extractor: track rsu_vest + rsu_offset separately from cash pay

UK payslips for equity-comp employees report RSU vests as notional pay
for HMRC only. A paired same-magnitude deduction (Shares Retained /
Stock Tax Withholding / RSU Offset) nets it back out of cash. The UK
payslip's income_tax line shows tax on the grossed-up total, but the
actual RSU tax is handled by Schwab (US broker) via share sale. No
cash flows through UK payroll for RSU.

Previously the extractor folded RSU notional into gross_pay and
income_tax, which inflated the dashboard numbers — a payslip with
£25k RSU vest looked like 2x salary with 80% tax rate.

Changes:
- schema: add rsu_vest + rsu_offset fields (default 0).
- db + alembic 0002: add two new NUMERIC(12,2) columns with server
  default 0 (backward-compatible; existing rows get 0).
- validate_totals: include rsu_offset in deductions sum so the
  gross + rsu_vest inflation is properly netted out.
- extraction prompt: explicit rules for identifying RSU lines by the
  common Meta/Sage/Workday labels, and to NOT put them in
  other_deductions.

Dashboards in a follow-up commit: cash_gross = gross_pay - rsu_vest,
effective tax rate based on cash metrics.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

alembic/versions/0002_add_rsu_columns.py

@@ -0,0 +1,33 @@
+"""Add rsu_vest and rsu_offset columns.
+
+UK payslips for Meta report RSU grants as notional pay (gross inflation)
+and offset them via a same-magnitude deduction. The cash gross Viktor
+cares about for dashboarding is gross_pay - rsu_vest. Track both for
+reporting + exactness; cash and tax-rate charts compute from them.
+"""
+import sqlalchemy as sa
+
+from alembic import op
+
+revision = "0002_add_rsu_columns"
+down_revision = "0001_initial"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "payslip",
+        sa.Column("rsu_vest", sa.Numeric(12, 2), nullable=False, server_default=sa.text("0")),
+        schema="payslip_ingest",
+    )
+    op.add_column(
+        "payslip",
+        sa.Column("rsu_offset", sa.Numeric(12, 2), nullable=False, server_default=sa.text("0")),
+        schema="payslip_ingest",
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("payslip", "rsu_offset", schema="payslip_ingest")
+    op.drop_column("payslip", "rsu_vest", schema="payslip_ingest")

payslip_ingest/db.py

@@ -46,6 +46,12 @@ class Payslip(Base):
     student_loan: Mapped[Decimal] = mapped_column(Numeric(12, 2),
                                                   nullable=False,
                                                   server_default=text("0"))
+    rsu_vest: Mapped[Decimal] = mapped_column(Numeric(12, 2),
+                                              nullable=False,
+                                              server_default=text("0"))
+    rsu_offset: Mapped[Decimal] = mapped_column(Numeric(12, 2),
+                                                nullable=False,
+                                                server_default=text("0"))
     other_deductions: Mapped[dict[str, Any] | None] = mapped_column(JSON_TYPE, nullable=True)
     net_pay: Mapped[Decimal] = mapped_column(Numeric(12, 2), nullable=False)
     tax_year: Mapped[str] = mapped_column(String, nullable=False)

