = (
len(fixture["target"]["charts"]),
fixture["target"]["charts"],
)
target_client.get_databases.return_value = (
len(fixture["target"]["databases"]),
fixture["target"]["databases"],
)
parser = MagicMock()
parser.extract_objects_from_zip.return_value = fixture["transformed_zip_objects"]
service = MigrationDryRunService(parser=parser)
with patch("src.core.migration.dry_run_orchestrator.MigrationEngine") as EngineMock:
engine = MagicMock()
engine.transform_zip.return_value = True
EngineMock.return_value = engine
result = service.run(selection, source_client, target_client, db)
if "summary" not in result:
raise AssertionError("summary is missing in dry-run payload")
if result["summary"]["selected_dashboards"] != 1:
raise AssertionError("selected_dashboards summary mismatch")
if result["summary"]["dashboards"]["update"] != 1:
raise AssertionError("dashboard update count mismatch")
if result["summary"]["charts"]["create"] != 1:
raise AssertionError("chart create count mismatch")
if result["summary"]["datasets"]["create"] != 1:
raise AssertionError("dataset create count mismatch")
risk_codes = {item["code"] for item in result["risk"]["items"]}
if "missing_datasource" not in risk_codes:
raise AssertionError("missing_datasource risk is not detected")
if "breaking_reference" not in risk_codes:
raise AssertionError("breaking_reference risk is not detected")
# [/DEF:backend.tests.core.migration.test_dry_run_orchestrator:Module]

View File

@@ -0,0 +1,67 @@
# [DEF:backend.tests.core.test_git_service_gitea_pr:Module]
# @TIER: STANDARD
# @SEMANTICS: tests, git, gitea, pull_request, fallback
# @PURPOSE: Validate Gitea PR creation fallback behavior when configured server URL is stale.
# @LAYER: Domain
# @RELATION: TESTS -> backend.src.services.git_service.create_gitea_pull_request
# @INVARIANT: A 404 from primary Gitea URL retries once against remote-url host when different.
import asyncio
import sys
from pathlib import Path
from fastapi import HTTPException
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
from src.services.git_service import GitService
# [DEF:test_derive_server_url_from_remote_strips_credentials:Function]
# @PURPOSE: Ensure helper returns host base URL and removes embedded credentials.
# @PRE: remote_url is an https URL with username/token.
# @POST: Result is scheme+host only.
def test_derive_server_url_from_remote_strips_credentials():
service = GitService(base_path="test_repos")
derived = service._derive_server_url_from_remote(
"https://oauth2:token@giteabusya.bebesh.ru/busya/covid-vaccine-dashboard.git"
)
assert derived == "https://giteabusya.bebesh.ru"
# [/DEF:test_derive_server_url_from_remote_strips_credentials:Function]
# [DEF:test_create_gitea_pull_request_retries_with_remote_host_on_404:Function]
# @PURPOSE: Verify create_gitea_pull_request retries with remote URL host after primary 404.
# @PRE: primary server_url differs from remote_url host.
# @POST: Method returns success payload from fallback request.
def test_create_gitea_pull_request_retries_with_remote_host_on_404(monkeypatch):
service = GitService(base_path="test_repos")
calls = []
async def fake_gitea_request(method, server_url, pat, endpoint, payload=None):
calls.append((method, server_url, endpoint))
if len(calls) == 1:
raise HTTPException(status_code=404, detail="Gitea API error: The target couldn't be found.")
return {"number": 42, "html_url": "https://giteabusya.bebesh.ru/busya/covid-vaccine-dashboard/pulls/42", "state": "open"}
monkeypatch.setattr(service, "_gitea_request", fake_gitea_request)
result = asyncio.run(
service.create_gitea_pull_request(
server_url="https://gitea.bebesh.ru",
pat="secret",
remote_url="https://oauth2:secret@giteabusya.bebesh.ru/busya/covid-vaccine-dashboard.git",
from_branch="ss-dev",
to_branch="main",
title="Promote ss-dev -> main",
description="",
)
)
assert result["id"] == 42
assert len(calls) == 2
assert calls[0][1] == "https://gitea.bebesh.ru"
assert calls[1][1] == "https://giteabusya.bebesh.ru"
# [/DEF:test_create_gitea_pull_request_retries_with_remote_host_on_404:Function]
# [/DEF:backend.tests.core.test_git_service_gitea_pr:Module]

