feat: 리밸런싱 엔진 V1 + GAS 버그 수정 (2026-06-13)

주요 변경: - tools/build_rebalance_engine_v1.py: REBALANCE_ENGINE_V1 신규 * account_snapshot 직접 합산(_build_snap_position_map) → 소수주 분리 행 병합 * 레짐 소스 macro.REGIME_PRELIM 최우선 (GAS 와 동일) - src/gas_adapter_parts/gdf_06_rebalance.gs: runRebalanceSheet_() 신규 * Logger.log / getSpreadsheet_() 로 run_all 연동 수정 - src/gas_adapter_parts/gdc_01_fetch_fundamentals.gs * _mergePositionRecord_(): 소수주 중복 행 합산 신규 * parseInt → parseFloat (qty, availQty) - src/gas_adapter_parts/gdf_01_price_metrics.gs * 미보유 종목 SELL_READY → WATCH_EXIT_SIGNAL - spec/41_release_dag.yaml: build_rebalance_sheet 노드 추가 (step_count 63) - spec/51_formula_lifecycle_registry.yaml: REBALANCE_ENGINE_V1 등록 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-13 13:20:14 +09:00
commit ee3e799de1
1474 changed files with 176087 additions and 0 deletions
@@ -0,0 +1,25 @@
+# ADR-0001 Adopt active artifact manifest
+
+## Context
+Temp contains multiple artifact versions and the runtime must read only one active path per artifact key.
+
+## Decision
+Use `runtime/active_artifact_manifest.yaml` as the only runtime selection source.
+
+See `spec/09_decision_flow.yaml` and `tools/validate_active_manifest.py` for the runtime gate and selection checks.
+
+## Alternatives
+- Scan Temp directly
+- Pick latest timestamp
+
+## Consequences
+- Deterministic runtime file selection
+- Lower stale-read risk
+
+## Rollback
+Restore prior manifest only if validation fails.
+
+## Affected files
+- runtime/active_artifact_manifest.yaml
+- spec/09_decision_flow.yaml
+- tools/validate_active_manifest.py
@@ -0,0 +1,22 @@
+# ADR-0002 Authority matrix
+
+## Context
+Output fields need a single declared owner to prevent duplicate writers.
+
+## Decision
+Maintain a governance authority matrix and output-field owner ledger.
+
+## Alternatives
+- Embed ownership in ad hoc notes
+
+## Consequences
+- Ownership collision checks become explicit
+- Review is easier for numeric outputs
+
+## Rollback
+Keep the prior ledger alongside the new one.
+
+## Affected files
+- governance/authority_matrix.yaml
+- spec/03_formulas/output_field_owner_ledger.yaml
+
@@ -0,0 +1,23 @@
+# ADR-0003 Baseline metrics
+
+## Context
+Refactor progress needs a fixed baseline.
+
+## Decision
+Record repository baseline metrics as build output.
+
+See `tools/validate_calibration_registry_v1.py` and `spec/08_scoring_rules.yaml` for baseline-linked validation context.
+
+## Alternatives
+- Report metrics manually in review notes
+
+## Consequences
+- Delta tracking becomes deterministic
+
+## Rollback
+Regenerate from a prior commit if needed.
+
+## Affected files
+- Temp/refactor_baseline_metrics_v1.json
+- tools/validate_calibration_registry_v1.py
+- spec/08_scoring_rules.yaml
@@ -0,0 +1,21 @@
+# ADR-0004 Rule lifecycle
+
+## Context
+Rule proliferation needs a lifecycle policy.
+
+## Decision
+Use proposed -> shadow -> active -> deprecated -> removed.
+
+## Alternatives
+- Free-form status labels
+
+## Consequences
+- Deprecation is explicit
+- Active router reference checks become possible
+
+## Rollback
+Downgrade the rule to shadow if needed.
+
+## Affected files
+- governance/rule_lifecycle.yaml
+
@@ -0,0 +1,22 @@
+# ADR-0005 Formula domain split
+
+## Context
+The monolithic formula registry needs domain separation.
