junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-08 11:17:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs: handover + next-agent prompt post S0380.110..114 (cert 000565 SAP exact at 1e-4)

Browse source 
Five spec-cited slices closed cert 000565 from continuous SAP
Δ = -0.0059 → +0.000042 (within user 1e-4 tolerance):

- S0380.110: per-rooflight g_L via Appendix L §L2a
- S0380.111: roof-window inclination adj via Table 6e Note 2
- S0380.112: per-BP rooflight deduction via RdSAP §3.7
- S0380.113: H=0 gable retention via RdSAP §3.9.2 step (b)
- S0380.114: pump GAIN for HP+boiler via Table 5a Note a)

Handover documents the two parallel workstreams the next agent
should tackle:
1. Final sweep for TRULY exact continuous SAP on cert 000565
   (close the remaining sub-1e-4 cost/CO2/SH/fuel/ECF residuals)
2. Tighten golden test residuals across the corpus per
   [[feedback-golden-residuals-near-zero]]

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Khalim Conn-Kowlessar 2026-05-30 19:53:45 +00:00
parent cc70e55917
commit 2fe84fcc7e
2 changed files with 483 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

297
domain/sap10_calculator/docs/HANDOVER_POST_S0380_114.md Normal file
View file

@ -0,0 +1,297 @@
# Handover — post S0380.110..114 (cert 000565 continuous SAP exact at 1e-4)
Branch: `feature/per-cert-mapper-validation`. **HEAD `cc70e559`**.
Predecessor: [`HANDOVER_POST_S0380_109.md`](HANDOVER_POST_S0380_109.md).
## TL;DR
Cert 000565 was closed from continuous SAP Δ = −0.0059 → **+0.000042**
(within the user's 1e-4 tolerance) across 5 spec-cited slices:
| Slice | Commit | Spec | Effect on cert 000565 |
|---|---|---|---|
| **S0380.110** | `9461e657` | SAP 10.2 Appendix L §L2a (PDF p.88) — per-rooflight g_L via Table 6b | `lighting_kwh` -2.17 → ✓ EXACT |
| **S0380.111** | `794ef7ed` | SAP 10.2 §3.2 + Table 6e Note 2 (PDF p.180) — roof-window inclination adj +0.30 W/m²K | `roof_windows_w_per_k` -0.43 → ✓ EXACT |
| **S0380.112** | `a461b70d` | RdSAP 10 §3.7 (PDF p.19) — per-BP rooflight deduction | Roof +0.30 → -0.06 W/K, TB +0.15 → -0.03 W/K |
| **S0380.113** | `59de805e` | RdSAP 10 §3.9.2 step (b) (PDF p.23) — absent gable H=0 lodgement | Fabric closed (max 0.005 W/K residual across 8 components) |
| **S0380.114** | `cc70e559` | SAP 10.2 Table 5a Note a) (PDF p.177) — pump GAIN for HP+boiler hybrids | Continuous SAP -0.008 → **+0.000042** |
**Test baseline at HEAD `cc70e559`:** **616 pass + 5 expected
`test_sap_result_pin[000565-*]` fails** (continuous SAP pin closed;
remaining 5 are cost / CO2 / SH / fuel / ECF at strict 1e-4 abs).
Pyright net-zero per touched file across every slice.
## Critical user direction (read before any tool call)
1. **Primary metric is `sap_score_continuous`.** Target is EXACT
(Δ = 0), not 1e-4. The user explicitly wants the cascade to be a
true spec replica. Sub-1e-4 residuals are not "essentially exact"
— they are real bugs to find and close.
2. **Tighten loose pins as the cascade improves.** Per
[[feedback-golden-residuals-near-zero]] the
[test_golden_fixtures.py](domain/sap10_calculator/rdsap/tests/test_golden_fixtures.py)
`expected_*_resid` values were pinned at whatever the cascade
produced at the time. As the cascade gets more spec-correct, those
pins should shrink toward 0. **This is now an active workstream**
— not just for cert 000565 but across the whole golden corpus.
