Split 49 modules/suites into independent git repos; untrack from monorepo

Each top-level module/suite folder is now its own private repo on GitHub
(gsinghpal/<name>) and gitea (admin/<name>), with a fresh single initial
commit. The monorepo no longer tracks them (added to .gitignore + git rm
--cached); working-tree files are retained on disk and managed in their
own repos. The monorepo keeps shared root files (CLAUDE.md, docs/, scripts/,
tools/, AGENTS.md, WIP/obsolete dirs) and full history.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

fusion_accounting/fusion_accounting_reports/services/commentary_prompt.py

@@ -1,67 +0,0 @@
-"""LLM prompt for AI report commentary.
-
-Provider-agnostic system + user prompt builder. Output contract:
-JSON with keys summary, highlights, concerns, next_actions."""
-
-
-SYSTEM_PROMPT = """You are an experienced CFO providing executive-level commentary
-on a financial report. Your output MUST be valid JSON of this exact shape:
-
-{
-  "summary": "<2-3 sentence executive summary of the report period>",
-  "highlights": ["<observation 1>", "<observation 2>", ...],
-  "concerns": ["<thing to investigate 1>", ...],
-  "next_actions": ["<suggested action 1>", ...]
-}
-
-Rules:
-- Use the data provided. Do not invent numbers.
-- Tone: professional, concise, factual.
-- Currency formatting: always include the $ symbol and 2 decimal places.
-- For anomalies: explicitly mention the variance percentage AND the dollar amount.
-- Do NOT include markdown code fences. Do NOT include any prose outside the JSON.
-"""
-
-
-def build_prompt(report_result: dict, anomalies: list) -> tuple[str, str]:
-    """Build (system_prompt, user_prompt) tuple."""
-    parts = []
-
-    # Report context
-    parts.append(f"REPORT: {report_result.get('report_name', 'Untitled')}")
-    period = report_result.get('period', {})
-    parts.append(f"PERIOD: {period.get('label', '')} "
-                 f"({period.get('date_from', '')} to {period.get('date_to', '')})")
-    comp_period = report_result.get('comparison_period')
-    if comp_period:
-        parts.append(f"COMPARED TO: {comp_period.get('label', '')} "
-                     f"({comp_period.get('date_from', '')} to {comp_period.get('date_to', '')})")
-    parts.append("")
-
-    # Rows (the actual numbers)
-    parts.append("REPORT LINES:")
-    for row in report_result.get('rows', []):
-        line = f"  - {row.get('label', '?')}: ${row.get('amount', 0):,.2f}"
-        if row.get('amount_comparison') is not None:
-            line += f" (comparison: ${row['amount_comparison']:,.2f}"
-            if row.get('variance_pct') is not None:
-                line += f", {row['variance_pct']:+.1f}%"
-            line += ")"
-        if row.get('is_subtotal'):
-            line += " [SUBTOTAL]"
-        parts.append(line)
-    parts.append("")
-
-    # Anomalies
-    if anomalies:
-        parts.append("ANOMALIES (variances exceeding threshold):")
-        for a in anomalies[:10]:
-            parts.append(
-                f"  - {a['label']}: {a['direction']}d {a['variance_pct']:.1f}% "
-                f"(${a['variance_amount']:+,.2f}, severity: {a['severity']})"
-            )
-        parts.append("")
-
-    parts.append("Generate the JSON commentary per the system prompt.")
-
-    return (SYSTEM_PROMPT, "\n".join(parts))