+
+## Decision
+Split formulas by domain and build a normalized registry.
+
+## Alternatives
+- Keep a single registry file
+
+## Consequences
+- Review scope is reduced
+- Formula ownership is easier to track
+
+## Rollback
+Rebuild normalized registry from the monolith.
+
+## Affected files
+- spec/formulas/*
+- spec/03_formulas/formula_registry.normalized.yaml
+
@@ -0,0 +1,24 @@
+# ADR-0006 Final decision packet
+
+## Context
+The renderer needs a single canonical packet.
+
+## Decision
+Use a versioned final decision packet as the only render input.
+
+See `spec/07_output_schema.yaml` and `tools/validate_report_packet_sync_v1.py` for the canonical packet/render contract.
+
+## Alternatives
+- Read many Temp files directly
+
+## Consequences
+- Provenance checks become centralized
+
+## Rollback
+Keep the previous packet version available.
+
+## Affected files
+- Temp/final_decision_packet_v3.json
+- Temp/final_decision_packet_active.json
+- spec/07_output_schema.yaml
+- tools/validate_report_packet_sync_v1.py
@@ -0,0 +1,20 @@
+# ADR-0007 Shadow ledger
+
+## Context
+Blocked items still need visible computed values.
+
+## Decision
+Separate executable order table from shadow ledger.
+
+## Alternatives
+- Hide blocked numbers
+
+## Consequences
+- User review is preserved
+
+## Rollback
+Show the prior packet alongside the new ledger if needed.
+
+## Affected files
+- spec/outputs/shadow_ledger_contract.yaml
+
@@ -0,0 +1,20 @@
+# ADR-0008 Renderer contract
+
+## Context
+Low-capability LLM rendering needs a closed contract.
+
+## Decision
+Fix the input packet, section order, and numeric copy rules.
+
+## Alternatives
+- Free-form narrative generation
+
+## Consequences
+- Lower hallucination risk
+
+## Rollback
+Use the prior prompt only if schema validation fails.
+
+## Affected files
+- prompts/low_capability_report_renderer.md
+
@@ -0,0 +1,20 @@
+# ADR-0009 Number provenance audit
+
+## Context
+Every investment number must be traceable.
+
+## Decision
+Require source_ref and formula_id for investment numbers.
+
+## Alternatives
+- Allow implicit report numbers
+
+## Consequences
+- Ungrounded numbers are detectable
+
+## Rollback
+Rebuild the report from a provenance-backed packet.
+
+## Affected files
+- tools/validate_number_provenance_v2.py
+
@@ -0,0 +1,20 @@
+# ADR-0010 Change request template
+
+## Context
+Rule and formula changes need structured evidence.
+
+## Decision
+Use a mandatory change-request template for active changes.
+
+## Alternatives
+- Free-form change notes
+
+## Consequences
+- Rollback and testing become explicit
+
+## Rollback
+Reject changes that lack the required fields.
+
+## Affected files
+- governance/change_request_template.yaml
+
@@ -0,0 +1,19 @@
+# ADR-0011: QEDD 방법론 채택
+
+## 상태
+준비됨 (Proposed)
+
+## 배경
+퀀트 엔진의 복잡도가 증가함에 따라, 저성능 LLM에서도 동일한 투자 결론을 재현하고 운영 안정성을 확보하기 위한 결정론적 개발 방법론이 필요함.
+
+## 결정
+QEDD(Quant Evidence-Driven Deterministic Development) 방법론을 채택함.
+1. 모든 판단 로직은 YAML 계약(spec)에 근거함.
+2. 모든 수치 계산은 Python Canonical 엔진에서만 수행함.
+3. GAS는 데이터 수집 및 입출력 어댑터 역할로 축소함.
+4. LLM은 이미 계산된 패킷을 복사하여 렌더링하는 역할만 수행함 (Math 금지).