3. **Don't widen tolerances to make tests pass.** Per
[[feedback-zero-error-strict]] — 1e-4 absolute is the bar, no
`pytest.approx(rel=...)`, no `xfail`, no "spec-precision floor"
framing.
## State table — cert 000565 (HEAD `cc70e559`)
### Fabric — all ✓ EXACT
| Component | Cascade | WS | Δ |
|---|---:|---:|---:|
| walls (29a) | 604.0710 | 604.0710 | +0.0000 |
| floor (28a/b) | 61.6743 | 61.6700 | +0.0043 |
| roof (30) | 51.3768 | 51.3795 | −0.0027 |
| windows (27) | 11.4788 | 11.4787 | +0.0001 |
| roof_windows (27a) | 3.5806 | 3.5805 | +0.0001 |
| doors (26a) | 11.1000 | 11.1000 | 0.0000 |
| party_walls (32) | 65.1300 | 65.1300 | 0.0000 |
| thermal_bridging (36) | 128.6448 | 128.6500 | −0.0052 |
| external area (31) | 857.6323 | 857.6400 | −0.0077 |
| **total HTC (33)** | **937.0563** | **937.0600** | **−0.0037** |
### Energy + cost — close but not exact
| Pin | Cascade | WS | Δ | Rel |
|---|---:|---:|---:|---:|
| sap_score (int) | 29 | 29 | 0 | ✓ EXACT |
| **sap_score_continuous** | **28.508742** | **28.5087** | **+0.000042** | **1.5e-6** |
| ecf | 5.386823 | 5.3866 | +0.000223 | 4e-5 |
| total_fuel_cost_gbp | 4680.2515 | 4680.2593 | −0.0078 | 2e-6 |
| co2_kg_per_yr | 6447.6161 | 6447.6263 | −0.0102 | 2e-6 |
| space_heating_kwh | 59008.2363 | 59008.3499 | −0.1136 | 2e-6 |
| main_heating_fuel | 34710.7272 | 34710.7941 | −0.0669 | 2e-6 |
| lighting_kwh | 1384.8353 | 1384.8353 | 0 | ✓ EXACT |
| hot_water_kwh | 3755.0288 | 3755.0288 | 0 | ✓ EXACT |
| pumps_fans_kwh | 252.5159 | 252.5159 | 0 | ✓ EXACT |
| pumps_fans_co2 | 35.3349 | 35.3349 | 0 | ✓ EXACT |
| pumps_fans_pe | 383.3797 | 383.3796 | 0 | ✓ EXACT |
## Next agent's job — **TWO PARALLEL WORKSTREAMS**
### Workstream 1: True exact closure of cert 000565
Continuous SAP currently at +4.2e-5. The user wants 0. The remaining
sub-1e-4 residuals are sub-spec float drift somewhere in the cascade.
Some candidates worth investigating:
1. **Floor +0.0043 W/K residual.** Small but persistent. Probably a
2-d.p. rounding inconsistency in u_floor or floor-area cascade.
At U≈0.7, this is 0.006 m² of phantom area.
2. **Roof −0.0027 W/K residual.** Probably the Ext3 A_RR_shell
formula precision (12.5 × √(32.0/1.5) cascade vs Elmhurst's
slightly different result). Could be a rounding step in the
cascade Elmhurst doesn't apply, or vice versa.
3. **MIT off by 0.0008°C average.** Tiny but accumulates over 8
heating months. Drives part of the SH residual.
4. **Utilisation factor off by 0.0001.** Same story.
5. **Cost / CO2 / PE per-month factor application.** The cascade
applies SAP10.2 Table 12 monthly factors to per-month fuel
energy. Look for whether the cascade uses the worksheet's exact
monthly weighting vs an annual-average shortcut.