View File

@@ -0,0 +1,34 @@
{
"policy_enterprise_clean": {
"policy_id": "policy-enterprise-clean-v1",
"policy_version": "1.0.0",
"active": true,
"prohibited_artifact_categories": ["test-data", "demo-data", "load-test", "sample-repository"],
"required_system_categories": ["system-init", "security-bootstrap", "schema-migrations"],
"external_source_forbidden": true,
"internal_source_registry_ref": "registry-internal-v1",
"effective_from": "2026-03-03T00:00:00Z",
"effective_to": null,
"profile": "enterprise-clean"
},
"candidate_clean_ready": {
"candidate_id": "2026.03.03-rc1",
"version": "2026.03.03",
"profile": "enterprise-clean",
"created_at": "2026-03-03T09:00:00Z",
"created_by": "release-manager",
"source_snapshot_ref": "git:abc123",
"status": "prepared"
},
"compliance_report_blocked_example": {
"report_id": "CCR-2026-03-03-001",
"check_run_id": "check-run-001",
"candidate_id": "2026.03.03-rc1",
"generated_at": "2026-03-03T09:15:00Z",
"final_status": "blocked",
"operator_summary": "Blocked due to external-source violation",
"structured_payload_ref": "file:///tmp/ccr-2026-03-03-001.json",
"violations_count": 2,
"blocking_violations_count": 2
}
}

View File

@@ -0,0 +1,58 @@
{
"source_dashboard_summary": [
{
"id": 42,
"title": "Sales"
}
],
"target": {
"dashboards": [
{
"uuid": "dash-1",
"dashboard_title": "Sales Old",
"slug": "sales-old",
"position_json": "{}",
"json_metadata": "{}",
"description": "",
"owners": [
{
"username": "owner-a"
}
]
}
],
"datasets": [],
"charts": [],
"databases": []
},
"transformed_zip_objects": {
"dashboards": [
{
"uuid": "dash-1",
"title": "Sales New",
"signature": "{\"title\":\"Sales New\"}",
"owners": [
{
"username": "owner-b"
}
]
}
],
"charts": [
{
"uuid": "chart-1",
"title": "Chart A",
"signature": "{\"title\":\"Chart A\"}",
"dataset_uuid": "dataset-404"
}
],
"datasets": [
{
"uuid": "dataset-1",
"title": "orders",
"signature": "{\"title\":\"orders\"}",
"database_uuid": "db-missing"
}
]
}
}

View File

@@ -0,0 +1,41 @@
# [DEF:backend.tests.services.clean_release.test_manifest_builder:Module]
# @TIER: CRITICAL
# @SEMANTICS: tests, clean-release, manifest, deterministic
# @PURPOSE: Validate deterministic manifest generation behavior for US1.
# @LAYER: Domain
# @RELATION: VERIFIES -> backend.src.services.clean_release.manifest_builder
# @INVARIANT: Same input artifacts produce identical deterministic hash.
from src.services.clean_release.manifest_builder import build_distribution_manifest
# [DEF:test_manifest_deterministic_hash_for_same_input:Function]
# @PURPOSE: Ensure hash is stable for same candidate/policy/artifact input.
# @PRE: Same input lists are passed twice.
# @POST: Hash and summary remain identical.
def test_manifest_deterministic_hash_for_same_input():
artifacts = [
{"path": "a.yaml", "category": "system-init", "classification": "required-system", "reason": "required"},
{"path": "b.yaml", "category": "test-data", "classification": "excluded-prohibited", "reason": "prohibited"},
]
manifest1 = build_distribution_manifest(
manifest_id="m1",
candidate_id="2026.03.03-rc1",
policy_id="policy-enterprise-clean-v1",
generated_by="tester",
artifacts=artifacts,
)
manifest2 = build_distribution_manifest(
manifest_id="m2",
candidate_id="2026.03.03-rc1",
policy_id="policy-enterprise-clean-v1",
generated_by="tester",
artifacts=artifacts,
)
assert manifest1.deterministic_hash == manifest2.deterministic_hash
assert manifest1.summary.included_count == manifest2.summary.included_count
assert manifest1.summary.excluded_count == manifest2.summary.excluded_count
# [/DEF:test_manifest_deterministic_hash_for_same_input:Function]
# [/DEF:backend.tests.services.clean_release.test_manifest_builder:Module]