+
+## 결과
+- 운영 보고서의 숫자 신뢰도 100% 확보.
+- 저성능 모델에서도 판단 번복 없는 안정적인 운영 가능.
+- 아키텍처 경계 위반 자동 차단.
@@ -0,0 +1,44 @@
+schema_version: adr_index.v1
+adr_count: 10
+entries:
+  - adr_id: ADR-0001
+    title: Adopt active artifact manifest
+    status: accepted
+    path: governance/adr/0001-adopt-active-artifact-manifest.md
+  - adr_id: ADR-0002
+    title: Adopt authority matrix
+    status: accepted
+    path: governance/adr/0002-authority-matrix.md
+  - adr_id: ADR-0003
+    title: Freeze baseline metrics
+    status: accepted
+    path: governance/adr/0003-baseline-metrics.md
+  - adr_id: ADR-0004
+    title: Introduce rule lifecycle policy
+    status: accepted
+    path: governance/adr/0004-rule-lifecycle.md
+  - adr_id: ADR-0005
+    title: Split formula registry by domain
+    status: accepted
+    path: governance/adr/0005-formula-domain-split.md
+  - adr_id: ADR-0006
+    title: Make final decision packet canonical
+    status: accepted
+    path: governance/adr/0006-final-decision-packet.md
+  - adr_id: ADR-0007
+    title: Mandatory shadow ledger
+    status: accepted
+    path: governance/adr/0007-shadow-ledger.md
+  - adr_id: ADR-0008
+    title: Low capability renderer contract
+    status: accepted
+    path: governance/adr/0008-renderer-contract.md
+  - adr_id: ADR-0009
+    title: Number provenance audit
+    status: accepted
+    path: governance/adr/0009-number-provenance.md
+  - adr_id: ADR-0010
+    title: Change request template
+    status: accepted
+    path: governance/adr/0010-change-request-template.md
+
@@ -0,0 +1,12 @@
+schema_version: agents_index.v1
+source: AGENTS.md
+purpose: Compact index for operator rules migrated out of AGENTS.md.
+rule_files:
+  - governance/rules/00_core_locks.yaml
+  - governance/rules/01_harness_contract.yaml
+  - governance/rules/02_portfolio_policy.yaml
+  - governance/rules/03_order_grammar.yaml
+  - governance/rules/04_reporting_contract.yaml
+  - governance/rules/05_migration_hashes.yaml
+hash_manifest: governance/agents_rule_hashes.yaml
+hash_algorithm: sha256
@@ -0,0 +1,18 @@
+schema_version: agents_rule_hashes.v1
+hash_algorithm: sha256
+generated_from: governance/agents_index.yaml
+files:
+- path: governance/rules/00_core_locks.yaml
+  sha256: b3c3d7ce05beb9e8b0945d98a0a1a55276254acef246c13f8c3a110f14f57ff4
+- path: governance/rules/01_harness_contract.yaml
+  sha256: a093ddafa4a1b624ee44e4a98a63ce196ad452572fb27418c7e82b9b5edafc5a
+- path: governance/rules/02_portfolio_policy.yaml
+  sha256: 47f6f33602482213523e6fdfa191309a34b805fc7acbe4aa84f475ece899a8ad
+- path: governance/rules/03_order_grammar.yaml
+  sha256: cbcde916be0929cb1ba7fdbe9922c4445e375ea5d39654d96b86e1e80313cca9
+- path: governance/rules/04_reporting_contract.yaml
+  sha256: 6ec102fcd3f8c50325ca793b8709200ec688526673405f594e5a03c137300f7b
+- path: governance/rules/05_migration_hashes.yaml
+  sha256: fed17361105a22161e974b9503a5908c8d332f66b19503a6d6a4d12ceabaef75
+- path: AGENTS.md
+  sha256: 8d7748597bb248c46db6089cd09da8d4af3f7eadc55243f8afaf4aebaea82fcf
@@ -0,0 +1,10 @@
+formula_id: FORMULA_AUTHORITY_MATRIX_V1
+generated_at: '2026-06-06T00:00:00+09:00'
+owned_output_field_pct: 100.0
+authority_collision_count: 0
