# sannicholas/corpus_script_optimization architecture

> Architecture diagram of the GitHub repository sannicholas/corpus_script_optimization, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sannicholas/corpus_script_optimization
- Repository: https://github.com/sannicholas/corpus_script_optimization

## Overview

Hermes Live Corpus Agent processes live-commerce scripts for compliance and quality: the CLI or web interface starts a pipeline, which selects pending corpus records, analyzes them with rules and optionally an LLM, revises issues, and persists outcomes. The repository also includes web-based corpus browsing/export and pipeline status, plus configurable database and LLM settings. The README is empty; workflow links rely on the shown excerpts and SOURCE INDEX, so links for unsampled pipeline internals are marked unverified.

Main entry points: [`out/production/Corpus_script_optimization/src/main.py`](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/main.py) (CLI pipeline), [`out/production/Corpus_script_optimization/src/web/app.py`](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/web/app.py) (Web pipeline), [`out/production/Corpus_script_optimization/src/db/connection.py`](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/db/connection.py) (Corpus database), [`out/production/Corpus_script_optimization/src/parser/reader.py`](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/parser/reader.py) (Corpus reader)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_entry["Entry points"]
  node_cli["CLI pipeline<br/>[main.py]"]
  node_web["Web interface<br/>[app.py]"]
  node_web_pipeline["Web pipeline<br/>[app.py]"]
end

subgraph group_pipeline["Corpus processing"]
  node_reader["Corpus reader<br/>[reader.py]"]
  node_writer["Corpus writer<br/>[writer.py]"]
end

subgraph group_analysis["Analysis and revision"]
  node_rules["Rule analysis<br/>[rule_engine.py]"]
  node_llm_analysis["LLM analysis<br/>[llm_analyzer.py]"]
  node_rule_revision["Rule revision<br/>[rule_revisor.py]"]
  node_llm_revision["LLM revision<br/>[llm_revisor.py]"]
end

subgraph group_data["Configuration and data"]
  node_corpus_model["Corpus models<br/>[corpus.py]"]
  node_database[("Corpus database<br/>[connection.py]")]
  node_settings["Application settings<br/>[settings.py]"]
  node_rule_data["Sensitive-word rules"]
end

node_operator(("Operator"))
node_llm_service{{"LLM provider"}}

node_operator -->|"runs"| node_cli
node_operator -->|"uses"| node_web
node_web -->|"starts"| node_web_pipeline
node_cli -.->|"selects batches"| node_reader
node_cli -.->|"analyzes"| node_rules
node_cli -.->|"analyzes"| node_llm_analysis
node_cli -.->|"revises"| node_rule_revision
node_cli -.->|"revises"| node_llm_revision
node_cli -.->|"persists results"| node_writer
node_web_pipeline -.->|"selects batches"| node_reader
node_web_pipeline -.->|"analyzes"| node_rules
node_web_pipeline -.->|"analyzes"| node_llm_analysis
node_web_pipeline -.->|"revises"| node_rule_revision
node_web_pipeline -.->|"revises"| node_llm_revision
node_web_pipeline -.->|"persists results"| node_writer
node_web -->|"queries"| node_database
node_reader -->|"reads"| node_database
node_writer -->|"writes"| node_database
node_database -->|"maps records"| node_corpus_model
node_rules -->|"loads rules"| node_rule_data
node_settings -->|"configures"| node_database
node_llm_analysis -.->|"requests analysis"| node_llm_service
node_llm_revision -.->|"requests revisions"| node_llm_service

