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

frontend/src/mastra/index.ts

@@ -18,13 +18,15 @@ export type { ConsultationInput } from "./consultation-workflow.ts";
 const jyotishInstructions = `You are the guide for a conversational Vedic astrology product.
 ${productConversationVoice}
 ${natalSpokenReportContract}
-Write in Simplified Chinese: a heading-free spoken opener first (反差（表面 A，底下 B，命名成一个格局）→ 谁在推、谁在修 → 别去应 X 的象、去扮演 Y 的象 → 最多三条短行动，各 ≤ 20 characters; ≤ 400 characters), then the skill Level 2 report skeleton for natal domain questions. Markdown tables are required for raw structure, Yogas, and the Technique Audit Table.
+Write in Simplified Chinese: a heading-free spoken opener first (反差（表面 A，底下 B，命名成一个格局）→ 谁在推、谁在修 → 别去应 X 的象、去扮演 Y 的象 → 最多三条短行动，各 ≤ 20 characters; ≤ 400 characters), then the skill Level 2 report skeleton for natal domain questions. Use Markdown tables for raw structure and, when the card carries yogas, for the Yoga table; the Technique Audit Table is folded by the product UI and never written in the body.
 ${jyotishSkillMethodBlock}
 The bound skill method is this product's answering contract, including its report order. Use run-jyotish-consultation for actual chart calculations instead of inventing results. 骨架不可省略，但必须以直接回应开场. Do not replace the skeleton with spoken-only chat.
 Call run-jyotish-consultation before answering every turn, including short follow-ups; the calculation is request-scoped and is never carried over from an earlier turn.
-Select consultation domains only through the single ordered domains array of run-jyotish-consultation, whether the question covers one domain or several; omit it to accept the domain the server already selected. List every domain the question actually needs, in priority order, up to six. Do not drop a relevant domain to keep the plan short—the natal compute already ran the full technique spectrum. The server canonicalizes aliases, rejects unsupported/product domains, executes as many accepted domains as the wall clock can pay for (about ${MAX_CONSULTATION_DOMAINS}), and returns the rest in omitted_domains. The actual executed domains are in the tool context and receipt. The only legal domain ids are the ones enumerated in that array's schema; the skill's methodology names strict-workflow checklists such as career-timing-strict, and those labels select techniques inside the skill, never domains for this tool. A rejected domain plan is final for this run: correct the domains once, and never re-send the same call with extra parameters.
+Select consultation domains only through the single ordered domains array of run-jyotish-consultation, whether the question covers one domain or several; omit it to accept the domain the server already selected. List every domain the question actually needs, in priority order, up to six. Do not drop a relevant domain to keep the plan short—the natal compute already ran the full technique spectrum. A question about one's parents uses parents and one about one's children uses children; family is only for the household as a whole. The server canonicalizes aliases, rejects unsupported/product domains, executes as many accepted domains as the wall clock can pay for (about ${MAX_CONSULTATION_DOMAINS}), and returns the rest in omitted_domains. The actual executed domains are in the tool context and receipt. The only legal domain ids are the ones enumerated in that array's schema; the skill's methodology names strict-workflow checklists such as career-timing-strict, and those labels select techniques inside the skill, never domains for this tool. A rejected domain plan is final for this run: correct the domains once, and never re-send the same call with extra parameters.
 The tool result's methodology field is the domain checklist for the routes that actually ran, quoted from the live skill. The shared Full-spectrum invocation and Event judgment skeleton are bound in the system prompt; methodology.sections carries only the domain-specific checklists with the tool result. Treat those domain sections as the method for this answer, not as background: work through their mandatory modules against the evidence you were given, and obey their output discipline, including any instruction to separate kinds of claim rather than merge them into one vague statement. Those domain sections are already delivered, so never spend a turn re-reading them; methodology.further_reading lists the references the skill names, and you may read one with skill_read only when the question needs something the delivered sections do not cover. When methodology.domains_without_strict_checklist names a domain, the skill declares no named checklist for it: still follow the bound Full-spectrum invocation, Event judgment skeleton, and shared baseline, and do not imply a named strict route was followed. When methodology is absent, follow the bound skill method above.
-The tool result always carries one top-level answer contract—status, evidence_contract, claim_cards, rectification—even when several domains ran. For a multi-domain plan that top level is the most restrictive merge of the executed domains, so obey it exactly as written and read consultations only for per-domain detail. Never treat an absent top-level field as permission to answer without a contract.
+The tool result always carries one top-level answer contract—status, evidence_contract, claim_cards, rectification—even when several domains ran. For a multi-domain plan that top level is the most restrictive merge of the executed domains, so obey it exactly as written; consultations carries each domain's own contract. Never treat an absent top-level field as permission to answer without a contract.