View File

@@ -0,0 +1,144 @@
# [DEF:backend.tests.services.clean_release.test_policy_engine:Module]
# @TIER: CRITICAL
# @SEMANTICS: tests, clean-release, policy-engine, deterministic
# @PURPOSE: Validate policy model contracts and deterministic classification prerequisites for US1.
# @LAYER: Domain
# @RELATION: VERIFIES -> backend.src.models.clean_release.CleanProfilePolicy
# @INVARIANT: Enterprise policy rejects invalid activation states.
import pytest
from datetime import datetime, timezone
from src.models.clean_release import CleanProfilePolicy, ProfileType
# [DEF:test_policy_enterprise_clean_valid:Function]
# @PURPOSE: Ensure valid enterprise policy payload is accepted.
# @PRE: Fixture-like payload contains prohibited categories and registry ref.
# @POST: Model is created with external_source_forbidden=True.
def test_policy_enterprise_clean_valid():
policy = CleanProfilePolicy(
policy_id="policy-enterprise-clean-v1",
policy_version="1.0.0",
active=True,
prohibited_artifact_categories=["test-data", "demo-data"],
required_system_categories=["system-init"],
external_source_forbidden=True,
internal_source_registry_ref="registry-internal-v1",
effective_from=datetime.now(timezone.utc),
profile=ProfileType.ENTERPRISE_CLEAN,
)
assert policy.external_source_forbidden is True
assert policy.prohibited_artifact_categories == ["test-data", "demo-data"]
# [/DEF:test_policy_enterprise_clean_valid:Function]
# [DEF:test_policy_missing_registry_fails:Function]
# @PURPOSE: Verify missing registry ref violates policy contract.
# @PRE: enterprise-clean policy payload has blank registry ref.
# @POST: Validation error is raised.
def test_policy_missing_registry_fails():
with pytest.raises(ValueError):
CleanProfilePolicy(
policy_id="policy-enterprise-clean-v1",
policy_version="1.0.0",
active=True,
prohibited_artifact_categories=["test-data"],
required_system_categories=["system-init"],
external_source_forbidden=True,
internal_source_registry_ref="",
effective_from=datetime.now(timezone.utc),
profile=ProfileType.ENTERPRISE_CLEAN,
)
# [/DEF:test_policy_missing_registry_fails:Function]
# [DEF:test_policy_empty_prohibited_categories_fails:Function]
# @PURPOSE: Verify enterprise policy cannot activate without prohibited categories.
# @PRE: enterprise-clean policy payload has empty prohibited categories.
# @POST: Validation error is raised.
def test_policy_empty_prohibited_categories_fails():
with pytest.raises(ValueError):
CleanProfilePolicy(
policy_id="policy-enterprise-clean-v1",
policy_version="1.0.0",
active=True,
prohibited_artifact_categories=[],
required_system_categories=["system-init"],
external_source_forbidden=True,
internal_source_registry_ref="registry-internal-v1",
effective_from=datetime.now(timezone.utc),
profile=ProfileType.ENTERPRISE_CLEAN,
)
# [/DEF:test_policy_empty_prohibited_categories_fails:Function]
# [DEF:test_policy_conflicting_external_forbidden_flag_fails:Function]
# @PURPOSE: Verify enterprise policy enforces external_source_forbidden=true.
# @PRE: enterprise-clean policy payload sets external_source_forbidden to false.
# @POST: Validation error is raised.
def test_policy_conflicting_external_forbidden_flag_fails():
with pytest.raises(ValueError):
CleanProfilePolicy(
policy_id="policy-enterprise-clean-v1",
policy_version="1.0.0",
active=True,
prohibited_artifact_categories=["test-data"],
required_system_categories=["system-init"],
external_source_forbidden=False,
internal_source_registry_ref="registry-internal-v1",
effective_from=datetime.now(timezone.utc),
profile=ProfileType.ENTERPRISE_CLEAN,
)
# [/DEF:test_policy_conflicting_external_forbidden_flag_fails:Function]
# [/DEF:backend.tests.services.clean_release.test_policy_engine:Module]
from src.models.clean_release import ResourceSourceRegistry, ResourceSourceEntry, RegistryStatus
from src.services.clean_release.policy_engine import CleanPolicyEngine
def _policy_enterprise_clean() -> CleanProfilePolicy:
return CleanProfilePolicy(
policy_id="policy-enterprise-clean-v1",
policy_version="1.0.0",
active=True,
prohibited_artifact_categories=["test-data"],
required_system_categories=["system-init"],
external_source_forbidden=True,
internal_source_registry_ref="registry-internal-v1",
effective_from=datetime.now(timezone.utc),
profile=ProfileType.ENTERPRISE_CLEAN,
)
def _registry() -> ResourceSourceRegistry:
return ResourceSourceRegistry(
registry_id="registry-internal-v1",
name="Internal",
entries=[ResourceSourceEntry(source_id="1", host="nexus.internal", protocol="https", purpose="pkg", enabled=True)],
updated_at=datetime.now(timezone.utc),
updated_by="tester",
)
# [DEF:test_policy_valid:Function]
# @PURPOSE: Validate policy valid scenario
def test_policy_valid():
engine = CleanPolicyEngine(_policy_enterprise_clean(), _registry())
res = engine.validate_policy()
assert res.ok is True
# [DEF:test_conflicting_registry:Function]
# @PURPOSE: Validate policy conflicting registry edge
def test_conflicting_registry():
reg = _registry()
reg.registry_id = "other-registry"
engine = CleanPolicyEngine(_policy_enterprise_clean(), reg)
res = engine.validate_policy()
assert res.ok is False
assert "Policy registry ref does not match provided registry" in res.blocking_reasons
# [DEF:test_external_endpoint:Function]
# @PURPOSE: Validate policy external endpoint edge
def test_external_endpoint():
engine = CleanPolicyEngine(_policy_enterprise_clean(), _registry())
res = engine.validate_resource_source("external.org")
assert res.ok is False
assert res.violation["category"] == "external-source"

