/DevOpsMadDog/Aldeci

Wiki directory

Browse AI-generated documentation for any repository.

Feature: Decision Explainability

Relevant source files

The following files were used as context for generating this wiki page:

The Decision Explainability feature provides mechanisms to understand and interpret the automated decisions made by the Aldeci platform. It aims to deliver "explainable verdicts" by identifying the primary drivers behind a decision and generating human-readable narratives. This is achieved through two main components: a high-level factor analysis within the StageRunner and a granular, feature-level attribution analysis provided by the ExplainabilityService.

This feature is crucial for providing transparency, building trust in the automated system, and generating auditable records. It produces outputs like "top factors" influencing a decision, compliance rollups, and marketplace recommendations based on the analysis.

Sources: core/stage_runner.py:612-619, services/explainability.py:5-6, artifacts/upstream_doc_index.json:68-68

High-Level Decision Factors

The StageRunner class is responsible for orchestrating the various stages of the pipeline. During the decision stage, it synthesizes outputs from previous stages to determine a final verdict and identifies the most significant factors that contributed to it.

Sources: core/stage_runner.py:126-129, core/stage_runner.py:612-619

Decision Processing Flow

The _process_decision method in StageRunner collects all relevant documents from the pipeline run, calculates the top factors, determines a verdict, and bundles all information into an evidence package.

The following diagram illustrates the data flow for processing a decision and identifying top factors.

Generating architecture diagram...

Sources: core/stage_runner.py:612-649

Top Factor Identification

The _decision_factors method identifies up to three key reasons for a decision by examining specific conditions in the build, test, deploy, and operate stage outputs. If no negative conditions are met, a "Stable release" factor is returned.

The table below summarizes the conditions checked to determine the top factors.

Factor Name	Weight	Condition	Rationale	Source File & Lines
Critical/High Severity Detected	0.4 / 0.32	`test.report.json` contains 'critical' or 'high' severity findings.	"Testing summary reported {count} {level} findings"	`core/stage_runner.py:722-735`
Guardrail Violation	0.4	`deploy.manifest.json` indicates publicly exposed storage buckets.	"Deployment posture shows publicly exposed storage buckets"	`core/stage_runner.py:736-743`
Elevated Exploit Pressure	0.35	`operate.snapshot.json` contains hits from the Known Exploited Vulnerability (KEV) feed.	"Known exploited vulnerability feed triggered for monitored components"	`core/stage_runner.py:744-751`
Stable Release	0.2	None of the above conditions are met.	"No critical findings, posture gaps, or exploit signals detected"	`core/stage_runner.py:752-758`

Sources: core/stage_runner.py:716-759

Granular Feature Attribution (`ExplainabilityService`)

The ExplainabilityService provides a deterministic, lightweight method for generating feature attributions, similar in concept to SHAP/LIME, without requiring heavy machine learning library dependencies. It calculates how much each feature in a given vector contributed to a deviation from a historical baseline.

Sources: services/explainability.py:31-33

Class Architecture

The ExplainabilityService is a self-contained class designed to be primed with baseline data and then used to explain new feature vectors.

This diagram shows the structure of the ExplainabilityService class.

Generating architecture diagram...

Sources: services/explainability.py:34-123

Key Methods

`prime_baseline()`

This method seeds the service with historical data. It calculates the mean value for each feature across a collection of training examples and stores it as the baseline for future comparisons.

Sources: services/explainability.py:37-51

`explain()`

This method calculates the "contribution" of each feature in a new vector. The contribution is the difference between the feature's current value and its established baseline mean. This indicates how much a feature's value deviates from the historical norm.

The following flowchart shows the logic of the explain method.

Generating architecture diagram...

Sources: services/explainability.py:53-65

`generate_narrative()`

This method creates a human-readable summary of the analysis. It identifies the top three features with the highest absolute contribution values (positive or negative) and constructs a sentence describing their impact. If no features are influential, it returns a default message.

Example output: "feature_x increased risk by 0.45, feature_y decreased risk by 0.20"

Sources: services/explainability.py:67-81

`enrich_findings()`

This method integrates the explainability analysis directly into a list of findings. For each finding, it extracts a feature vector, calculates contributions using explain(), generates a summary with generate_narrative(), and appends the results into a new explainability dictionary within the finding object.