**Approach:** the existing audit method works — dump every monthly
intermediate value, diff against worksheet line refs, find the
smallest residual that's still > 1e-6, trace its source. Continue
the discipline from the prior 5 slices.
**Verification:** the e2e test
[`test_sap_result_pin[000565-*]`](domain/sap10_calculator/worksheet/tests/test_e2e_elmhurst_sap_score.py)
pins every result field at abs=1e-4. When all 5 currently-failing
fields close, cert 000565 is truly exact.
### Workstream 2: Tighten golden test residuals
[test_golden_fixtures.py](domain/sap10_calculator/rdsap/tests/test_golden_fixtures.py)
has ~50+ certs with `expected_sap_resid` / `expected_pe_resid` /
`expected_co2_resid` baselines. Many were pinned at whatever the
cascade produced at the time of test-creation. After the recent
slice improvements (especially S0380.110..114), several of these
should now be re-pinnable at SMALLER residuals.
**Approach:**
1. Run the golden fixture suite — note any tests that still pass but
have an `expected_*_resid` magnitude > 1e-4. Each is a candidate
for re-pinning.
2. For each candidate, check the actual cascade residual today vs
the pinned expected. If the cascade is now CLOSER to lodged
(residual smaller in magnitude), re-pin to the new (smaller)
value. Document the why in the test's `notes` field.
3. For pins that are far from 0 (e.g. `expected_sap_resid=-14` on
cert 0240), investigate the gap. Some will be load-bearing mapper
gaps (cert 0240 has a documented mapper note); others may be
spec bugs the recent slices half-closed. Treat each as a mini-
audit.
4. The user's bar (2026-05-28 onwards): residuals should be at
~1e-2 PE / 1e-3 CO2 or smaller for mapper-closed certs. Any cert
whose `notes` say "mapper gap closed in slice X" should have
`expected_*_resid` pinned at near-zero.
**Other test files to sweep:**
- [test_section_cascade_pins.py](domain/sap10_calculator/worksheet/tests/test_section_cascade_pins.py)
— per-section line-ref pins; tolerance shapes vary.
- [test_fuel_cost.py](domain/sap10_calculator/worksheet/tests/test_fuel_cost.py)
- [test_internal_gains.py](domain/sap10_calculator/worksheet/tests/test_internal_gains.py)
- [test_appendix_h_solar.py](domain/sap10_calculator/worksheet/tests/test_appendix_h_solar.py)
Each may have `assert abs(diff) <= TOL` constructs where TOL is
historically lax. Sweep + tighten as the underlying cascade
precision allows.
## Memories to load before any tool call
1. **`project_cert_000565_recovery_state`** — per-slice history + open work
2. **`project_sap10_ml_deprecation`** — `domain/sap10_ml/` retiring
3. **`feedback_sap_10_2_only_never_10_3`** — **CRITICAL** — never reference SAP 10.3
4. **`feedback_spec_citation_in_commits`** — quote spec + page in commit messages
5. **`feedback_verify_handover_claims`** — verify numeric claims against source PDF
6. **`feedback_zero_error_strict`** — pyright net-zero per touched file
7. **`feedback_commit_per_slice`** — one slice = one commit
8. **`feedback_aaa_test_convention`** — `# Arrange / # Act / # Assert` headers
9. **`feedback_e2e_validation_philosophy`** — abs=1e-4 pins, no rel/xfail
10. **`feedback_abs_diff_over_pytest_approx`** — use `abs(x-y) <= tol`
11. **`feedback_spec_floor_skepticism`** — verify "spec-precision floor" claims
12. **`feedback_golden_residuals_near_zero`** — golden pins should shrink toward 0
13. **`reference_unmapped_sap_code`** — calculator strict-raise pattern
## How to run the baseline
```bash
PYTHONPATH=/workspaces/model python -m pytest \
backend/documents_parser/tests/test_summary_pdf_mapper_chain.py \
backend/documents_parser/tests/test_elmhurst_extractor.py \
backend/documents_parser/tests/test_elmhurst_end_to_end.py \
domain/sap10_calculator/worksheet/tests/test_e2e_elmhurst_sap_score.py \
domain/sap10_calculator/worksheet/tests/test_appendix_h_solar.py \
domain/sap10_calculator/worksheet/tests/test_mev.py \
domain/sap10_calculator/rdsap/tests/test_cert_to_inputs.py \
domain/sap10_calculator/rdsap/tests/test_golden_fixtures.py \
domain/sap10_calculator/tests/test_pcdb_table_322_lookup.py \
domain/sap10_calculator/tests/test_pcdb_table_329_lookup.py \
--no-cov -q
```
Expected: **616 pass + 5 expected `test_sap_result_pin[000565-*]` fails**:
```
ecf
total_fuel_cost_gbp
co2_kg_per_yr
space_heating_kwh_per_yr
main_heating_fuel_kwh_per_yr
```
(Note: `sap_score_continuous` pin already passes at +4.2e-5 < 1e-4.)