View File

@@ -0,0 +1,58 @@
# [DEF:backend.tests.services.clean_release.test_source_isolation:Module]
# @TIER: STANDARD
# @SEMANTICS: tests, clean-release, source-isolation, internal-only
# @PURPOSE: Verify internal source registry validation behavior.
# @LAYER: Domain
# @RELATION: TESTS -> backend.src.services.clean_release.source_isolation
# @INVARIANT: External endpoints always produce blocking violations.
from datetime import datetime, timezone
from src.models.clean_release import ResourceSourceEntry, ResourceSourceRegistry
from src.services.clean_release.source_isolation import validate_internal_sources
def _registry() -> ResourceSourceRegistry:
return ResourceSourceRegistry(
registry_id="registry-internal-v1",
name="Internal Sources",
entries=[
ResourceSourceEntry(
source_id="src-1",
host="repo.intra.company.local",
protocol="https",
purpose="artifact-repo",
enabled=True,
),
ResourceSourceEntry(
source_id="src-2",
host="pypi.intra.company.local",
protocol="https",
purpose="package-mirror",
enabled=True,
),
],
updated_at=datetime.now(timezone.utc),
updated_by="tester",
status="active",
)
def test_validate_internal_sources_all_internal_ok():
result = validate_internal_sources(
registry=_registry(),
endpoints=["repo.intra.company.local", "pypi.intra.company.local"],
)
assert result["ok"] is True
assert result["violations"] == []
def test_validate_internal_sources_external_blocked():
result = validate_internal_sources(
registry=_registry(),
endpoints=["repo.intra.company.local", "pypi.org"],
)
assert result["ok"] is False
assert len(result["violations"]) == 1
assert result["violations"][0]["category"] == "external-source"
assert result["violations"][0]["blocked_release"] is True

