root/Jyotisha
2
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

v6.1.10: Wire DK and RTN into theme reports

Browse Source
This commit is contained in:
732642856
2026-06-08 14:06:13 +08:00
parent 5d74d9544d
commit 068a8e2818
7 changed files with 164 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+21
View File
@@ -1,5 +1,26 @@
# 印度占星 Skill 更新日志
## v6.1.10（2026-06-08）—— P0 规划继续落地：Darakaraka / RTN 接入主题化报告
> **目标**：继续执行覆盖度地图中的 P0 规划，把已经存在但未充分进入 full-reading / 主题报告叙事链的婚姻核心技法真正接线。
### 关键改进
- `scripts/jyotish_engine.py`：将 `scripts/darakaraka_reader.py` 接入 `full-reading.modules.jaimini.darakaraka`，输出 DK 行星、星座、宫位、D9 尊严、合相影响、婚姻质量评分和叙事。
- `scripts/orchestrator_bridge.py`：新增 Jaimini/关系层注入，把 `jaimini.darakaraka` 与 `rashi_tulya_navamsa` 转为婚姻主题证据；RTN 的凶星合相与 Gunas 平衡也分别注入健康/灵性主题。
- `references/technique_registry.json`：补齐 Darakaraka / Rashi Tulya Navamsa 的知识引用与 v6.1.10 验证说明。
- `docs/roadmap/jyotish_technique_coverage_map.md`：更新 P0 规划状态，标注 DK、RTN、主题报告、Yoga F1 95%+ 的当前落地状态。
### 验证
```bash
python3 -m py_compile scripts/jyotish_engine.py scripts/orchestrator_bridge.py scripts/darakaraka_reader.py scripts/rashi_tulya_navamsa.py
python3 scripts/jyotish_engine.py full-reading --year 1990 --month 6 --day 15 --hour 10 --minute 30 --lat 39.9 --lon 116.4 --tz 8
python3 scripts/orchestrator_bridge.py /tmp/jyotish_full_reading_v6110.json
python3 scripts/audit_capabilities.py --mode validate
python3 scripts/run_quality_gate.py --skip-yoga-logic
```
---
## v6.1.9（2026-06-08）—— 本地散落资料安全入仓：Benchmark、竞品研究、覆盖度地图与PDF验证方法论
> **目标**：把历史 WorkBuddy 会话中散落但有长期价值的资料，按公开仓库隐私边界整理入 `yinduzhanxing`，避免遗漏，同时不上传真实用户个案、原始 PDF 文本或 raw full-reading 输出。
README.md
+10 -10
View File
@@ -266,24 +266,24 @@ Examples:
## Project Status
**Current version:** `v6.0.23-full-reading-regression`
**Current version:** `v6.1.10-dk-rtn-theme-bridge`
### Recently Completed
- `v6.0.11` — Shadbala internal invariant validation (1200/1200 pass); downgraded to `partial`
- `v6.0.18` — Solar Return / Varshaphala + Muntha
- `v6.0.20` — Narayana Dasha / Rishi Dasha
- `v6.0.21` — Muhurta (Panchanga-based electional astrology)
- `v6.0.22` — Nakshatra Advanced (Chandra Bala / Tara Bala)
- `v6.0.23` — Full-reading regression fix (45 modules, 0 errors)
- `v6.1.10` — Darakaraka deep reader wired into `full-reading.modules.jaimini.darakaraka`; thematic reports now consume real DK and Rashi Tulya Navamsa evidence.
- `v6.1.9` — Public/sanitized benchmark suite, competitive research, coverage roadmap and PDF validation methodology added.
- `v6.1.8` — Yoga validation reached F1=95.22% (FP=36, FN=63); thematic reports consume real `full-reading.modules` evidence.
- `v6.1.6` — Five-system Dasha convergence wired into full-reading (Vimshottari + Chara + Yogini + Ashtottari + Kalachakra).