## Cohort fixture state (HEAD `cc70e559`)
For reference, the 7 hand-built / extractor-driven fixtures all
land their integer SAP exact:
| cert | sap_score | sap_continuous |
|---|---:|---:|
| 000474 | 62 | 62.2584 |
| 000477 | 65 | 65.0057 |
| 000480 | 61 | 61.2986 |
| 000487 | 62 | 61.6431 |
| 000490 | 57 | 57.3979 |
| 000516 | 63 | 62.7937 |
| **000565** | **29** | **28.5087** ← user target reached |
## How the audit worked (replicate this method)
The single-bug-per-slice closure pattern that worked for S0380.110..114:
1. **Audit before implementing.** Dump every cascade intermediate
value alongside the worksheet line ref. Don't trust handover
narratives — verify the actual numerical residual against the
source PDF.
2. **Find the spec citation.** When you spot a residual, search the
spec for what the value SHOULD be. The bug is almost always a
misreading or omission of a specific spec clause.
3. **Confirm the back-solve.** Before writing code, prove the
hypothesis: "if I add the spec rule, the cascade should produce
X". Compare X against the worksheet. If it matches at 1e-4 or
better, ship the slice.
4. **Tight AAA tests.** Pin the narrowest intermediate the slice
directly changes. Don't pin downstream-rolled-up values with
tight thresholds (S0380.103 cost-test reframing pattern).
5. **Cohort safety.** Verify the new rule doesn't break the cohort
certs. Usually the new spec branch is gated by a condition that
doesn't fire on cohort (e.g. "non-HP system present alongside
HP" doesn't apply to cohort gas-only certs).
## Spec source quick-reference
All under `domain/sap10_calculator/docs/specs/`:
- **SAP 10.2 full spec**: `sap-10-2-full-specification-2025-03-14.pdf`
- §3.2 + Table 6e Note 2 (p.180) — roof-window inclination adj — S0380.111
- §10a Table 12a Grid 2 (p.191) + Table 12d (p.194) + Table 12e (p.195) — MEV trifecta
- Appendix L §L2a (p.88) + Table 6b (p.178) — daylight factor — S0380.110
- Table 5a Note a) (p.177) — pump gain spec — S0380.114
- **RdSAP 10 spec**: `RdSAP 10 Specification 10-06-2025.pdf`
- §3.7 (p.19) — per-BP window/door deduction — S0380.112
- §3.7.1 (p.21) — window vs roof window classification — S0380.107
- §3.9.2 step (b) (p.23) — Type 2 RR gable formula (including H=0) — S0380.113
- §3.9.2 step (d) (p.23) — Connected RR deduction — S0380.108
- §5.6 + Table 12 (p.40-41) — stone wall — S0380.109
- §5.7 + Table 13 (p.41) — brick wall U₀ — S0380.109
- §5.8 + Table 14 (p.41-42) — insulation R — S0380.109
- **SAP 10.3** at `sap-10-3-full-specification-2026-01-13.pdf`:
**DO NOT reference** ([[feedback-sap-10-2-only-never-10-3]])
## Files touched this session (S0380.110..114)
| File | Slices | Purpose |
|---|---|---|
| `datatypes/epc/domain/epc_property_data.py` | .110, .112 | `SapRoofWindow.glazing_type` + `.window_location` |
| `datatypes/epc/domain/mapper.py` | .110, .111, .112, .113 | Roof-window glazing/BP/inclination; H=0 gable retention |
| `domain/sap10_calculator/worksheet/internal_gains.py` | .110, .114 | Per-rooflight g_L dispatch; HP+boiler pump gain |
| `domain/sap10_calculator/worksheet/heat_transmission.py` | .112, .113 | Per-BP rooflight deduction; negative gable area handling |