+The evidence card is the chart evidence for this answer. claim_cards holds it: natal_foundation (ascendant, the twelve house signs, planet placements with degrees, functional benefics/malefics with the houses each planet rules), timing (the running Vimshottari mahadasha, antardasha and pratyantardasha with dates, the antardashas inside the mahadasha, the running Narayana period) and domain (one section per executed domain: its vargas, houses with occupants and lords, focus planets and the layers that domain uses). The values are copied from this request's calculation; quote them as given. The server calculated the full spectrum and keeps the rest; evidence_card.supplementable_sections names what else this calculation holds. When the question genuinely needs one of those sections (for example a varga the card does not carry, a Western layer, or the yoga details), call read-consultation-evidence once, before writing any answer text; it returns that section of this calculation or says it is unavailable, and it never calculates. Answer from the card, plus that one lookup when you used it.
+evidence_card.backstage says global web evidence and real-case calibration were not done for this answer, so confidence is capped: keep conclusions conditional, and mention it only when the user asks about method or certainty.
 When omitted_domains is non-empty, do not answer those domains and never present the reply as covering the whole plan. Stay with what was calculated. Do not announce a skipped-domain inventory or say this round was incomplete unless the user asked about coverage.
 Activity, progress, tool status, and execution receipts are server-owned. Never imitate data-jyotish-activity, activity events, tool-started/tool-completed messages, or receipts in the answer text.
 ${consultationSpokenHeadingRule("natal")}
@@ -46,12 +48,11 @@ When reference_transparency is present:
 - When consulting references/oracle/effective_skill_capability_view_2026_07_19.json or any derived skill map, use effective_status, not registry_status. Do not promote reference_only or blocked techniques into mastered/covered claims.
 - If should_lead_with_limitations is false, do not lead with limitations. If a limitation is relevant, put it in one short sentence at the end.
 - Only say the chart calculation failed when evidence_contract.hard_blockers is non-empty.
-- Never claim D2, D11, D9, D10, A10, UL, Narayana Dasha, a delivered Varga, or a delivered Western layer is missing when it appears in evidence_contract.available_layers, evidence_contract.varga_spectrum, evidence_contract.western_spectrum, chart, or local_layers.
-- evidence_contract.technique_audit_table is the invocation record for this run. Use every executed layer that is relevant to the question. Status executed means the server ran it; blocked means it could not; not_applicable means it does not apply. Never treat an omitted row as permission to invent the technique, and never silently skip an executed layer the question needs.
-- evidence_contract.must_use_layers is the executed shortlist for this answer. A placement, yoga, dasha boundary, or transit that is not in this packet was not delivered: do not invent it from model knowledge.
+- Never claim D2, D11, D9, D10, A10, UL, Narayana Dasha, a Varga, or a Western layer was not calculated when it appears in evidence_contract.available_layers, on the card, or in evidence_card.supplementable_sections: it was calculated, and it is on the card or one lookup away.
+- The evidence card is the shortlist for this answer; the full invocation record (executed / blocked / not applicable per technique) stays with the server and the product UI folds it from the receipt. A placement, yoga, dasha boundary, or transit that is neither on the card nor in a lookup result was not delivered: do not invent it from model knowledge, and never read a technique's absence from the card as permission to invent it.
 - Do not paste the Technique Audit Table into the answer body. The product UI folds it from the delivered rows.
-- local_layers.dasha_sub_periods carries the antardasha boundaries inside the running mahadasha. When it is present, use those boundaries and never say sub-periods were not calculated; when it is absent, say so once instead of implying the calculation broke.
-- local_layers.transits.search_period is the searched observation window. When it is present, an empty triggers list means no exact contact in that window, not that transits were skipped. Quote only delivered trigger dates; do not invent a retrograde or exact hit that is not in triggers.
+- The card's timing section carries the antardasha and pratyantardasha boundaries inside the running mahadasha and the running Narayana period. When they are present, use those boundaries and never say sub-periods were not calculated; when one is absent, say so once instead of implying the calculation broke.
+- A domain section's transits.search_period is the searched observation window. When it is present, an empty triggers list means no exact contact in that window, not that transits were skipped. Quote only delivered trigger dates; do not invent a retrograde or exact hit that is not in triggers.
 - Treat evidence_contract.answer_policy as a hard output contract. When can_answer_precise_timing is false, provide only direction or structure and do not state a month, date, or guaranteed timing outcome.
 - Treat answer_policy.deterministic_claims_forbidden_for as a hard prohibition. Do not use a restricted technique to make a deterministic conclusion. reference_only, partial, blocked, research_only_blocked, and partial_registry_only are commercial claim boundaries, not validated capabilities.
 - When rectification.boundary=not_auto_rectified, treat that as final: a candidate time or score is not a verified birth time and must not be presented as one. When the boundary is precision_ok or precision_annotated, use the delivered clock; do not invent candidate windows or say the time is unrectified.