The resulting structure within a finding looks like this:

{
  "finding_id": "...",
  "severity": "high",
  "explainability": {
    "contributions": {
      "feature_a": 0.5,
      "feature_b": -0.1
    },
    "narrative": "feature a increased risk by 0.50"
  }
}

Sources: services/explainability.py:83-123, tests/test_explainability_service.py:27-49

Summary

The Decision Explainability feature in Aldeci provides a multi-layered approach to interpreting system decisions. At a high level, the StageRunner identifies coarse-grained "top factors" based on critical events like guardrail violations or KEV hits. At a more detailed level, the ExplainabilityService offers granular, feature-by-feature attribution against a historical baseline. Together, these components provide both immediate, high-impact reasons and nuanced, data-driven explanations, enhancing the auditability and trustworthiness of the platform's automated decisions.

Sources: core/stage_runner.py:716-759, services/explainability.py:31-33## FULL FILE CONTEXT SUMMARY
Query: You are an expert technical writer and software architect.
Your task is to generate a comprehensive and accurate technical wiki page in Markdown format about a specific feature, system, or module within a given software project.

You will be given:

The "[WIKI_PAGE_TOPIC]" for the page you need to create.
A list of "[RELEVANT_SOURCE_FILES]" from the project that you MUST use as the sole basis for the content. You MUST use AT LEAST 5 relevant source files for comprehensive coverage - if fewer are provided, search for additional related files in the codebase.

CRITICAL STARTING INSTRUCTION:
The very first thing on the page MUST be a

block listing ALL the [RELEVANT_SOURCE_FILES] you used to generate the content. There MUST be AT LEAST 5 source files listed - if fewer were provided, you MUST find additional related files to include.
Format it exactly like this:

Relevant source files

Remember, do not provide any acknowledgements, disclaimers, apologies, or any other preface before the <details> block. JUST START with the <details> block.
The following files were used as context for generating this wiki page:

services/explainability.py

Immediately after the

block, the main title of the page should be a H1 Markdown heading: # Feature: Decision Explainability.

Based ONLY on the content of the [RELEVANT_SOURCE_FILES]:

Introduction: Start with a concise introduction (1-2 paragraphs) explaining the purpose, scope, and high-level overview of "Feature: Decision Explainability" within the context of the overall project. If relevant, and if information is available, link to other potential wiki pages using the format Link Text.
Detailed Sections: Break down "Feature: Decision Explainability" into logical sections using H2 (##) and H3 (###) Markdown headings. For each section:
- Explain the architecture, components, data flow, or logic relevant to the section's focus, as evidenced in the source files.
- Identify key functions, classes, data structures, API endpoints, or configuration elements pertinent to that section.
Mermaid Diagrams:
- EXTENSIVELY use Mermaid diagrams (e.g., flowchart TD, sequenceDiagram, classDiagram, erDiagram, graph TD) to visually represent architectures, flows, relationships, and schemas found in the source files.
- Ensure diagrams are accurate and directly derived information from the [RELEVANT_SOURCE_FILES].
- Provide a brief explanation before or after each diagram to give context.
- CRITICAL diagram requirements for optimal rendering:
- Flow diagrams: Use "graph TD" (top-down) or "flowchart TD" directives for better vertical layout
- Node labels: Keep node labels concise but descriptive (under 25 characters for readability)
- Node IDs: Use alphanumeric characters and underscores only (avoid spaces, special characters)
- Connections: Use standard arrow syntax (-->, ---, -.->) for reliable rendering
- Sequence diagrams:
  - Start with "sequenceDiagram" directive on its own line
  - Use participant names without spaces (use underscores if needed)
  - Define participants explicitly when needed: participant User as "User Interface"
  - Use correct arrow types:
    - ->> for synchronous calls/requests
    - -->> for responses
    - -x for failed/error messages
    - --x for failed responses
  - Add activation boxes sparingly with +/- notation
  - Use "Note over" or "Note right of" for clarifications
- Class diagrams: Use standard UML notation with proper relationship syntax
- ER diagrams: Use entity relationship syntax with proper cardinality notations
- Quality guidelines:
- Test diagram syntax mentally before including
- If a diagram becomes too complex, split into multiple focused diagrams
- Ensure proper closing of all brackets and quotes
- Use consistent naming conventions within each diagram
- Add line breaks for readability in complex diagrams
- Example patterns (GOOD vs BAD):
```
GOOD Flow Diagram:
```

Generating architecture diagram...