| `domain/sap10_calculator/worksheet/tests/_elmhurst_worksheet_000516.py` | .110, .112 | `glazing_type=2` + `window_location="Main"` on cohort rooflight |
| `backend/documents_parser/tests/test_summary_pdf_mapper_chain.py` | .110..114 | AAA tests for each slice |
## What NOT to do
- **Don't reference SAP 10.3** ([[feedback-sap-10-2-only-never-10-3]]).
- **Don't widen pin tolerances** to make currently-failing pins pass
([[feedback-zero-error-strict]]). Find the bug, fix it, the pin
closes.
- **Don't re-investigate any closed work** (.91..114). All settled.
- **Don't add new helpers to `domain/sap10_ml/`** — deprecation path.
- **Don't pin downstream-only metrics with tight thresholds** —
S0380.103 cost-test pattern. Pin the narrowest intermediate the
slice directly changes.
## Memory hygiene
After each new slice, update:
- `project_cert_000565_recovery_state` — append slice closure + refresh open work
- `MEMORY.md` — refresh HEAD + one-line summary
Good luck. Cert 000565 is at the threshold — one or two more
spec-precision slices and it's truly exact. Then sweep the rest of
the cohort + golden fixtures with the same discipline.

186
domain/sap10_calculator/docs/NEXT_AGENT_PROMPT_POST_S0380_114.md Normal file
View file

@ -0,0 +1,186 @@
# Next-agent prompt — post S0380.110..114
Branch: `feature/per-cert-mapper-validation`. **HEAD `cc70e559`**.
You are picking up after cert 000565's continuous SAP was closed
from Δ = −0.0059 → **+0.000042** across 5 spec-cited slices
(S0380.110..114). The cascade is now within the user's 1e-4
tolerance on continuous SAP — but the user wants **truly exact**
(Δ = 0), so this isn't done.
Read these in order before any tool call:
1. [`HANDOVER_POST_S0380_114.md`](HANDOVER_POST_S0380_114.md) — full state
2. [`HANDOVER_POST_S0380_109.md`](HANDOVER_POST_S0380_109.md) — predecessor
Load these memories:
- `project_cert_000565_recovery_state` — per-slice history + per-pin state
- `project_sap10_ml_deprecation` — `domain/sap10_ml/` is retiring
- `feedback_sap_10_2_only_never_10_3` — **CRITICAL** — never reference SAP 10.3
- `feedback_spec_citation_in_commits` — quote spec + page in commits
- `feedback_verify_handover_claims` — verify numeric claims against PDFs
- `feedback_zero_error_strict` — pyright net-zero per touched file
- `feedback_commit_per_slice` — one slice = one commit
- `feedback_aaa_test_convention` — `# Arrange / # Act / # Assert` headers
- `feedback_e2e_validation_philosophy` — abs=1e-4 pins, no rel/xfail
- `feedback_abs_diff_over_pytest_approx` — `abs(x-y) <= tol`
- `feedback_spec_floor_skepticism` — verify "spec-precision floor" claims
- `feedback_golden_residuals_near_zero` — golden pins should shrink to ~0
- `reference_unmapped_sap_code` — calculator strict-raise pattern
## Your task — two parallel workstreams
The user explicitly asked for both, in one new session:
> "I want to try and get exact. I think we can so we should try, and
> truly replicate the spec. I also want to review our existing
> tests, golden tests and see if we can reduce our expected
> residuals to better than 1e-4."