View File

@@ -1,73 +1,366 @@
# [DEF:backend.tests.test_dashboards_api:Module]
# @TIER: STANDARD
# @PURPOSE: Contract-driven tests for Dashboard Hub API
# @PURPOSE: Comprehensive contract-driven tests for Dashboard Hub API
# @LAYER: Domain (Tests)
# @SEMANTICS: tests, dashboards, api, contract
# @RELATION: TESTS -> backend.src.api.routes.dashboards
# @SEMANTICS: tests, dashboards, api, contract, remediation
import pytest
from fastapi.testclient import TestClient
from unittest.mock import MagicMock, patch
from unittest.mock import MagicMock, patch, AsyncMock
from datetime import datetime, timezone
from src.app import app
from src.api.routes.dashboards import DashboardsResponse
from src.api.routes.dashboards import DashboardsResponse, DashboardDetailResponse, DashboardTaskHistoryResponse, DatabaseMappingsResponse
from src.dependencies import get_current_user, has_permission, get_config_manager, get_task_manager, get_resource_service, get_mapping_service
# Global mock user
mock_user = MagicMock()
mock_user.username = "testuser"
mock_user.roles = []
admin_role = MagicMock()
admin_role.name = "Admin"
mock_user.roles.append(admin_role)
@pytest.fixture(autouse=True)
def mock_deps():
config_manager = MagicMock()
task_manager = MagicMock()
resource_service = MagicMock()
mapping_service = MagicMock()
app.dependency_overrides[get_config_manager] = lambda: config_manager
app.dependency_overrides[get_task_manager] = lambda: task_manager
app.dependency_overrides[get_resource_service] = lambda: resource_service
app.dependency_overrides[get_mapping_service] = lambda: mapping_service
app.dependency_overrides[get_current_user] = lambda: mock_user
# Overrides for specific permission checks
app.dependency_overrides[has_permission("plugin:migration", "READ")] = lambda: mock_user
app.dependency_overrides[has_permission("plugin:migration", "EXECUTE")] = lambda: mock_user
app.dependency_overrides[has_permission("plugin:backup", "EXECUTE")] = lambda: mock_user
app.dependency_overrides[has_permission("tasks", "READ")] = lambda: mock_user
app.dependency_overrides[has_permission("dashboards", "READ")] = lambda: mock_user
yield {
"config": config_manager,
"task": task_manager,
"resource": resource_service,
"mapping": mapping_service
}
app.dependency_overrides.clear()
client = TestClient(app)
# [DEF:test_get_dashboards_success:Function]
# @TEST: GET /api/dashboards returns 200 and valid schema
# @PRE: env_id exists
# @POST: Response matches DashboardsResponse schema
def test_get_dashboards_success():
with patch("src.api.routes.dashboards.get_config_manager") as mock_config, \
patch("src.api.routes.dashboards.get_resource_service") as mock_service, \
patch("src.api.routes.dashboards.has_permission") as mock_perm:
# --- 1. get_dashboards tests ---
def test_get_dashboards_success(mock_deps):
"""Uses @TEST_FIXTURE: dashboard_list_happy data."""
mock_env = MagicMock()
mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_deps["task"].get_all_tasks.return_value = []
# @TEST_FIXTURE: dashboard_list_happy -> {"id": 1, "title": "Main Revenue"}
mock_deps["resource"].get_dashboards_with_status = AsyncMock(return_value=[
{"id": 1, "title": "Main Revenue", "slug": "main-revenue", "git_status": {"branch": "main", "sync_status": "OK"}}
])
response = client.get("/api/dashboards?env_id=prod&page=1&page_size=10")
assert response.status_code == 200
data = response.json()
# exhaustive @POST assertions
assert "dashboards" in data
assert len(data["dashboards"]) == 1 # @TEST_FIXTURE: expected_count: 1
assert data["dashboards"][0]["title"] == "Main Revenue"
assert data["total"] == 1
assert data["page"] == 1
assert data["page_size"] == 10
assert data["total_pages"] == 1
# schema validation
DashboardsResponse(**data)
def test_get_dashboards_with_search(mock_deps):
mock_env = MagicMock()
mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_deps["task"].get_all_tasks.return_value = []
mock_deps["resource"].get_dashboards_with_status = AsyncMock(return_value=[
{"id": 1, "title": "Sales Report", "slug": "sales"},
{"id": 2, "title": "Marketing", "slug": "marketing"}
])
# Mock environment
response = client.get("/api/dashboards?env_id=prod&search=sales")
assert response.status_code == 200
data = response.json()
assert len(data["dashboards"]) == 1
assert data["dashboards"][0]["title"] == "Sales Report"
def test_get_dashboards_empty(mock_deps):
"""@TEST_EDGE: empty_dashboards -> {env_id: 'empty_env', expected_total: 0}"""
mock_env = MagicMock()
mock_env.id = "empty_env"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_deps["task"].get_all_tasks.return_value = []
mock_deps["resource"].get_dashboards_with_status = AsyncMock(return_value=[])
response = client.get("/api/dashboards?env_id=empty_env")
assert response.status_code == 200
data = response.json()
assert data["total"] == 0
assert len(data["dashboards"]) == 0
assert data["total_pages"] == 1
DashboardsResponse(**data)
def test_get_dashboards_superset_failure(mock_deps):
"""@TEST_EDGE: external_superset_failure -> {env_id: 'bad_conn', status: 503}"""
mock_env = MagicMock()
mock_env.id = "bad_conn"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_deps["task"].get_all_tasks.return_value = []
mock_deps["resource"].get_dashboards_with_status = AsyncMock(
side_effect=Exception("Connection refused")
)
response = client.get("/api/dashboards?env_id=bad_conn")
assert response.status_code == 503
