Cracked the DSCA33/45 accuracy-block numeric formatting against the Hoffman originals
(formatAccuracyLineDSCA3345):
- mA-output models store calc (and, for DSCA45, meas) in AMPS -> x1000 to display mA;
DSCA33 stores meas already in display unit (NOT scaled), DSCA45 scales both.
- DSCA33 (AC-RMS): stim/calc/meas UNSIGNED, error signed; stim is AC input to 3 dp.
- DSCA45 (frequency): stim is an UNSIGNED integer Hz; calc/meas/error SIGNED.
- Math.fround on accuracy values (QB single-precision rounding), matching the Final-Test fix.
Final-Test fixes too: leading-zero drop only when the value overflows QB's 6-char field
("-0.0005"->"-.0005", but "-0.750" keeps its zero); spec-less section sub-heads
(Zero-Crossing Input / TTL Input) render with NO status (only Withstand/Hi-Pot get PASS);
DSCA33 prints a "Check List" header after the underline.
slotmap-from-hoffman.js (new): derive slotMaps for the models the staged multi-unit
derivation couldn't (vintage-heavy) by matching the Hoffman _srcSerial original's
Final-Test measured values (at display precision) to the DB STATUS entries. Recovered
all 13 remaining DSCA33 models.
Validation (validate-dsca3345.js, content-normalized byte-compare vs live Hoffman
originals): 54 of 56 models PASS and are marked validated:true (the render gate).
2 holdouts (DSCA33-04A, DSCA33-1891) each have ONE accuracy cert at a rounding boundary
where fround rounds opposite to the original; left UNvalidated -> still render null
(safe). DSCA33-1948 + DSCA45-1746 (24 units) have no Hoffman original.
Gate now OPEN for the 54 validated models (render live); 2 holdouts + the no-template
pair stay null. Publishing the api_uploaded_at IS NULL gap next (never re-pushes the
~7,157 pristine originals).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Per the 5070 handoff (DSCA33-45-HOFFMAN-RECOVERY): the lost DSCA33/45 specs are
recoverable from Hoffman, not John. Wired the mined dsca33-45-templates.json (56
models) into the renderer:
- datasheet-exact.js: load DSCA3345_TEMPLATES; for family DSCA, the Hoffman-mined
template takes PRECEDENCE over the stale staged-extraction entry (which shadowed 25
models with accOut "?"/no accHeader). Emit the verbatim 2-line accHeader for these
families (Vin (mVAC)/Iin (AAC)/Frequency (Hz), Output (VDC)/(mADC)). Per-model
`validated` GATE: a DSCA33/45 model renders only after byte-matching its Hoffman
original; until then it returns null (skipped) so an unverified render can never
overwrite a pristine live original. DSCA_VALIDATE_MODE env opens the gate for the
validation harness only. Exposed rendersWithoutSpecs().
- render-datasheet.js: allow a null-specs render for DSCA33/45 (their spec files were
lost; template-driven) instead of bailing on missing specs.
- derive-dsca-slotmaps.js: DSCA_TPL env to target the 3345 templates; derived 43 slot
maps into them (22 models need none, 8 DSCA33 still below threshold).
- validate-dsca3345.js (new): renders each model's _srcSerial, fetches the live
Hoffman original (GET TestReportDataFiles/{serial}, deployed uploader token — no
vault needed), content-normalized compare; --apply marks validated.
STATUS: gate is CLOSED — 0 models validated, all DSCA33/45 still render null, nothing
published, no risk. Final-Test block + accuracy headers now byte-match the Hoffman
originals for all 56 models; the remaining blocker is accuracy-DATA numeric quirks that
must match to pass the gate:
- DSCA33 calc column stored in A but displayed in mADC (x1000); measured stored in
mA (not scaled) — an original-software unit quirk.
- sign conventions differ per layout (DSCA33 stim/calc/meas unsigned, error signed;
DSCA45 stim unsigned, calc/meas/error signed).
- DSCA45 frequency-input stim formatting.
These need per-layout reverse-engineering against the originals (the validation harness
is the oracle). 8 DSCA33 models (DSCA33-02/03/03A/04/04A/05/05A/1642) also lack a slot
map (below threshold). DSCA33-1948 + DSCA45-1746 (24 units) have no Hoffman original.
Cleanups: deleted superseded memory project_dsca33_45_spec_gap; struck the obsolete
"ask John" TODO 2 from the handoff note.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Some DSCA subtypes' raw_data STATUS groups carry more (or fewer) value-bearing
entries than the template's spec-bearing rows (the test program measures slots the
printed sheet omits, e.g. DSCA49's 5mA load pair), so the in-order zip misaligned
values and those models were skipped by the count-guard.
New tool derive-dsca-slotmaps.js derives a per-model slotMap (absolute statusEntries
index per spec-bearing row) by greedily matching a staged original's printed values
to the DB raw_data STATUS entries (same fround formatting), then picking the
candidate map that validates against the most units. Models are grouped by identical
row-name signature and one map is derived per group from all sibling units — this
disambiguates duplicate values (e.g. a unit where 5mA != 50mA linearity forces the
correct slot; DSCA49-04 alone has only 2 staged units that can't, but its siblings'
25 units do). Stored as `slotMap` in dsca-templates.json.