### Workstream 1: Final sweep for true exact continuous SAP on cert 000565
Current state (cert 000565, HEAD `cc70e559`):
| Pin | Cascade | WS | Δ |
|---|---:|---:|---:|
| sap_score_continuous | 28.508742 | 28.5087 | +0.000042 (within 1e-4) |
| ecf | 5.386823 | 5.3866 | +0.000223 |
| total_fuel_cost_gbp | 4680.2515 | 4680.2593 | −0.0078 |
| co2_kg_per_yr | 6447.6161 | 6447.6263 | −0.0102 |
| space_heating_kwh | 59008.2363 | 59008.3499 | −0.1136 |
| main_heating_fuel | 34710.7272 | 34710.7941 | −0.0669 |
5 currently-failing pins; all sub-1e-4 absolute but the user wants
them at 0 (truly exact).
**Candidates worth investigating** (from the audit at end of
S0380.114):
1. **Floor +0.0043 W/K residual.** Sub-spec 2-d.p. rounding
inconsistency in `u_floor` or floor-area cascade.
2. **Roof −0.0027 W/K residual.** Likely Ext3 A_RR_shell precision
(12.5 × √(32.0/1.5) cascade rounding vs Elmhurst's).
3. **MIT off 0.0008°C avg.** Accumulates over 8 heating months.
4. **Utilisation factor off 0.0001.** Same story.
5. **Cost / CO2 / PE monthly factor application.** Verify cascade
applies SAP10.2 Table 12 monthly factors in the same order /
precision as Elmhurst.
**Approach (proven 5× this session):**
1. Run [test_e2e_elmhurst_sap_score.py](domain/sap10_calculator/worksheet/tests/test_e2e_elmhurst_sap_score.py) for cert 000565 — see which pins fail.
2. Dump every monthly cascade intermediate (66)..(98a) vs worksheet line refs.
3. Find the smallest residual that's still > 1e-6.
4. Search the spec for what the value SHOULD be.
5. Confirm by back-solving against the worksheet PDF before writing code.
6. Failing AAA test → implement → verify → commit with spec citation.
**Verification:** all 5 currently-failing pins close to abs=1e-4 →
cert 000565 truly exact.
### Workstream 2: Tighten golden test residuals
[test_golden_fixtures.py](domain/sap10_calculator/rdsap/tests/test_golden_fixtures.py)
has many certs with `expected_*_resid` baselines pinned at whatever
the cascade produced at test-creation time. The recent S0380.91..114
work moved the cascade significantly closer to spec — many of these
pins are now stale (cascade is closer to lodged than the pin admits).
Per [[feedback-golden-residuals-near-zero]]:
> "After closing any cohort-2 cert's SAP residual to <1e-4,
> immediately check its golden PE / CO2 residual. If non-zero,
> that's the next slice."
**Approach:**
1. Run the golden fixture suite (`test_golden_fixtures.py`).
2. For each cert that PASSES at its current `expected_*_resid`, check
if the actual cascade residual is smaller in magnitude than the
pin. If so, re-pin to the new tighter value (and document in the
`notes` field — see existing cert 6035 / 0240 patterns).
3. For pins with magnitude > 1e-4 that DON'T have a documented mapper
gap in `notes`, treat as a mini-audit: probe the cascade vs the
cert's lodged values, find the spec gap, ship a slice if it's a
real bug.