- `v6.0.11` — Shadbala internal invariant validation (1200/1200 pass); downgraded to `partial`.
### Actively Working On (P0)
1. **Chara Dasha rewrite** — align with PyJHora KN Rao method (target: ≥95% match)
2. **Shadbala external calibration** — align with JHora / PyJHora / BV Raman
3. **KP Sub-Lord full implementation** — unequal Vimshottari subdivisions
4. **Bhava Chalit complete** — cusp-based planet reassignment
5. **Sudarshana Chakra traditional** — Sun/Moon/Lagna reference points
3. **Darakaraka / RTN external benchmark** — v6.1.10 has wired the modules; next step is traditional case validation and evidence ranking
4. **KP Sub-Lord full implementation** — unequal Vimshottari subdivisions
5. **Bhava Chalit complete** — cusp-based planet reassignment
6. **Sudarshana Chakra traditional** — Sun/Moon/Lagna reference points
### Next (P1)
SKILL.md
+2 -2
View File
@@ -313,9 +313,9 @@ $PYTHON $SCRIPT <子命令> [参数]
---
**版本**：v6.1.9-public-benchmarks-research-roadmap
**版本**：v6.1.10-dk-rtn-theme-bridge
**创建日期**：2026-04-20
**最后更新**：2026-06-08（v6.1.9 将历史散落资料安全整理入仓：新增 `benchmarks/jyotish/` 公开/虚构 smoke benchmark 套件、`docs/research/jyotish_projects_comparison.md`、`docs/roadmap/jyotish_technique_coverage_map.md` 与 `references/validation/pdf-chart-reading-validation-methodology.md`。v6.1.8 Yoga 指标保持有效：F1=95.22%，FP=36、FN=63；Yoga 当前以 `references/validation_logic_report.json` 为准。）
**最后更新**：2026-06-08（v6.1.10 继续落地 P0 规划：`full-reading.modules.jaimini.darakaraka` 已接入 Darakaraka 深度解读，主题化报告桥接层已消费 `jaimini.darakaraka` 与 `rashi_tulya_navamsa`，为婚姻/健康/灵性主题补入真实 DK/RTN 证据。v6.1.9 已将历史散落资料安全整理入仓；v6.1.8 Yoga 指标保持有效：F1=95.22%，FP=36、FN=63。）
---
docs/roadmap/jyotish_technique_coverage_map.md
+8 -8
View File
@@ -544,10 +544,10 @@
### P0 (最高优先级) — 影响核心解盘质量
1. **Darakaraka深度解读** — 婚姻分析核心缺口
2. **Rashi Tulya Navamsa** — 多维度交叉验证基础
3. **主题化报告重构** — 从"罗列"到"叙事"
4. **Yoga F1提升至95%+** — 精度是底线
1. **Darakaraka深度解读** — ✅ v6.1.10 已接入 `full-reading.modules.jaimini.darakaraka`，并注入主题化婚姻报告；仍需外部传统案例 benchmark 深化。
2. **Rashi Tulya Navamsa** — ✅ v6.1.10 已从 `modules.rashi_tulya_navamsa` 注入婚姻/健康/灵性主题证据；当前仍为 partial，需继续完善变体与外部验证。
3. **主题化报告重构** — ✅ v6.1.8 已从"罗列"升级为消费 `full-reading.modules` 的真实叙事；v6.1.10 继续补入 DK/RTN 证据。