   BAD Flow Diagram:

Generating architecture diagram...

   GOOD Sequence Diagram:

Generating architecture diagram...

```

4. Tables:
* Use Markdown tables to summarise information such as:
* Key features or components and their descriptions.
* API endpoint parameters, types, and descriptions.
* Configuration options, their types, and default values.
* Data model fields, types, constraints, and descriptions.

Code Snippets (ENTIRELY OPTIONAL):
- Include short, relevant code snippets (e.g., Python, Java, JavaScript, SQL, JSON, YAML) directly from the [RELEVANT_SOURCE_FILES] to illustrate key implementation details, data structures, or configurations.
- Ensure snippets are well-formatted within Markdown code blocks with appropriate language identifiers.
Source Citations (EXTREMELY IMPORTANT):
- For EVERY piece of significant information, explanation, diagram, table entry, or code snippet, you MUST cite the specific source file(s) and relevant line numbers from which the information was derived.
- Place citations at the end of the paragraph, under the diagram/table, or after the code snippet.
- Use the exact format: Sources: [filename.ext:start_line-end_line](https://github.com/DevOpsMadDog/Aldeci/blob/HEAD/filename.ext%3Astart_line-end_line) for a range, or Sources: [filename.ext:line_number](https://github.com/DevOpsMadDog/Aldeci/blob/HEAD/filename.ext%3Aline_number) for a single line. Multiple files can be cited: Sources: [file1.ext:1-10](https://github.com/DevOpsMadDog/Aldeci/blob/HEAD/file1.ext#L1-L10), [file2.ext:5](https://github.com/DevOpsMadDog/Aldeci/blob/HEAD/file2.ext#L5), [dir/file3.ext](https://github.com/DevOpsMadDog/Aldeci/blob/HEAD/dir/file3.ext) (if the whole file is relevant and line numbers are not applicable or too broad).
- If an entire section is overwhelmingly based on one or two files, you can cite them under the section heading in addition to more specific citations within the section.
- You MUST cite AT LEAST 5 different source files throughout the wiki page to ensure comprehensive coverage.
Technical Accuracy: All information must be derived SOLELY from the [RELEVANT_SOURCE_FILES]. Do not infer, invent, or use external knowledge about similar systems or common practices unless it's directly supported by the provided code. If information is not present in the provided files, do not include it or explicitly state its absence if crucial to the topic.
Clarity and Conciseness: Use clear, professional, and concise technical language suitable for other developers working on or learning about the project. Avoid unnecessary jargon, but use correct technical terms where appropriate.
Conclusion/Summary: End with a brief summary paragraph if appropriate for "Feature: Decision Explainability", reiterating the key aspects covered and their significance within the project.

IMPORTANT: Generate the content in English language.

Remember:

Ground every claim in the provided source files.
Prioritize accuracy and direct representation of the code's functionality and structure.
Structure the document logically for easy understanding by other developers.

Total Files Included: 5
Total Files Skipped: 0
Total Context Tokens: 96,380 / 800,000 (12.0%)
Remaining Token Budget: 703,620

Included Files:

artifacts/upstream_symbol_index.json (48,544 tokens)
core/stage_runner.py (7,954 tokens)
artifacts/upstream_doc_index.json (37,837 tokens)
tools/importer/mine_docs.py (1,085 tokens)
services/explainability.py (960 tokens)

{
"files": [
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".coveragerc"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": ".emergent/emergent.yml"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".emergent/summary.txt"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".env.example"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/HEAD"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/config"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/description"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/applypatch-msg.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/commit-msg.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/fsmonitor-watchman.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/post-update.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/pre-applypatch.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/pre-commit.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/pre-merge-commit.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/pre-push.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/pre-rebase.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/pre-receive.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/prepare-commit-msg.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/push-to-checkout.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/sendemail-validate.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/hooks/update.sample"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/index"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/info/exclude"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/logs/HEAD"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/logs/refs/heads/main"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/logs/refs/remotes/origin/HEAD"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/objects/pack/pack-8cdaf39776ff81276fb8ac18c6fc8bbf6a277e81.idx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/objects/pack/pack-8cdaf39776ff81276fb8ac18c6fc8bbf6a277e81.pack"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/objects/pack/pack-8cdaf39776ff81276fb8ac18c6fc8bbf6a277e81.rev"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/packed-refs"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/refs/heads/main"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/refs/remotes/origin/HEAD"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".git/shallow"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": ".github/workflows/ci.yml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": ".github/workflows/fixops-ci.yml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": ".github/workflows/provenance.yml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": ".github/workflows/qa.yml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": ".github/workflows/release-sign.yml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": ".github/workflows/repro-verify.yml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": ".pre-commit-config.yaml"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": ".secrets.baseline"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "ARCHITECTURE.md"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "BACKLOG.csv"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "CHANGELOG.