4. Also sweep:
- [test_section_cascade_pins.py](domain/sap10_calculator/worksheet/tests/test_section_cascade_pins.py)
- [test_fuel_cost.py](domain/sap10_calculator/worksheet/tests/test_fuel_cost.py)
- [test_internal_gains.py](domain/sap10_calculator/worksheet/tests/test_internal_gains.py)
- [test_appendix_h_solar.py](domain/sap10_calculator/worksheet/tests/test_appendix_h_solar.py)
Look for `assert abs(diff) <= TOL` constructs where TOL is lax
(e.g. > 1e-3). Tighten as the underlying cascade allows.
**Bar:** for any cert whose mapper/cascade gap has been closed (i.e.
`notes` say "closed in slice X" or there's no documented gap), the
`expected_*_resid` should be at ≤1e-3 absolute, ideally ≤1e-4.
## How to run the baseline
```bash
PYTHONPATH=/workspaces/model python -m pytest \
backend/documents_parser/tests/test_summary_pdf_mapper_chain.py \
backend/documents_parser/tests/test_elmhurst_extractor.py \
backend/documents_parser/tests/test_elmhurst_end_to_end.py \
domain/sap10_calculator/worksheet/tests/test_e2e_elmhurst_sap_score.py \
domain/sap10_calculator/worksheet/tests/test_appendix_h_solar.py \
domain/sap10_calculator/worksheet/tests/test_mev.py \
domain/sap10_calculator/rdsap/tests/test_cert_to_inputs.py \
domain/sap10_calculator/rdsap/tests/test_golden_fixtures.py \
domain/sap10_calculator/tests/test_pcdb_table_322_lookup.py \
domain/sap10_calculator/tests/test_pcdb_table_329_lookup.py \
--no-cov -q
```
Expected: **616 pass + 5 expected `test_sap_result_pin[000565-*]`
fails** (sap_score_continuous pin already closes; the 5 fails are
the cost/CO2/SH/fuel/ecf residuals).
## Standard workflow per slice
1. Read SAP 10.2 / RdSAP 10 spec page — quote it in the commit
2. Probe cascade output for cert 000565; identify spec-vs-cascade gap
3. Write failing AAA test FIRST (`# Arrange / # Act / # Assert`)
4. Implement helper / change
5. Verify test passes
6. Run full handover suite (command above)
7. Check pyright on touched files — net-zero from baseline
(`git stash` + re-run pyright to compute baseline)
8. Commit with spec citation + verbatim quote
9. Update `project_cert_000565_recovery_state` + `MEMORY.md` index
## What NOT to do
- **Don't reference SAP 10.3** ([[feedback-sap-10-2-only-never-10-3]]).
- **Don't widen pin tolerances** to make failing pins pass —
find the bug, fix it.
- **Don't re-investigate any closed work** (.91..114). All settled.
- **Don't add new helpers to `domain/sap10_ml/`** — deprecation path.
- **Don't accept "spec-precision floor" framing**
([[feedback-spec-floor-skepticism]]) — verify against PDFs first.
- **Don't pin downstream-only metrics with tight thresholds** —
pin the narrowest intermediate the slice directly changes.
## Spec source quick-reference
All under `domain/sap10_calculator/docs/specs/`:
- **SAP 10.2**: `sap-10-2-full-specification-2025-03-14.pdf`
- **RdSAP 10**: `RdSAP 10 Specification 10-06-2025.pdf`
- **SAP 10.3** (`sap-10-3-full-specification-2026-01-13.pdf`):
**DO NOT reference** ([[feedback-sap-10-2-only-never-10-3]])
The user's stated philosophy bears repeating:
> "It's okay if we temp drift away from continuous SAP, as long as
> we are actually fixing true problems with the intermediate values.
> Eventually, I expect the error of continuous SAP to be zero but
> that is only possible if we fix all of the sub components and
> remain true to spec."
Cert 000565 is at the threshold. One to three more spec-precision
slices and it's truly exact. Then sweep the golden corpus with the
same discipline.
Good luck.