Renderer: consults slotMap only when the sequential zip fails (value count !=
spec-row count), so the 88 already-clean models keep their path (no regression) and
ambiguous ones pull the right value via the map.
STAGE 3 re-validation: FINAL-TEST CLEAN 88 -> 92; 134 more certs now render
(null 450 -> 316); matches 2278 -> 2412. Same 6 retest-vintage dirty models, no
new mismatches. DSCA49 family + DSCA40-03 group now clean and validated.
Still blocked (separate gap, NOT layout ambiguity): DSCA45-* and most DSCA33-*
render null because they have NO spec-reader entries (render-datasheet bails before
rendering). Their slotMaps are derived and ready; they need spec coverage. One DSCA33
group (DSCA33-02/03/03A/04/05/1948) did not reach the slotMap validation threshold
(best 19/35 units) and stays skipped pending more/cleaner staged samples.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Root cause of the DSCA39 footer mismatch: the "Standard output load for test is
250 ohms." line is a footer note, not a parameter, but the STAGE 1 extractor
captured it as a (column-truncated) row "Standard output load for te". And the
renderer's OUTSIGTYPE==='CURRENT' emission was wrong on both ends — it printed the
note (after the underline, invisible to the validator gate) for many -C current
models whose staged originals never had it, and never placed it correctly for the
models that do.
Fix is data-driven, matching the rest of the template approach:
- derive-dsca-templates.js: detect the "Standard output load..." line, capture it
as a per-model `loadNote` property, and exclude it from rows. Regenerated
dsca-templates.json — surgically clean: only the 5 DSCA39 models changed (lost
the truncated row, gained loadNote); all 121 others byte-identical.
- datasheet-exact.js: emit `dscaTpl.loadNote` (blank line + note) before the footer
underline, only for models that have it; removed the OUTSIGTYPE-based emission.
STAGE 3 re-validation: FINAL-TEST CLEAN 85 -> 88, mismatches 9 -> 6, matches
2206 -> 2278. DSCA39-01/02/07 now fully clean; DSCA39-01 byte-content-verified.
No regression — the -C current models stayed clean and no longer carry the
spurious after-underline note.
The 6 remaining dirty models (DSCA38-05/-1793/-19C/-19E, DSCA39-05, DSCA39-1950)
are ALL retest data-vintage: the staged .TXT is an older test run than the DB
latest-wins record (Supply Current / Linearity differ by more than rounding).
Not render bugs — cannot be reconciled against an older sheet.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
formatMeasuredExact now applies Math.fround to the parsed value before toFixed.
The DOS QuickBASIC computed/stored these as single-precision floats, so the
last-digit rounding at the .5 boundary follows single, not double, precision.
Without it, double-precision toFixed flipped boundaries (9.9995 -> "9.999" vs
golden "10.000"; 46.85 -> "46.9" vs "46.8"; .45 -> "0.5" vs "0.4"; 3.3325 ->
"3.333" vs "3.332"). Verified each against the staged golden.
STAGE 3 re-validation: FINAL-TEST CLEAN models 68 -> 85 (+17), mismatches
26 -> 9, cert matches 2123 -> 2206. Zero regression — every remaining dirty
model was already dirty pre-fix; no previously-clean model flipped.
The 9 remaining are NOT rounding:
- 4 models (DSCA38-05/-1793/-19C/-19E): Supply Current retest data-vintage — the
staged .TXT is an older test run than the DB latest-wins record; not a render
bug, can't reconcile against an older sheet.
- 5 models (DSCA39-01/02/05/07/1950): STAGE 1 template artifact — the footer note
"Standard output load for test is 250 ohms." was mis-captured as a truncated
parameter row. A renderer-side fix was attempted but emitted the note for all
current-output models (regressed 24 clean -C models), so it was reverted; needs
a targeted STAGE 1 extractor fix instead.
Renamed dsca-clean68-models.json -> dsca-clean-models.json (now 85 models).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Deployed file is C:\Shares\testdatadb\templates\datasheet-exact.js; this
reconciles the repo copy + adds dsca-templates.json (STAGE 1 output).
What changed in generateExactDatasheet (DSCA family only; 5B/8B/7B/DSCT/SCMVAS
paths byte-unchanged):
- Load dsca-templates.json once at module top (126 per-model layouts).
- DSCA Final-Test now renders names + specs from the staged template rows, not
the single hardcoded DATA_LINES['DSCA'] + buildTSpecs DSCA branch.
- Value-bearing raw_data STATUS groups map positionally onto the spec-bearing
template rows; empty-spec rows (240VAC Withstand / Hi-Pot) render blank+PASS.
Removed the duplicate hardcoded 240VAC/Hi-Pot footer for DSCA (now rows).
- ACCURACY header uses the template accOut ("Output (V)"/"Output (mA)") with '-'
rule separators instead of "Vout (V)" + '='.