4. **Yoga F1提升至95%+** — ✅ v6.1.8 已达到 F1=95.22%，FP=36，FN=63。
### P1 (高优先级) — 丰富技法覆盖
@@ -581,16 +581,16 @@
| **计算精度** | A- | 星盘/Dasha/Varga计算精确 |
| **技法覆盖度** | C+ | 约37%，大量高级技法缺失 |
| **解读深度** | C | 有计算但缺深度叙事 |
| **验证体系** | B | 60张标准盘，Yoga F1=93.8% |
| **验证体系** | B+ | 60张标准盘，Yoga F1=95.22%（v6.1.8），并新增公开/虚构 benchmark 套件 |
| **文档完整度** | B+ | 105篇参考文档 |
| **工程化程度** | B | 模块化良好，但无统一API |
### 成为全球最好需要补什么
**短期 (达到"专业级")**:
- 补齐6大缺失模块
- Yoga F1 → 95%+
- 主题化报告重构
- 继续补齐/验证6大缺失模块中尚未成熟的部分（DK/RTN/主题报告/Yoga 95%+ 已进入可用层）
- 维持 Yoga F1 ≥95%，避免为召回牺牲准确率
- 深化主题化报告的传统案例 benchmark 与 evidence ranking
**中期 (达到"专家级")**:
- 推运体系扩展 (Ashtottari/Yogini/Chara)
references/technique_registry.json
+12 -4
View File
@@ -508,7 +508,10 @@
"karaka"
],
"status": "covered",
"knowledge_refs": [],
"knowledge_refs": [
"references/darakaraka-complete-guide.md",
"references/spouse-multi-layer-methodology.md"
],
"commands": [
"full-reading"
],
@@ -516,7 +519,8 @@
"modules.jaimini.darakaraka"
],
"audit_label": "Darakaraka (DK)",
"missing_impact": "Marriage/partner analysis incomplete without DK."
"missing_impact": "Marriage/partner analysis incomplete without DK.",
"validation_note": "v6.1.10 wires scripts/darakaraka_reader.py into full-reading and thematic reports; output includes DK planet/sign/house, D9 dignity, conjunctions, quality score and narrative."
},
"raj_yoga": {
"name": "Raj Yoga / 王者瑜伽",
@@ -752,7 +756,10 @@
"marriage"
],
"status": "partial",
"knowledge_refs": [],
"knowledge_refs": [
"references/rashi-tulya-navamsa-root-impulse.md",
"references/varga-system-quick-reference.md"
],
"commands": [
"full-reading"
],
@@ -761,7 +768,8 @@
],
"audit_label": "Rashi Tulya Navamsa",
"missing_impact": "D1-D9 同宫对比分析不完整，婚姻/内在潜力判断受限。",
"limitation": "Rashi Tulya Navamsa 分析当前基于 D1 与 D9 同宫行星的简单对比，未完整覆盖所有变体条件（如行星在 D9 中的精确度数对比、Vargottama 与非 Vargottama 的混合情况）。婚姻和内在潜力的深度解读应结合更多分盘（D7、D12）交叉验证。"
"limitation": "Rashi Tulya Navamsa 分析当前基于 D1 与 D9 同宫行星的简单对比，未完整覆盖所有变体条件（如行星在 D9 中的精确度数对比、Vargottama 与非 Vargottama 的混合情况）。婚姻和内在潜力的深度解读应结合更多分盘（D7、D12）交叉验证。",
"validation_note": "v6.1.10 exposes RTN evidence to thematic reports: relationship mapping, curse-yoga warnings and Guna balance are injected from modules.rashi_tulya_navamsa."