assert "Failed to fetch dashboards" in response.json()["detail"]
def test_get_dashboards_env_not_found(mock_deps):
mock_deps["config"].get_environments.return_value = []
response = client.get("/api/dashboards?env_id=nonexistent")
assert response.status_code == 404
assert "Environment not found" in response.json()["detail"]
def test_get_dashboards_invalid_pagination(mock_deps):
mock_env = MagicMock()
mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
# page < 1
assert client.get("/api/dashboards?env_id=prod&page=0").status_code == 400
assert client.get("/api/dashboards?env_id=prod&page=-1").status_code == 400
# page_size < 1
assert client.get("/api/dashboards?env_id=prod&page_size=0").status_code == 400
# page_size > 100
assert client.get("/api/dashboards?env_id=prod&page_size=101").status_code == 400
# --- 2. get_database_mappings tests ---
def test_get_database_mappings_success(mock_deps):
mock_s = MagicMock(); mock_s.id = "s"
mock_t = MagicMock(); mock_t.id = "t"
mock_deps["config"].get_environments.return_value = [mock_s, mock_t]
mock_deps["mapping"].get_suggestions = AsyncMock(return_value=[
{"source_db": "src", "target_db": "dst", "confidence": 0.9}
])
response = client.get("/api/dashboards/db-mappings?source_env_id=s&target_env_id=t")
assert response.status_code == 200
data = response.json()
assert len(data["mappings"]) == 1
assert data["mappings"][0]["confidence"] == 0.9
DatabaseMappingsResponse(**data)
def test_get_database_mappings_env_not_found(mock_deps):
mock_deps["config"].get_environments.return_value = []
response = client.get("/api/dashboards/db-mappings?source_env_id=ghost&target_env_id=t")
assert response.status_code == 404
# --- 3. get_dashboard_detail tests ---
def test_get_dashboard_detail_success(mock_deps):
with patch("src.api.routes.dashboards.SupersetClient") as mock_client_cls:
mock_env = MagicMock()
mock_env.id = "prod"
mock_config.return_value.get_environments.return_value = [mock_env]
mock_deps["config"].get_environments.return_value = [mock_env]
# Mock resource service response
mock_service.return_value.get_dashboards_with_status.return_value = [
{
"id": 1,
"title": "Sales Report",
"slug": "sales",
"git_status": {"branch": "main", "sync_status": "OK"},
"last_task": {"task_id": "task-1", "status": "SUCCESS"}
}
]
# Mock permission
mock_perm.return_value = lambda: True
mock_client = MagicMock()
detail_payload = {
"id": 42, "title": "Detail", "charts": [], "datasets": [],
"chart_count": 0, "dataset_count": 0
}
mock_client.get_dashboard_detail.return_value = detail_payload
mock_client_cls.return_value = mock_client
response = client.get("/api/dashboards?env_id=prod")
response = client.get("/api/dashboards/42?env_id=prod")
assert response.status_code == 200
data = response.json()
assert "dashboards" in data
assert len(data["dashboards"]) == 1
assert data["dashboards"][0]["title"] == "Sales Report"
# Validate against Pydantic model
DashboardsResponse(**data)
assert data["id"] == 42
DashboardDetailResponse(**data)
# [/DEF:test_get_dashboards_success:Function]
def test_get_dashboard_detail_env_not_found(mock_deps):
mock_deps["config"].get_environments.return_value = []
response = client.get("/api/dashboards/42?env_id=missing")
assert response.status_code == 404
# [DEF:test_get_dashboards_env_not_found:Function]
# @TEST: GET /api/dashboards returns 404 if env_id missing
# @PRE: env_id does not exist
# @POST: Returns 404 error
def test_get_dashboards_env_not_found():
with patch("src.api.routes.dashboards.get_config_manager") as mock_config, \
patch("src.api.routes.dashboards.has_permission") as mock_perm:
# --- 4. get_dashboard_tasks_history tests ---
def test_get_dashboard_tasks_history_success(mock_deps):
now = datetime.now(timezone.utc)
task1 = MagicMock(id="t1", plugin_id="superset-backup", status="SUCCESS", started_at=now, finished_at=None, params={"env": "prod", "dashboards": [42]}, result={})
mock_deps["task"].get_all_tasks.return_value = [task1]
response = client.get("/api/dashboards/42/tasks?env_id=prod")
assert response.status_code == 200
data = response.json()
assert data["dashboard_id"] == 42
assert len(data["items"]) == 1
DashboardTaskHistoryResponse(**data)
def test_get_dashboard_tasks_history_sorting(mock_deps):
"""@POST: Response contains sorted task history (newest first)."""
from datetime import timedelta
now = datetime.now(timezone.utc)
older = now - timedelta(hours=2)
newest = now
task_old = MagicMock(id="t-old", plugin_id="superset-backup", status="SUCCESS",
started_at=older, finished_at=None,
params={"env": "prod", "dashboards": [42]}, result={})
task_new = MagicMock(id="t-new", plugin_id="superset-backup", status="RUNNING",
started_at=newest, finished_at=None,
params={"env": "prod", "dashboards": [42]}, result={})
# Provide in wrong order to verify the endpoint sorts
mock_deps["task"].get_all_tasks.return_value = [task_old, task_new]
response = client.get("/api/dashboards/42/tasks?env_id=prod")
assert response.status_code == 200
data = response.json()
assert len(data["items"]) == 2
# Newest first
assert data["items"][0]["id"] == "t-new"
assert data["items"][1]["id"] == "t-old"
# --- 5. get_dashboard_thumbnail tests ---
def test_get_dashboard_thumbnail_success(mock_deps):
with patch("src.api.routes.dashboards.SupersetClient") as mock_client_cls:
mock_env = MagicMock(); mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_client = MagicMock()