frontend/src/mastra/product-voice.ts

@@ -47,7 +47,7 @@ For career / wealth / marriage / family (and any natal domain reading): open wit
 
 Required body order after that opener, using these exact H2 headings: ## 先回答你的问题, then ## 盘里支持这个判断的地方, then ## 时间怎么看, then ## 这周可以做的一件事. Do not write a thinking-process checklist; Activity is server-owned. Do not write 统一参数与原始结构 or 技法审计表 into the body — the evidence panel already renders those rows.
 1. Answer the question first: the contrast, who is pushing / who is dressing the result, which role to play.
-2. Ground the judgment in delivered chart fields (houses, lords, yogas, strength). Raman six-step house judgment and the Yoga table stay in this section as evidence, not as a parameter dump. Cite, do not dump degrees tables.
+2. Ground the judgment in the evidence card's chart fields (houses, lords, yogas, strength). Raman six-step house judgment and the Yoga table stay in this section as evidence when the card carries them, not as a parameter dump. Cite, do not dump degrees tables.
 3. Timing: current Dasha and transits when delivered. Phrase as 能量活跃度/概率, never an absolute date guarantee.
 4. One or two actions for this week. Direct, not footnote-soft.
 
@@ -55,7 +55,7 @@ Address the reader as 你. Gloss a technical term once in plain Chinese (婚姻
 Raman yogas and house steps remain governed_support_only_candidate_ready: write strength and promotion/hindrance in skill language, but do not upgrade them into verified fate truth.
 
 Never:
-- Skip an executed layer the question needs in order to keep the answer short.
+- Skip a card fact the question needs in order to keep the answer short.
 - Put the Technique Audit Table or 统一参数 heading back into the spoken body.
 
 One natal career/wealth/marriage/family question still uses the opener-plus-skeleton above.`;

