d11cebacf8
fix: harden accuracy and api guardrails
2026-06-26 00:44:09 +08:00
494e387018
Productize jyotish app release surface
2026-06-24 13:37:33 +08:00
3b167e28c3
v6.1.8: Improve Nishkapata yoga recall
2026-06-08 10:57:42 +08:00
ae959f362b
docs: align v6.1.7 skill entry and validation report
...
- Update SKILL.md to reflect five-system Dasa Convergence wording
- Clarify v6.1.7 as D9/D60 YogaContext integration plus Sankha tightening
- Refresh validation_logic_report.json after verification run (F1=95.02, FP=36, FN=67)
2026-06-08 10:30:02 +08:00
3c64e4576f
v6.1.7: Push Yoga validation F1 above 95 percent
...
- Inject D9/D60/Panchanga context into yoga and full-reading flows
- Add --context-json support for explicit YogaContext payloads
- Tighten Sankha Yoga movable-sign branch to require distinct L1/L10 lords
- Regenerate validation_logic_report: FP 36, FN 67, F1 95.02%
2026-06-08 10:27:57 +08:00
57e426515d
v6.1.6: Add five-system dasha convergence
2026-06-07 20:16:47 +08:00
0406723b7e
v6.1.3: D9/D60 engine upgrade + 5 bottleneck rules tuned
...
Engine (yoga_engine.py):
- Added D60/Shashtiamsa context injection (d60_house_of, d60_sign_of, etc.)
- Added D9 dignity queries (is_exalted_in_d9, is_own_sign_in_d9, etc.)
- Added functional_malefics() / functional_benefics()
- Added is_shashtiamsa_evil/good() and vaiseshikamsa_score()
- Exposed all new methods to rule expression sandbox
Data (_compute_one_chart.py):
- Generate D60 positions alongside D1/D9
- Inject D60 into context for all computed charts
Rules (yoga_rules.json):
- thrikaala_gnana: D1 strong = exalted/own/moola only (kendra/trikona removed)
+ D9 strong check (at least 1 of 3 in D9 exalted/own/moola)
FP: 12→0, FN: stable
- dharidhra: restored method1 (L2/L11 in dusthana + unfriendly navamsa + malefic aspect)
FN reduced
- bandhubhisthyaktha: added is_shashtiamsa_evil(lord_4)
- nishkapata: added vaiseshikamsa_score(lord(1)) >= 15
- kapata: reverted functional_malefics (caused 22 FN), back to MALEFICS
Validation:
- FP: 45→39 (-6)
- FN: 72→67 (-5)
- F1: 94.35%→94.88% (+0.53%)
- Precision: 95.60%→96.18% (+0.58%)
New scripts:
- scripts/add_d60_to_test_charts.py: batch D60 augmentation
- scripts/ashtottari_dasha.py, yogini_dasha.py, kalachakra_dasha.py
- scripts/report_orchestrator.py
D60 data added to all 60 standard test charts.
2026-06-07 14:44:53 +08:00
2a3359ea0f
v6.1.1-update: Refresh validation_logic_report.json with real metrics
...
Actual metrics after v6.1.1 aspect direction fixes:
- FP: 45 (was incorrectly reported as 9)
- FN: 72 (was incorrectly reported as 22)
- F1: 94.35% (confirmed accurate)
- Precision: 95.60% (confirmed accurate)
- Recall: 93.14%
2026-06-07 14:26:05 +08:00
fffdbda22c
Release v6.0.46: fix 5 completely wrong yoga rules, Precision 83.3%→92.5%, F1 87.2%→92.2%
...
- Fix kaalanirdesat_puthra_yoga (36→0 FPs): PyJHora 227/228 logic
- Fix sapthasankhya_sahodara_yoga (27→0 FPs): PyJHora L12+Mars+Moon+Jupiter+no Venus
- Fix sarpasaapa_yoga (25→0 FPs): PyJHora 212-215 variants
- Fix pushkala_yoga (9→0 FPs): PyJHora BVR-26 L1+Moon+dispositor
- Fix koorma_yoga (9→0 FPs): PyJHora BVR-54 method1
- Fix bhratrumooladdhanaprapti_yoga (9→0 FPs): PyJHora BVR-136
- Update hardcoded tests to match correct PyJHora logic
2026-06-06 21:54:59 +08:00
0003d0be88
Release v6.0.44 fix JD timezone bug in reference data
...
- Fix: _compute_one_chart.py JD calculation used PyJHora's
gregorian_to_jd() which ALWAYS returns noon JD regardless of time.
Changed to swe.julday() with correct UTC hour.
- Impact: All 60 test charts with non-noon birth times had wrong
ascendants and house assignments (e.g. Einstein went from
Scorpio Asc -> Gemini Asc, matching Swiss Ephemeris)
- Cross-validated: Swiss Ephemeris (industry gold standard) and
xalen-ephemeris (Rust, 5M chart oracle test)
- New baseline: F1=93.50% (Precision=93.82%, Recall=93.18%)
- Regenerated: standard_test_charts.json, planet_positions_60.json,
validation_logic_report.json
- Quality gate: compile/json/audit/BPHS/pytest/golden all passed
2026-06-06 14:43:11 +08:00
26835f80b8
Release v6.0.43 Yoga F1 93.76%
...
- Fix 3 PyJHora source bugs (kalaanidhi Yoga JUPITER_ID->VENUS_ID x2,
krisanga Yoga missing return)
- Implement planet_in_house_with_aspect_or_conjunction semantic condition
- Fix lagna_lord_in_dry_sign: dry_signs set correction (Capricorn->Taurus),
add ll_owner_dry check using dynamic co-lord resolution
- Regenerate reference data against fixed PyJHora
- F1 93.28% -> 93.76% (FN 96->86, FP 44 unchanged)
2026-06-06 09:58:28 +08:00
0d582dbaa3
Release v6.0.42 Yoga source parity
2026-06-06 00:28:17 +08:00
86e7d03c4a
Release v6.0.41 Yoga source parity
2026-06-05 23:20:53 +08:00
ede8b96d2c
Release v6.0.40 Yoga source parity
2026-06-05 22:37:25 +08:00
94be318d56
Release v6.0.39 Yoga source parity
2026-06-05 22:03:06 +08:00
58fc615b16
fix: align yoga source rules
2026-06-05 20:31:14 +08:00
4b840b5c2a
fix: tighten yoga precision pass
2026-06-05 16:39:05 +08:00
44221191f6
fix: align high-impact yoga logic
2026-06-05 16:17:38 +08:00
8da45c56b3
feat: add yoga logic validation and varga fixes
2026-06-05 14:30:20 +08:00
732642856