mock_response = MagicMock(status_code=200, content=b"img", headers={"Content-Type": "image/png"})
mock_client.network.request.side_effect = lambda method, endpoint, **kw: {"image_url": "url"} if method == "POST" else mock_response
mock_client_cls.return_value = mock_client
response = client.get("/api/dashboards/42/thumbnail?env_id=prod")
assert response.status_code == 200
assert response.content == b"img"
def test_get_dashboard_thumbnail_env_not_found(mock_deps):
mock_deps["config"].get_environments.return_value = []
response = client.get("/api/dashboards/42/thumbnail?env_id=missing")
assert response.status_code == 404
def test_get_dashboard_thumbnail_202(mock_deps):
"""@POST: Returns 202 when thumbnail is being prepared by Superset."""
with patch("src.api.routes.dashboards.SupersetClient") as mock_client_cls:
mock_env = MagicMock(); mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_client = MagicMock()
mock_config.return_value.get_environments.return_value = []
mock_perm.return_value = lambda: True
# POST cache_dashboard_screenshot returns image_url
mock_client.network.request.side_effect = [
{"image_url": "/api/v1/dashboard/42/thumbnail/abc123/"}, # POST
MagicMock(status_code=202, json=lambda: {"message": "Thumbnail is being generated"},
headers={"Content-Type": "application/json"}) # GET thumbnail -> 202
]
mock_client_cls.return_value = mock_client
response = client.get("/api/dashboards?env_id=nonexistent")
assert response.status_code == 404
assert "Environment not found" in response.json()["detail"]
response = client.get("/api/dashboards/42/thumbnail?env_id=prod")
assert response.status_code == 202
assert "Thumbnail is being generated" in response.json()["message"]
# [/DEF:test_get_dashboards_env_not_found:Function]
# --- 6. migrate_dashboards tests ---
def test_migrate_dashboards_success(mock_deps):
mock_s = MagicMock(); mock_s.id = "s"
mock_t = MagicMock(); mock_t.id = "t"
mock_deps["config"].get_environments.return_value = [mock_s, mock_t]
mock_deps["task"].create_task = AsyncMock(return_value=MagicMock(id="task-123"))
response = client.post("/api/dashboards/migrate", json={
"source_env_id": "s", "target_env_id": "t", "dashboard_ids": [1]
})
assert response.status_code == 200
assert response.json()["task_id"] == "task-123"
def test_migrate_dashboards_pre_checks(mock_deps):
# Missing IDs
response = client.post("/api/dashboards/migrate", json={
"source_env_id": "s", "target_env_id": "t", "dashboard_ids": []
})
assert response.status_code == 400
assert "At least one dashboard ID must be provided" in response.json()["detail"]
def test_migrate_dashboards_env_not_found(mock_deps):
"""@PRE: source_env_id and target_env_id are valid environment IDs."""
mock_deps["config"].get_environments.return_value = []
response = client.post("/api/dashboards/migrate", json={
"source_env_id": "ghost", "target_env_id": "t", "dashboard_ids": [1]
})
assert response.status_code == 404
assert "Source environment not found" in response.json()["detail"]
# --- 7. backup_dashboards tests ---
def test_backup_dashboards_success(mock_deps):
mock_env = MagicMock(); mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_deps["task"].create_task = AsyncMock(return_value=MagicMock(id="backup-123"))
response = client.post("/api/dashboards/backup", json={
"env_id": "prod", "dashboard_ids": [1]
})
assert response.status_code == 200
assert response.json()["task_id"] == "backup-123"
def test_backup_dashboards_pre_checks(mock_deps):
response = client.post("/api/dashboards/backup", json={
"env_id": "prod", "dashboard_ids": []
})
assert response.status_code == 400
def test_backup_dashboards_env_not_found(mock_deps):
"""@PRE: env_id is a valid environment ID."""
mock_deps["config"].get_environments.return_value = []
response = client.post("/api/dashboards/backup", json={
"env_id": "ghost", "dashboard_ids": [1]
})
assert response.status_code == 404
assert "Environment not found" in response.json()["detail"]
def test_backup_dashboards_with_schedule(mock_deps):
"""@POST: If schedule is provided, a scheduled task is created."""
mock_env = MagicMock(); mock_env.id = "prod"
mock_deps["config"].get_environments.return_value = [mock_env]
mock_deps["task"].create_task = AsyncMock(return_value=MagicMock(id="sched-456"))
response = client.post("/api/dashboards/backup", json={
"env_id": "prod", "dashboard_ids": [1], "schedule": "0 0 * * *"
})
assert response.status_code == 200
assert response.json()["task_id"] == "sched-456"
# Verify schedule was propagated to create_task
call_kwargs = mock_deps["task"].create_task.call_args
task_params = call_kwargs.kwargs.get("params") or call_kwargs[1].get("params", {})
assert task_params["schedule"] == "0 0 * * *"
# --- 8. Internal logic: _task_matches_dashboard ---
from src.api.routes.dashboards import _task_matches_dashboard
def test_task_matches_dashboard_logic():
task = MagicMock(plugin_id="superset-backup", params={"dashboards": [42], "env": "prod"})
assert _task_matches_dashboard(task, 42, "prod") is True
assert _task_matches_dashboard(task, 43, "prod") is False
assert _task_matches_dashboard(task, 42, "dev") is False
llm_task = MagicMock(plugin_id="llm_dashboard_validation", params={"dashboard_id": 42, "environment_id": "prod"})
assert _task_matches_dashboard(llm_task, 42, "prod") is True
assert _task_matches_dashboard(llm_task, 42, None) is True
# [/DEF:backend.tests.test_dashboards_api:Module]