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "CONTRIBUTING.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "HANDBOOK.md"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "Makefile"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "ONBOARDING.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "README.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "ROADMAP.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/README.md"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/backend_legacy/init.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/backend_legacy/app.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/backend_legacy/normalizers.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/backend_legacy/pipeline.py"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/.env.example"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/BANK_DEPLOYMENT_GUIDE.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/COMPLETE_DATA_FLOW.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/COMPREHENSIVE_GUIDE.md"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/Dockerfile"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/ENHANCED_VERSION.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/ENTERPRISE_DEPLOYMENT_GUIDE.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/FOLDER_README.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/PRODUCTION_DEPLOYMENT.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/README_BANK_DEPLOYMENT.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/RESEARCH_ROADMAP.md"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/alembic.ini"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/backstage/app-config.yaml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/backstage/catalog-info.yaml"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/backstage/plugins/fixops-overview-card.tsx"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/backstage/template.yaml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/backstage/terraform-deployment-template.yaml"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/create_admin_user.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/create_all_tables.py"
},
{
"classes": [],
"functions": [],
"language": "JSON",
"module": null,
"path": "WIP/code/enterprise_legacy/data/golden_regression_cases.json"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/deploy-bank.sh"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/deploy-complete.sh"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/deploy-production.sh"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/docker-compose.yml"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/docs/ARCHITECTURE.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/docs/ENTERPRISE_AUDIT_REPORT.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/docs/FIXOPS_SUGGESTIONS_SUMMARY.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/docs/INSTALL.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/docs/MARKETPLACE_GUIDE.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/docs/REQUIREMENTS.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/docs/REQUIREMENTS_COMPREHENSIVE.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/docs/ROADMAP.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/docs/SSVC.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/docs/index.md"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/fixops_enterprise.db"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/Dockerfile"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/index.html"
},
{
"classes": [],
"functions": [],
"language": "JSON",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/package.json"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/App.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/components/Layout.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/components/LoadingSpinner.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/components/ModeToggle.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/components/SecurityLayout.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/components/Tooltip.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/contexts/AuthContext.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/index.css"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/main.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/pages/ArchitectDashboard.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/pages/ArchitectureCenter.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/pages/ArchitecturePage.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/pages/CISODashboard.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/pages/CommandCenter.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/pages/DeveloperDashboard.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/pages/DeveloperOps.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/pages/EnhancedDashboard.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/pages/ExecutiveBriefing.jsx"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/pages/InstallPage.jsx"
},
{
"classes": [],
"functions": [],
"language": "JavaScript",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/src/utils/api.js"
},
{
"classes": [],
"functions": [],
"language": "JavaScript",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/tailwind.config.js"
},
{
"classes": [],
"functions": [],
"language": "JavaScript",
"module": null,
"path": "WIP/code/enterprise_legacy/frontend/vite.config.js"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/kubernetes/backend-deployment.yaml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/kubernetes/configmap.yaml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/kubernetes/frontend-deployment.yaml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/kubernetes/ingress.yaml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/kubernetes/namespace.yaml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/kubernetes/pvc.yaml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/kubernetes/rbac.yaml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/kubernetes/secret.yaml"