},
"marriage_counting": {
"name": "Marriage Counting Method / 婚姻计数法",
scripts/jyotish_engine.py
+33
View File
@@ -3600,6 +3600,39 @@ def cmd_full_reading(args):
ak_d9 = calc_varga(ak_lon, 9)
jaimini_result['karakamsha'] = calc_karakamsha(
ak_d9.get('sign', 'Aries'), ak_d9.get('degree_in_sign', 0))
# Darakaraka 深度解读（v6.1.10）
# Registry 已将 modules.jaimini.darakaraka 标为 covered；这里把独立 DK
# reader 接入 full-reading，使婚姻主题报告可消费真实 DK 画像、D9 状态、
# 合相影响和质量评分，而不是只停留在 chara_karaka 表格层。
try:
from darakaraka_reader import analyze_darakaraka
d9_planets_for_dk = {}
varga_data = report['modules'].get('varga_full', {})
d9_data = varga_data.get('D9_Navamsa', {}) if isinstance(varga_data, dict) else {}
d9_asc = d9_data.get('Ascendant', {}) if isinstance(d9_data, dict) else {}
d9_asc_idx = SIGNS.index(d9_asc.get('sign', 'Aries')) if isinstance(d9_asc, dict) and d9_asc.get('sign') in SIGNS else 0
if isinstance(d9_data, dict):
for d9_pn, d9_pd in d9_data.items():
if d9_pn == '_meta' or d9_pn == 'Ascendant' or not isinstance(d9_pd, dict) or 'sign' not in d9_pd:
continue
d9_sign = d9_pd.get('sign')
d9_deg = d9_pd.get('degree_in_sign', d9_pd.get('degree', 0) % 30)
d9_sign_idx = SIGNS.index(d9_sign) if d9_sign in SIGNS else 0
d9_planets_for_dk[d9_pn] = {
'sign': d9_sign,
'house': ((d9_sign_idx - d9_asc_idx) % 12) + 1,
'degree_in_sign': d9_deg,
'dignity': _get_dignity_level(d9_pn, d9_sign, d9_deg),
}
jaimini_result['darakaraka'] = analyze_darakaraka({
'ascendant': chart.get('ascendant', {}),
'planets': planets,
'context': {'navamsa_planets': d9_planets_for_dk},
}, use_8_karaka=True)
except Exception as dk_e:
jaimini_result['darakaraka'] = {'error': str(dk_e)}
report['modules']['jaimini'] = jaimini_result
except Exception as e:
report['errors'].append(f"jaimini: {e}")
scripts/orchestrator_bridge.py
+78 -2
View File
@@ -401,6 +401,7 @@ class OrchestratorBridge:
self._inject_yoga_module(modules, add)
self._inject_varga_modules(modules, add)
self._inject_strength_modules(modules, add)
self._inject_jaimini_relationship_modules(modules, add)
self._inject_special_points(modules, add)
self._inject_dasa_convergence_module(modules, add)
self._inject_transit_module(modules, add)
@@ -411,7 +412,8 @@ class OrchestratorBridge:
"counts": counts,
"source_modules": sorted(k for k in modules.keys() if k in {
"yoga", "varga_full", "d9_navamsa_expanded", "ashtakavarga", "shadbala",
"special_lagnas", "vivah_saham", "dasa_convergence", "transit_multi_reference",
"jaimini", "rashi_tulya_navamsa", "special_lagnas", "vivah_saham",
"dasa_convergence", "transit_multi_reference",
"dasha", "yogini_dasha", "ashtottari_dasha", "kalachakra_dasha",
}),
}
@@ -543,6 +545,79 @@ class OrchestratorBridge:
details={"source_module": "ashtakavarga", "scores": houses},
))
def _inject_jaimini_relationship_modules(self, modules: Dict[str, Any], add) -> None:
"""Inject relationship evidence from Jaimini DK and RTN modules.
v6.1.10 connects two previously underused P0 relationship layers:
`modules.jaimini.darakaraka` and `modules.rashi_tulya_navamsa`.
Both are deterministic full-reading outputs; the bridge translates them into
marriage/health/spirituality evidence so thematic reports can narrate them.