click node_cli "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/main.py"
click node_web "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/web/app.py"
click node_web_pipeline "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/web/app.py"
click node_reader "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/parser/reader.py"
click node_writer "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/generator/writer.py"
click node_rules "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/analyzer/rule_engine.py"
click node_llm_analysis "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/analyzer/llm_analyzer.py"
click node_rule_revision "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/revisor/rule_revisor.py"
click node_llm_revision "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/revisor/llm_revisor.py"
click node_corpus_model "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/models/corpus.py"
click node_database "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/db/connection.py"
click node_settings "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/config/settings.py"
click node_rule_data "https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/data/rules/sensitive_words.json"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_cli,node_web,node_web_pipeline toneBlue
class node_reader,node_writer toneAmber
class node_rules,node_llm_analysis,node_rule_revision,node_llm_revision toneMint
class node_corpus_model,node_database,node_settings,node_rule_data toneRose
class node_operator,node_llm_service toneIndigo
```

## Components

### Entry points

- [CLI pipeline](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/main.py): `out/production/Corpus_script_optimization/src/main.py`
- [Web interface](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/web/app.py): `out/production/Corpus_script_optimization/src/web/app.py`
- [Web pipeline](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/web/app.py): `out/production/Corpus_script_optimization/src/web/app.py`

### Corpus processing

- [Corpus reader](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/parser/reader.py): `out/production/Corpus_script_optimization/src/parser/reader.py`
- [Corpus writer](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/generator/writer.py): `out/production/Corpus_script_optimization/src/generator/writer.py`

### Analysis and revision

- [Rule analysis](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/analyzer/rule_engine.py): `out/production/Corpus_script_optimization/src/analyzer/rule_engine.py`
- [LLM analysis](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/analyzer/llm_analyzer.py): `out/production/Corpus_script_optimization/src/analyzer/llm_analyzer.py`
- [Rule revision](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/revisor/rule_revisor.py): `out/production/Corpus_script_optimization/src/revisor/rule_revisor.py`
- [LLM revision](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/revisor/llm_revisor.py): `out/production/Corpus_script_optimization/src/revisor/llm_revisor.py`

### Configuration and data

- [Corpus models](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/models/corpus.py): `out/production/Corpus_script_optimization/src/models/corpus.py`
- [Corpus database](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/db/connection.py): `out/production/Corpus_script_optimization/src/db/connection.py`
- [Application settings](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/src/config/settings.py): `out/production/Corpus_script_optimization/src/config/settings.py`
- [Sensitive-word rules](https://github.com/sannicholas/corpus_script_optimization/blob/main/out/production/Corpus_script_optimization/data/rules/sensitive_words.json): `out/production/Corpus_script_optimization/data/rules/sensitive_words.json`

### Other components

- **Operator**
- **LLM provider**

## Connections

- Operator → CLI pipeline: runs
- Operator → Web interface: uses
- Web interface → Web pipeline: starts (evidence: `out/production/Corpus_script_optimization/src/web/app.py`)
- CLI pipeline → Corpus reader: selects batches (evidence: `out/production/Corpus_script_optimization/src/main.py`)
- CLI pipeline → Rule analysis: analyzes (evidence: `out/production/Corpus_script_optimization/src/main.py`)
- CLI pipeline → LLM analysis: analyzes (evidence: `out/production/Corpus_script_optimization/src/main.py`)
- CLI pipeline → Rule revision: revises (evidence: `out/production/Corpus_script_optimization/src/main.py`)
- CLI pipeline → LLM revision: revises (evidence: `out/production/Corpus_script_optimization/src/main.py`)
- CLI pipeline → Corpus writer: persists results (evidence: `out/production/Corpus_script_optimization/src/main.py`)
- Web pipeline → Corpus reader: selects batches (evidence: `out/production/Corpus_script_optimization/src/web/app.py`)
- Web pipeline → Rule analysis: analyzes (evidence: `out/production/Corpus_script_optimization/src/web/app.py`)
- Web pipeline → LLM analysis: analyzes (evidence: `out/production/Corpus_script_optimization/src/web/app.py`)
- Web pipeline → Rule revision: revises (evidence: `out/production/Corpus_script_optimization/src/web/app.py`)
- Web pipeline → LLM revision: revises (evidence: `out/production/Corpus_script_optimization/src/web/app.py`)
- Web pipeline → Corpus writer: persists results (evidence: `out/production/Corpus_script_optimization/src/web/app.py`)
- Web interface → Corpus database: queries (evidence: `out/production/Corpus_script_optimization/src/web/app.py`)
- Corpus reader → Corpus database: reads (evidence: `out/production/Corpus_script_optimization/src/parser/reader.py`)
- Corpus writer → Corpus database: writes (evidence: `out/production/Corpus_script_optimization/src/generator/writer.py`)
- Corpus database → Corpus models: maps records (evidence: `out/production/Corpus_script_optimization/src/db/connection.py`)
- Rule analysis → Sensitive-word rules: loads rules (evidence: `out/production/Corpus_script_optimization/src/analyzer/rule_engine.py`)
- Application settings → Corpus database: configures (evidence: `out/production/Corpus_script_optimization/src/db/connection.py`)
- LLM analysis → LLM provider: requests analysis
- LLM revision → LLM provider: requests revisions