},
{
"classes": [],
"functions": [],
"language": "YAML",
"module": null,
"path": "WIP/code/enterprise_legacy/kubernetes/services.yaml"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/policies/sbom.rego"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/policies/vulnerability.rego"
},
{
"classes": [],
"functions": [],
"language": "JSON",
"module": null,
"path": "WIP/code/enterprise_legacy/postman/FixOps-Bank-API-Collection.json"
},
{
"classes": [],
"functions": [],
"language": "JSON",
"module": null,
"path": "WIP/code/enterprise_legacy/postman/FixOps-Bank-Development.postman_environment.json"
},
{
"classes": [],
"functions": [],
"language": "JSON",
"module": null,
"path": "WIP/code/enterprise_legacy/postman/FixOps-Bank-Production.postman_environment.json"
},
{
"classes": [],
"functions": [],
"language": "JSON",
"module": null,
"path": "WIP/code/enterprise_legacy/postman/FixOps-CICD-Tests.postman_collection.json"
},
{
"classes": [],
"functions": [],
"language": "JSON",
"module": null,
"path": "WIP/code/enterprise_legacy/postman/FixOps-Performance-Tests.postman_collection.json"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/postman/POSTMAN_COMPLETION.md"
},
{
"classes": [],
"functions": [],
"language": "Markdown",
"module": null,
"path": "WIP/code/enterprise_legacy/postman/README.md"
},
{
"classes": [],
"functions": [],
"language": "JSON",
"module": null,
"path": "WIP/code/enterprise_legacy/postman/sample-data/sample-sarif.json"
},
{
"classes": [],
"functions": [],
"language": "JSON",
"module": null,
"path": "WIP/code/enterprise_legacy/postman/sample-data/sample-sbom.json"
},
{
"classes": [],
"functions": [],
"language": "JSON",
"module": null,
"path": "WIP/code/enterprise_legacy/postman/workspace.json"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/quick_start.py"
},
{
"classes": [],
"functions": [],
"language": "Unknown",
"module": null,
"path": "WIP/code/enterprise_legacy/requirements.txt"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/run_enterprise.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/scripts/run_migrations.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/scripts/run_real_cve_playbook.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/scripts/seed_demo_data.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/server.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/business_context.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/business_context_enhanced.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/cicd.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/decisions.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/docs.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/enhanced.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/evidence.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/feeds.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/marketplace.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/monitoring.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/oss_tools.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/policy.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/processing_layer.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/production_readiness.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/sample_data_demo.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/scans.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/system.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/api/v1/system_mode.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/cli/main.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/config/settings.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/core/exceptions.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/core/middleware.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/core/security.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/db/migrations/init.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/db/migrations/env.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/db/migrations/versions/001_initial_schema.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/db/migrations/versions/002_add_kev_waivers.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/db/session.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/main.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/models/init.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/models/base.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/models/base_sqlite.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/models/security.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/models/security_sqlite.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/models/user.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/models/user_sqlite.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/models/waivers.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/schemas/user.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/advanced_llm_engine.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/business_context_processor.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/cache_service.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/chatgpt_client.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/compliance_engine.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/correlation_engine.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/decision_engine.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/enhanced_decision_engine.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/evidence_export.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/evidence_lake.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/explainability.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/feeds_service.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/fix_engine.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/golden_regression_store.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/knowledge_graph.py"
},
{
"classes": [],
"functions": [],
"language": "Python",
