feat(consult): prompt and Skill read from the evidence card (Skill 6.9.17)

The natal system prompt now says: the card in claim_cards is the chart
evidence for this answer, quote it as given, look up one further section of
this calculation with read-consultation-evidence before writing, and read
evidence_card.backstage as a confidence cap. The "use every executed layer"
and must_use_layers sentences are replaced; local_layers paths now point at
the card. SKILL.md 关联技法完整调取 / 0.0.1 and router 0.7 state that the
full result stays in receipts, the 本轮技法 panel and reports while web chat
answers from the card; computing the full spectrum is unchanged. Skill and
package version 6.9.16 -> 6.9.17 (tests/run_all.py 三栏).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8

tests/run_all.py

@@ -688,8 +688,10 @@ def t99():
 @test("Package version is consistent")
 def t100():
     from jyotish_vedic import __version__
-    # 原值＝6.9.15；新值＝6.9.16。原因＝婚恋三层模型与条件大运接入，新增 skill 版本目录。
-    assert __version__ == '6.9.16'
+    # 原值＝6.9.16；新值＝6.9.17。原因＝网页普通对话写答案改读数据卡（全谱系计算不变，
+    # 完整结果留在回执 / 本轮技法 / 报告），SKILL.md「关联技法完整调取」与 0.0.1 同步
+    # （TASK-consult-evidence-card-20260927 T4）。
+    assert __version__ == '6.9.17'
 
 # ── v6.9.11 Precision gate tests ──
 @test("Transit uses Swiss Ephemeris")