View File

@@ -1,3 +1,11 @@
# [DEF:tests.test_logger:Module]
# @TIER: STANDARD
# @SEMANTICS: logging, tests, belief_state
# @PURPOSE: Unit tests for the custom logger formatters and configuration context manager.
# @LAYER: Logging (Tests)
# @RELATION: VERIFIES -> src/core/logger.py
# @INVARIANT: All required log statements must correctly check the threshold.
import pytest
from src.core.logger import (
belief_scope,
@@ -210,4 +218,5 @@ def test_enable_belief_state_flag(caplog):
enable_belief_state=True
)
configure_logger(config)
# [/DEF:test_enable_belief_state_flag:Function]
# [/DEF:test_enable_belief_state_flag:Function]
# [/DEF:tests.test_logger:Module]

View File

@@ -1,6 +1,6 @@
import pytest
from fastapi.testclient import TestClient
from unittest.mock import MagicMock
from unittest.mock import MagicMock, AsyncMock
from src.app import app
from src.dependencies import get_config_manager, get_task_manager, get_resource_service, has_permission
@@ -27,10 +27,10 @@ def mock_deps():
task_manager.get_all_tasks.return_value = []
# Mock dashboards
resource_service.get_dashboards_with_status.return_value = [
resource_service.get_dashboards_with_status = AsyncMock(return_value=[
{"id": 1, "title": "Sales", "slug": "sales", "git_status": {"branch": "main", "sync_status": "OK"}, "last_task": None},
{"id": 2, "title": "Marketing", "slug": "mkt", "git_status": None, "last_task": {"task_id": "t1", "status": "SUCCESS"}}
]
])
app.dependency_overrides[get_config_manager] = lambda: config_manager
app.dependency_overrides[get_task_manager] = lambda: task_manager
@@ -39,6 +39,10 @@ def mock_deps():
# Bypass permission check
mock_user = MagicMock()
mock_user.username = "testadmin"
mock_user.roles = []
admin_role = MagicMock()
admin_role.name = "Admin"
mock_user.roles.append(admin_role)
# Override both get_current_user and has_permission
from src.dependencies import get_current_user
@@ -85,9 +89,9 @@ def test_get_dashboards_search(mock_deps):
# @TEST: Negative - Service failure returns 503
def test_get_datasets_success(mock_deps):
mock_deps["resource"].get_datasets_with_status.return_value = [
mock_deps["resource"].get_datasets_with_status = AsyncMock(return_value=[
{"id": 1, "table_name": "orders", "schema": "public", "database": "db1", "mapped_fields": {"total": 10, "mapped": 5}, "last_task": None}
]
])
response = client.get("/api/datasets?env_id=env1")
assert response.status_code == 200
@@ -102,10 +106,10 @@ def test_get_datasets_not_found(mock_deps):
assert response.status_code == 404
def test_get_datasets_search(mock_deps):
mock_deps["resource"].get_datasets_with_status.return_value = [
mock_deps["resource"].get_datasets_with_status = AsyncMock(return_value=[
{"id": 1, "table_name": "orders", "schema": "public", "database": "db1", "mapped_fields": {"total": 10, "mapped": 5}, "last_task": None},
{"id": 2, "table_name": "users", "schema": "public", "database": "db1", "mapped_fields": {"total": 5, "mapped": 5}, "last_task": None}
]
])
response = client.get("/api/datasets?env_id=env1&search=orders")
assert response.status_code == 200
@@ -114,10 +118,39 @@ def test_get_datasets_search(mock_deps):
assert data["datasets"][0]["table_name"] == "orders"
def test_get_datasets_service_failure(mock_deps):
mock_deps["resource"].get_datasets_with_status.side_effect = Exception("Superset down")
mock_deps["resource"].get_datasets_with_status = AsyncMock(side_effect=Exception("Superset down"))
response = client.get("/api/datasets?env_id=env1")
assert response.status_code == 503
assert "Failed to fetch datasets" in response.json()["detail"]
# [/DEF:test_datasets_api:Test]
# [DEF:test_pagination_boundaries:Test]
# @PURPOSE: Verify pagination validation for GET endpoints
# @TEST: page<1 and page_size>100 return 400
def test_get_dashboards_pagination_zero_page(mock_deps):
"""@TEST_EDGE: pagination_zero_page -> {page:0, status:400}"""
response = client.get("/api/dashboards?env_id=env1&page=0")
assert response.status_code == 400
assert "Page must be >= 1" in response.json()["detail"]
def test_get_dashboards_pagination_oversize(mock_deps):
"""@TEST_EDGE: pagination_oversize -> {page_size:101, status:400}"""
response = client.get("/api/dashboards?env_id=env1&page_size=101")
assert response.status_code == 400
assert "Page size must be between 1 and 100" in response.json()["detail"]
def test_get_datasets_pagination_zero_page(mock_deps):
"""@TEST_EDGE: pagination_zero_page on datasets"""
response = client.get("/api/datasets?env_id=env1&page=0")
assert response.status_code == 400
def test_get_datasets_pagination_oversize(mock_deps):
"""@TEST_EDGE: pagination_oversize on datasets"""
response = client.get("/api/datasets?env_id=env1&page_size=101")
assert response.status_code == 400
# [/DEF:test_pagination_boundaries:Test]

0
docs/architecture.md Normal file
View File

Some files were not shown because too many files have changed in this diff Show More