"module": null,
"path": "WIP/code/enterprise_legacy/src/services/llm_explanation_engine.py"

Feature: Decision Explainability

Relevant source files

The following files were used as context for generating this wiki page:

Sources: core/stage_runner.py:612-619, services/explainability.py:5-6, artifacts/upstream_doc_index.json:68-68

High-Level Decision Factors

Sources: core/stage_runner.py:126-129, core/stage_runner.py:612-619

Decision Processing Flow

The following diagram illustrates the data flow for processing a decision and identifying top factors.

Generating architecture diagram...

Sources: core/stage_runner.py:612-649

Top Factor Identification

The table below summarizes the conditions checked to determine the top factors.

Factor Name	Weight	Condition	Rationale	Source File & Lines
Critical/High Severity Detected	0.4 / 0.32	`test.report.json` contains 'critical' or 'high' severity findings.	"Testing summary reported {count} {level} findings"	`core/stage_runner.py:722-735`
Guardrail Violation	0.4	`deploy.manifest.json` indicates publicly exposed storage buckets.	"Deployment posture shows publicly exposed storage buckets"	`core/stage_runner.py:736-743`
Elevated Exploit Pressure	0.35	`operate.snapshot.json` contains hits from the Known Exploited Vulnerability (KEV) feed.	"Known exploited vulnerability feed triggered for monitored components"	`core/stage_runner.py:744-751`
Stable Release	0.2	None of the above conditions are met.	"No critical findings, posture gaps, or exploit signals detected"	`core/stage_runner.py:752-758`

Sources: core/stage_runner.py:716-759

Granular Feature Attribution (`ExplainabilityService`)

Sources: services/explainability.py:31-33

Class Architecture

The ExplainabilityService is a self-contained class designed to be primed with baseline data and then used to explain new feature vectors.

This diagram shows the structure of the ExplainabilityService class.

Generating architecture diagram...

Sources: services/explainability.py:34-123

Key Methods

`prime_baseline()`

This method seeds the service with historical data. It calculates the mean value for each feature across a collection of training examples and stores it as the baseline for future comparisons.

Sources: services/explainability.py:37-51

`explain()`

The following flowchart shows the logic of the explain method.

Generating architecture diagram...

Sources: services/explainability.py:53-65

`generate_narrative()`

Example output: "feature_x increased risk by 0.45, feature_y decreased risk by 0.20"

Sources: services/explainability.py:67-81

`enrich_findings()`

The resulting structure within a finding looks like this:

{
  "finding_id": "...",
  "severity": "high",
  "explainability": {
    "contributions": {
      "feature_a": 0.5,
      "feature_b": -0.1
    },
    "narrative": "feature a increased risk by 0.50"
  }
}

Sources: services/explainability.py:83-123, tests/test_explainability_service.py:27-49

Summary

You will be given:

The "[WIKI_PAGE_TOPIC]" for the page you need to create.
A list of "[RELEVANT_SOURCE_FILES]" from the project that you MUST use as the sole basis for the content. You MUST use AT LEAST 5 relevant source files for comprehensive coverage - if fewer are provided, search for additional related files in the codebase.

CRITICAL STARTING INSTRUCTION:
The very first thing on the page MUST be a

Relevant source files

services/explainability.py

Immediately after the

block, the main title of the page should be a H1 Markdown heading: # Feature: Decision Explainability.

Based ONLY on the content of the [RELEVANT_SOURCE_FILES]:

Introduction: Start with a concise introduction (1-2 paragraphs) explaining the purpose, scope, and high-level overview of "Feature: Decision Explainability" within the context of the overall project. If relevant, and if information is available, link to other potential wiki pages using the format Link Text.
Detailed Sections: Break down "Feature: Decision Explainability" into logical sections using H2 (##) and H3 (###) Markdown headings. For each section:
- Explain the architecture, components, data flow, or logic relevant to the section's focus, as evidenced in the source files.
- Identify key functions, classes, data structures, API endpoints, or configuration elements pertinent to that section.
Mermaid Diagrams:
- EXTENSIVELY use Mermaid diagrams (e.g., flowchart TD, sequenceDiagram, classDiagram, erDiagram, graph TD) to visually represent architectures, flows, relationships, and schemas found in the source files.
- Ensure diagrams are accurate and directly derived information from the [RELEVANT_SOURCE_FILES].
- Provide a brief explanation before or after each diagram to give context.
- CRITICAL diagram requirements for optimal rendering:
- Flow diagrams: Use "graph TD" (top-down) or "flowchart TD" directives for better vertical layout
- Node labels: Keep node labels concise but descriptive (under 25 characters for readability)
- Node IDs: Use alphanumeric characters and underscores only (avoid spaces, special characters)
- Connections: Use standard arrow syntax (-->, ---, -.->) for reliable rendering
- Sequence diagrams:
  - Start with "sequenceDiagram" directive on its own line
  - Use participant names without spaces (use underscores if needed)
  - Define participants explicitly when needed: participant User as "User Interface"
  - Use correct arrow types:
    - ->> for synchronous calls/requests
    - -->> for responses
    - -x for failed/error messages
    - --x for failed responses
  - Add activation boxes sparingly with +/- notation
  - Use "Note over" or "Note right of" for clarifications
- Class diagrams: Use standard UML notation with proper relationship syntax
- ER diagrams: Use entity relationship syntax with proper cardinality notations
- Quality guidelines:
- Test diagram syntax mentally before including
- If a diagram becomes too complex, split into multiple focused diagrams
- Ensure proper closing of all brackets and quotes
- Use consistent naming conventions within each diagram
- Add line breaks for readability in complex diagrams
- Example patterns (GOOD vs BAD):
```
GOOD Flow Diagram:
```

Generating architecture diagram...

   BAD Flow Diagram:

Generating architecture diagram...

   GOOD Sequence Diagram:

Generating architecture diagram...