payslip_ingest/extractor.py

@@ -30,6 +30,8 @@ EXTRACTION_PROMPT = (
     '  "pension_employee": number,\n'
     '  "pension_employer": number,\n'
     '  "student_loan": number,\n'
+    '  "rsu_vest": number,\n'
+    '  "rsu_offset": number,\n'
     '  "other_deductions": {"label": number, ...},\n'
     '  "net_pay": number\n'
     "}\n"
@@ -37,8 +39,19 @@ EXTRACTION_PROMPT = (
     "Rules:\n"
     "- Report numbers as the payslip shows them; do not compute sums.\n"
     "- Unknown numeric fields → 0, not null.\n"
+    "- `rsu_vest`: any notional/reporting entry in the EARNINGS block labelled "
+    '"RSU Vest", "Restricted Stock Units", "Stock Value", "Notional Pay", '
+    '"Share Award", "Equity Vest", "GSU Vest". For Meta UK payslips this is '
+    "the grossed-up RSU value reported for HMRC only; Schwab handles actual "
+    "tax withholding via share sale.\n"
+    "- `rsu_offset`: the matching DEDUCTION that nets the RSU out of cash pay — "
+    'labels vary: "Shares Retained", "Stock Tax Withholding", "RSU Offset", '
+    '"Notional Pay Offset", "Shares Withheld". For Meta this is typically equal '
+    "in magnitude to rsu_vest so cash net is unaffected.\n"
+    "- If either rsu_vest or rsu_offset is present, BOTH should be populated; "
+    "do NOT put them in `other_deductions`.\n"
     "- `other_deductions` covers cycle-to-work, share-save, benefits-in-kind, court orders, "
-    "anything not in the main fields.\n"
+    "anything not in the main fields (and NOT RSU — those have dedicated fields).\n"
     "- All money in GBP unless the payslip is denominated otherwise.\n"
     '- If a field\'s value is ambiguous, pick the value from the "this period" column, not YTD.')
 

payslip_ingest/processor.py

@@ -107,6 +107,8 @@ async def _insert_payslip(
             pension_employee=extracted.pension_employee,
             pension_employer=extracted.pension_employer,
             student_loan=extracted.student_loan,
+            rsu_vest=extracted.rsu_vest,
+            rsu_offset=extracted.rsu_offset,
             other_deductions=_decimals_to_float(extracted.other_deductions),
             net_pay=extracted.net_pay,
             tax_year=derive_tax_year(extracted.pay_date),

payslip_ingest/schema.py

@@ -20,6 +20,16 @@ class ExtractedPayslip(BaseModel):
     pension_employee: Decimal = Field(default=Decimal("0"))
     pension_employer: Decimal = Field(default=Decimal("0"))
     student_loan: Decimal = Field(default=Decimal("0"))
+    # RSU vest reported on the UK payslip is notional — the share grant is
+    # handled by Schwab which withholds US-side tax by selling shares. The
+    # UK payslip only lists it for HMRC reporting; no cash flows through
+    # UK payroll. Track it separately so dashboards can derive cash-only
+    # gross = gross_pay - rsu_vest.
+    rsu_vest: Decimal = Field(default=Decimal("0"))
+    # Corresponding offset deduction that nets the RSU out of cash pay on the
+    # UK slip (labels vary: "Shares Retained", "Stock Tax Withholding",
+    # "RSU Offset", "Notional Pay Offset"). Same as rsu_vest in magnitude.
+    rsu_offset: Decimal = Field(default=Decimal("0"))
     other_deductions: dict[str, Decimal] = Field(default_factory=dict)
     net_pay: Decimal
 
@@ -33,10 +43,13 @@ class WebhookPayload(BaseModel):
 def validate_totals(p: ExtractedPayslip) -> bool:
     """Check that gross - deductions ≈ net within a 2p tolerance.
 
-    Employer pension is excluded — it never leaves the employer's books and
+    - Employer pension is excluded — it never leaves the employer's books.
-    doesn't affect take-home pay arithmetic.
+    - `rsu_offset` is included as a deduction: it's the line that nets
+      the RSU notional back out of cash pay on UK payslips with stock comp.
+      The gross + rsu_vest inflation is offset by rsu_offset of equal size.
     """
     deductions = (p.income_tax + p.national_insurance + p.pension_employee + p.student_loan +
+                  p.rsu_offset +
                   sum(p.other_deductions.values(), start=Decimal("0")))
     diff = abs(p.gross_pay - deductions - p.net_pay)
     return diff < TOTALS_TOLERANCE

tests/test_processor.py

@@ -22,6 +22,8 @@ def _sample_extraction() -> ExtractedPayslip:
         pension_employee=Decimal("250.00"),
         pension_employer=Decimal("150.00"),
         student_loan=Decimal("100.00"),
+        rsu_vest=Decimal("0.00"),
+        rsu_offset=Decimal("0.00"),
         other_deductions={"cycle_to_work": Decimal("50.00")},
         net_pay=Decimal("3450.00"),
     )