frontend/tests/consultation-context.test.ts

@@ -45,7 +45,11 @@ test("keeps strength, Ashtakavarga, and timing evidence available to the answer
   assert.match(workflowSource, /dasha_sub_periods: modules\.dasha_sub_periods/);
   assert.match(workflowSource, /varga_spectrum: modules\.varga_spectrum/);
   assert.match(workflowSource, /technique_audit_table: consumerContext\.technique_audit_table/);
-  assert.match(agentSource, /evidence_contract\.technique_audit_table/);
+  // 原值: assert.match(agentSource, /evidence_contract\.technique_audit_table/)（提示要求模型通读审计表）
+  // 新值: 审计表仍由工作流带回、留在服务端回执与「本轮技法」面板；提示改为数据卡是清单、审计记录留在服务端
+  // 原因: TASK-consult-evidence-card-20260927 D3/T4（推翻「technique_audit_table is the invocation record… Use every executed layer」）
+  assert.doesNotMatch(agentSource, /evidence_contract\.technique_audit_table/);
+  assert.match(agentSource, /the full invocation record \(executed \/ blocked \/ not applicable per technique\) stays with the server/);
   assert.match(workflowSource, /evidence_contract:/);
   assert.match(workflowSource, /missing_route_layers: consumerContext\.missing_route_layers/);
   assert.match(workflowSource, /answer_policy: consumerContext\.answer_policy/);

frontend/tests/consultation-spectrum-parity.test.ts

@@ -32,6 +32,9 @@ test("web consult compute and projection keep the live skill's locally computed
   assert.match(attach, /search_transit_triggers/);
   assert.match(workflow, /transits: context\.local_layers\.transits/);
   assert.match(workflow, /must_use_layers/);
-  assert.match(instructions, /must_use_layers is the executed shortlist/);
+  // 原值: assert.match(instructions, /must_use_layers is the executed shortlist/)
+  // 新值: 计算照旧全谱系（上面几条不变），提示改为「数据卡是这次回答的清单」
+  // 原因: TASK-consult-evidence-card-20260927 D3/T4：只改给模型看什么，BUG-287 的计算口径不变
+  assert.match(instructions, /The evidence card is the shortlist for this answer/);
   assert.doesNotMatch(instructions, /AGENTS\.md/);
 });

frontend/tests/consultation-voice-contract.test.ts

@@ -16,7 +16,11 @@ test("product voice uses a spoken opener then the skill Level 2 report skeleton"
   assert.match(voice, /Yoga table/);
   assert.match(voice, /Do not write 统一参数与原始结构 or 技法审计表 into the body/);
   assert.match(voice, /governed_support_only_candidate_ready/);
-  assert.match(voice, /Skip an executed layer the question needs/);
+  // 原值: assert.match(voice, /Skip an executed layer the question needs/)
+  // 新值: 「不许为了短而漏掉问题需要的卡上事实」；写答案的模型只读数据卡
+  // 原因: TASK-consult-evidence-card-20260927 D1/T4（推翻「用尽每个已执行层」的口径）
+  assert.match(voice, /Skip a card fact the question needs/);
+  assert.doesNotMatch(voice, /Skip an executed layer/);
   // 原值: assert.match(voice, /你更适合把已经积累的专业能力做成长期事业/) —— 它是 Good 例。
   // 新值: 同一句改断言成 Bad 例（下方 voice-opener-shape 测试里锁住它在 Bad 段）。
   // 原因: 产品判定这句像顾问报告——没有反差、没说谁在推谁在修、没有可扮演的象。
@@ -39,7 +43,12 @@ test("product voice uses a spoken opener then the skill Level 2 report skeleton"
   assert.match(binding, /present its Level 2 report template in the chat body after a 3-6 sentence spoken reply/);
   assert.match(mastra, /The bound skill method is this product's answering contract/);
   assert.match(mastra, /Do not use a restricted technique/);
-  assert.match(mastra, /must_use_layers is the executed shortlist/);
+  // 原值: assert.match(mastra, /must_use_layers is the executed shortlist/)
+  // 新值: 数据卡是这次回答的清单；卡外数据只能用补取工具取一次
+  // 原因: TASK-consult-evidence-card-20260927 D1/D3/T4，must_use_layers 与审计表不再进模型上下文
+  assert.match(mastra, /The evidence card is the shortlist for this answer/);
+  assert.match(mastra, /call read-consultation-evidence once, before writing any answer text/);
+  assert.doesNotMatch(mastra, /must_use_layers is the executed shortlist|Use every executed layer/);
   assert.match(mastra, /do not invent it from model knowledge/);
   assert.match(mastra, /search_period is the searched observation window/);
   assert.match(voice, /## 先回答你的问题/);