```

Code Snippets (ENTIRELY OPTIONAL):
- Include short, relevant code snippets (e.g., Python, Java, JavaScript, SQL, JSON, YAML) directly from the [RELEVANT_SOURCE_FILES] to illustrate key implementation details, data structures, or configurations.
- Ensure snippets are well-formatted within Markdown code blocks with appropriate language identifiers.
Source Citations (EXTREMELY IMPORTANT):
- For EVERY piece of significant information, explanation, diagram, table entry, or code snippet, you MUST cite the specific source file(s) and relevant line numbers from which the information was derived.
- Place citations at the end of the paragraph, under the diagram/table, or after the code snippet.
- Use the exact format: Sources: [filename.ext:start_line-end_line](https://github.com/DevOpsMadDog/Aldeci/blob/HEAD/filename.ext%3Astart_line-end_line) for a range, or Sources: [filename.ext:line_number](https://github.com/DevOpsMadDog/Aldeci/blob/HEAD/filename.ext%3Aline_number) for a single line. Multiple files can be cited: Sources: [file1.ext:1-10](https://github.com/DevOpsMadDog/Aldeci/blob/HEAD/file1.ext#L1-L10), [file2.ext:5](https://github.com/DevOpsMadDog/Aldeci/blob/HEAD/file2.ext#L5), [dir/file3.ext](https://github.com/DevOpsMadDog/Aldeci/blob/HEAD/dir/file3.ext) (if the whole file is relevant and line numbers are not applicable or too broad).
- If an entire section is overwhelmingly based on one or two files, you can cite them under the section heading in addition to more specific citations within the section.
- You MUST cite AT LEAST 5 different source files throughout the wiki page to ensure comprehensive coverage.
Technical Accuracy: All information must be derived SOLELY from the [RELEVANT_SOURCE_FILES]. Do not infer, invent, or use external knowledge about similar systems or common practices unless it's directly supported by the provided code. If information is not present in the provided files, do not include it or explicitly state its absence if crucial to the topic.
Clarity and Conciseness: Use clear, professional, and concise technical language suitable for other developers working on or learning about the project. Avoid unnecessary jargon, but use correct technical terms where appropriate.
Conclusion/Summary: End with a brief summary paragraph if appropriate for "Feature: Decision Explainability", reiterating the key aspects covered and their significance within the project.

IMPORTANT: Generate the content in English language.

Remember:

Ground every claim in the provided source files.
Prioritize accuracy and direct representation of the code's functionality and structure.
Structure the document logically for easy understanding by other developers.

Total Files Included: 5
Total Files Skipped: 0
Total Context Tokens: 96,380 / 800,000 (12.0%)
Remaining Token Budget: 703,620

Included Files:

artifacts/upstream_symbol_index.json (48,544 tokens)
core/stage_runner.py (7,954 tokens)
artifacts/upstream_doc_index.json (37,837 tokens)
tools/importer/mine_docs.py (1,085 tokens)
services/explainability.py (960 tokens)

Feature: Decision Explainability

High-Level Decision Factors

Decision Processing Flow

Top Factor Identification

Granular Feature Attribution (ExplainabilityService)

Class Architecture

Key Methods

prime_baseline()

explain()

generate_narrative()

enrich_findings()

Summary

Included Files:

Feature: Decision Explainability

High-Level Decision Factors

Decision Processing Flow

Top Factor Identification

Granular Feature Attribution (ExplainabilityService)

Class Architecture

Key Methods

prime_baseline()

explain()

generate_narrative()

enrich_findings()

Summary

Included Files:

Granular Feature Attribution (`ExplainabilityService`)

`prime_baseline()`

`explain()`

`generate_narrative()`

`enrich_findings()`

Granular Feature Attribution (`ExplainabilityService`)

`prime_baseline()`

`explain()`

`generate_narrative()`

`enrich_findings()`