"""
jaimini = modules.get("jaimini") or {}
darakaraka = jaimini.get("darakaraka") if isinstance(jaimini, dict) else None
if isinstance(darakaraka, dict) and darakaraka and not darakaraka.get("error"):
score = darakaraka.get("marriage_quality_score")
score_text = f"，质量评分约{score:.0%}" if isinstance(score, (int, float)) else ""
conclusion = (
f"Darakaraka：{darakaraka.get('dk_planet', '未知')}落{darakaraka.get('dk_sign', '未知')}"
f"第{darakaraka.get('dk_house', '?')}宫，伴侣原型={darakaraka.get('core_profile', '未标注')}{score_text}。"
)
if darakaraka.get("d9_sign"):
conclusion += f" D9中落{darakaraka.get('d9_sign')}，尊严={darakaraka.get('d9_dignity', '未知')}。"
add(ThemeName.MARRIAGE, ReportTechniqueResult(
technique="jaimini:darakaraka_deep_reader",
chart="D1/D9",
conclusion=conclusion,
sentiment="positive" if isinstance(score, (int, float)) and score >= 0.6 else ("negative" if isinstance(score, (int, float)) and score < 0.4 else "neutral"),
strength=StrengthLevel.STRONG,
details={"source_module": "jaimini.darakaraka", "raw": darakaraka},
))
rtn_module = modules.get("rashi_tulya_navamsa") or {}
rtn = rtn_module.get("analysis") if isinstance(rtn_module, dict) and isinstance(rtn_module.get("analysis"), dict) else rtn_module
if isinstance(rtn, dict) and rtn and not rtn.get("error"):
house_mapping = rtn.get("house_mapping") or {}
curse_yogas = rtn.get("curse_yogas") or []
strength_score = rtn.get("strength_score")
weakness_score = rtn.get("weakness_score")
marriage_planets = house_mapping.get(7) or house_mapping.get("7") or []
summary_parts = []
if marriage_planets:
summary_parts.append(f"RTN第7宫映射行星={marriage_planets}")
if curse_yogas:
summary_parts.append(f"检测到{len(curse_yogas)}个凶星合相命名")
if isinstance(strength_score, (int, float)) and isinstance(weakness_score, (int, float)):
summary_parts.append(f"隐藏力量={strength_score:.0%}，弱点={weakness_score:.0%}")
conclusion = "；".join(summary_parts) or "Rashi Tulya Navamsa 已完成 D1/D9 映射分析。"
sentiment = "negative" if curse_yogas or (isinstance(weakness_score, (int, float)) and weakness_score > strength_score) else "positive"
add(ThemeName.MARRIAGE, ReportTechniqueResult(
technique="rashi_tulya_navamsa:relationship_mapping",
chart="D1/D9",
conclusion=conclusion,
sentiment=sentiment,
strength=StrengthLevel.MODERATE,
details={"source_module": "rashi_tulya_navamsa", "raw": rtn},
))
if curse_yogas:
add(ThemeName.HEALTH, ReportTechniqueResult(
technique="rashi_tulya_navamsa:curse_yogas",
chart="D1/D9",
conclusion=f"RTN凶星合相提示健康/危机压力：{[c.get('name') for c in curse_yogas[:3]]}",
sentiment="negative",
strength=StrengthLevel.MODERATE,
details={"source_module": "rashi_tulya_navamsa", "curse_yogas": curse_yogas},
))
guna = rtn.get("guna_narrative")
if guna:
add(ThemeName.SPIRITUALITY, ReportTechniqueResult(
technique="rashi_tulya_navamsa:guna_balance",
chart="D1/D9",
conclusion=f"RTN Gunas：{guna}",
sentiment="neutral",
strength=StrengthLevel.MODERATE,
details={"source_module": "rashi_tulya_navamsa", "guna_balance": rtn.get("guna_balance")},
))
def _inject_special_points(self, modules: Dict[str, Any], add) -> None:
special = modules.get("special_lagnas") or {}
if isinstance(special, dict):
@@ -791,7 +866,8 @@ def _extract_modules(chart_data: Any) -> Dict[str, Any]:
# Allow passing modules directly in tests.
known = {
"yoga", "varga_full", "d9_navamsa_expanded", "ashtakavarga", "shadbala",
"special_lagnas", "vivah_saham", "dasa_convergence", "transit_multi_reference",
"jaimini", "rashi_tulya_navamsa", "special_lagnas", "vivah_saham",
"dasa_convergence", "transit_multi_reference",
"dasha", "yogini_dasha", "ashtottari_dasha", "kalachakra_dasha",
}
if any(k in chart_data for k in known):