- Header/columns match the staged originals (Measured Value*, 25/15/19/6 rule).
Two real bugs fixed (both are the handoff's "lines drop" / wrong-value defect):
- formatMeasuredExact reads the value from index 4 so negative signs survive
("PASS-4.24..." -> "-4", not "4"); also decimal-code N -> toFixed(N) exactly
(DSCA differs from 5B/8B where code 2 means 1 decimal).
- parseRawData no longer consumes the first DSCA STATUS group as a bare
step-response line when that line is absent (dropped 3 rows on e.g. DSCA39-01).
Safety: when value count != spec-row count the positional zip is ambiguous
(subtype measures load points the template omits, e.g. DSCA49 5mA pair), so the
cert is SKIPPED (null) and left for STAGE 3 per-subtype mapping rather than
emitting misaligned data.
Validation: DSCA38-05 (SN 180224-1) Final-Test block byte-identical to its
staged original. 92/126 templated models render cleanly; 7 ambiguous + 27
no-spec skip. Remaining ACCURACY-block spacing diffs are the deferred cosmetic
gap. NOT YET LIVE: testdatadb service not restarted, nothing re-pushed to
Hoffman (STAGE 3 gate).
Coverage gap to resolve before publish: only 126/357 DSCA models in the DB have
a staged template (56,074 certs, 70.1%); 231 models / 23,866 certs have none and
now render null — needs a STAGE 1 extension (more staged originals).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Repo copy only (review before deploying to C:\Shares\testdatadb). Folds RTD
(sensorNum 7) into the temperature path so the ACCURACY input column shows
'Temp. (C)' with signed temperature values, matching the original DOS-generated
datasheets and thermocouples (3-6). raw_data stimulus is already in deg C; no
conversion. getSensorNum and the i==13 ohm/ohm unit override are untouched.
Verified read-only against deployed env: 8B35 SN 179553-13 now shows Temp (C);
regression over 184 5B/8B renders -> 15 RTD changed (intended), 0 non-RTD changed.
Does NOT address Defect B (DSCA template). See DATASHEET-RTD-BUG-DIAGNOSIS-2026-06-17.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Extends the Test Datasheet Pipeline on AD2:C:\Shares\testdatadb to
generate web-published datasheets for the SCMVAS-Mxxx (obsolete) and
SCMHVAS-Mxxxx (replacement) High Voltage Input Module product lines.
Both are tested either with the existing TESTHV3 software (production
VASLOG .DAT logs) or in Engineering with plain .txt output.
Key changes on AD2 (all deployed 2026-04-12 with dated backups):
- parsers/spec-reader.js: getSpecs() returns a `{_family:'SCMVAS',
_noSpecs:true}` sentinel for SCMVAS/SCMHVAS/VAS-M/HVAS-M model prefixes
so the export pipeline does not silently skip them for missing specs.
- templates/datasheet-exact.js: new Accuracy-only template branch
(generateSCMVASDatasheet + helpers) that mirrors the existing shipped
format byte-for-byte. Extraction regex covers both QuickBASIC STR$()
output formats: scientific-with-trailing-status-digit (98.4% of
records) and plain-decimal (1.6% of records above QB's threshold).
- parsers/vaslog-engtxt.js (new): parses the Engineering-Tested .txt
files in TS-3R\LOGS\VASLOG\VASLOG - Engineering Tested\. Filename SN
regex strips optional trailing 14-digit timestamp; in-file "SN:"
header is the authoritative source when the filename is malformed.
- database/import.js: LOG_TYPES grows a VASLOG_ENG entry with
subfolder + recursive flags. Pre-existing 7 log types keep their
implicit recursive=true behaviour (config.recursive !== false).
importFiles() routes VASLOG_ENG paths before the generic loop so a
VASLOG - Engineering Tested/*.txt path does not mis-dispatch to the
multiline parser.
- database/export-datasheets.js: VASLOG_ENG records are written
verbatim via fs.copyFileSync(source_file, For_Web/<SN>.TXT) for true
byte-level pass-through, with a graceful raw_data fallback when the
source file is no longer on disk.
Deploy outcome:
- 27,503 SCMVAS/SCMHVAS datasheets rendered (27,065 from scientific +
438 from plain-decimal PASS lines, post-patch rerun)
- 434 Engineering-Tested .txt files pass-through-copied to For_Web
- 0 errors across both batches
Repo layout added here:
- scmvas-hvas-research/: discovery artifacts (source .BAS, hvin.dat,
sample .DAT + .txt, binary-format notes, IMPLEMENTATION_PLAN.md)
- implementation/: staged final code + deploy helpers + local test
harness + per-step verification scripts
- backups/pre-deploy-20260412/: independent local snapshot of the 4
AD2 files replaced, pulled byte-for-byte before deploy
All helper scripts fetch the AD2 password at runtime from the SOPS
vault (clients/dataforth/ad2.sops.yaml). None of the committed files
contain the plaintext credential. Known vault-entry hygiene issue
(stale shell-escape backslash before the `!`) is documented in the
fetcher comments and stripped at read-time; flagged separately for
cleanup.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