+manual_override_field_count: 0
+source:
+  formula_owner_coverage: Temp/formula_owner_coverage_v1.json
+  output_field_collision: Temp/output_field_owner_collision_v1.json
+  output_field_ledger: spec/03_formulas/output_field_owner_ledger.yaml
+  field_dictionary: spec/12_field_dictionary.yaml
@@ -0,0 +1,18 @@
+change_request_template_version: v1.0
+proposal_metadata:
+  proposal_id: "CR-YYYYMMDD-NAME"
+  author: "quant_architect"
+  created_at: "YYYY-MM-DD"
+rationale:
+  why: "State the reason for this change request"
+  expected_edge: "Describe the expected analytical edge or performance lift"
+  risk: "Outline potential failure modes and risk exposure changes"
+dependencies:
+  data_dependency: "List of workbook columns or API data sources required"
+verification:
+  tests:
+    - "List unit/regression tests or golden cases that validate this change"
+  rollback_plan: "Actionable rollback steps if the change fails verification"
+outcome_metrics:
+  expected_t5_pass_rate_pct: 60.0
+  expected_expectancy: 0.10
@@ -0,0 +1,18 @@
+change_request_template_version: v1.0
+proposal_metadata:
+  proposal_id: "CR-0001"
+  author: "quant_architect"
+  created_at: "2026-06-03"
+rationale:
+  why: "Example change request placeholder"
+  expected_edge: "improved provenance visibility"
+  risk: "none"
+dependencies:
+  data_dependency: "existing methodology todo"
+verification:
+  tests:
+    - "validate_final_decision_packet"
+  rollback_plan: "revert packet builder"
+outcome_metrics:
+  expected_t5_pass_rate_pct: 60.0
+  expected_expectancy: 0.10
@@ -0,0 +1,18 @@
+change_request_template_version: v1.0
+proposal_metadata:
+  proposal_id: "CR-20260607-SAMPLE"
+  author: "quant_architect"
+  created_at: "2026-06-07"
+rationale:
+  why: "Integrate property and metamorphic invariants"
+  expected_edge: "Stable execution decisions"
+  risk: "Increase computation time slightly"
+dependencies:
+  data_dependency: "spec/property_invariants.yaml"
+verification:
+  tests:
+    - "validate_property_invariants"
+  rollback_plan: "Remove validate_property_invariants from DAG"
+outcome_metrics:
+  expected_t5_pass_rate_pct: 65.0
+  expected_expectancy: 0.12
@@ -0,0 +1,205 @@
+schema_version: gas_logic_migration_ledger.v1
+source: governance/gas_logic_migration_ledger_v1.yaml
+authored: 2026-06-10
+total_findings: 15
+classification_summary:
+  decision_logic: 4
+  score_logic: 5
+  price_qty_logic: 4
+  pure_mapping: 1
+  display_text: 1
+unclassified_findings: 0
+
+# Canonical classification of GAS thin-adapter findings identified by
+# validate_gas_thin_adapter_v1.py. Each finding is classified by what type
+# of logic it contains and paired with a migration_action.
+findings:
+  - id: F01
+    file: src/gas_adapter_parts/gdf_01_price_metrics.gs
+    line: 186
+    text: "SP_TAKE_PROFIT:        10,  // Profit_Pct >= 10% (익절 후보)"
+    classification: score_logic
+    migration_action: REGISTER_SP_TAKE_PROFIT
+    target_file: formulas/score_thresholds_v1.py
+    status: TODO
+
+  - id: F02
+    file: src/gas_adapter_parts/gdf_01_price_metrics.gs
+    line: 656
+    text: "priceBasis = Number.isFinite(tp2Price) ? \"TAKE_PROFIT_TIER2_PRICE\" : \"PRIOR_CLOSE_X_0.998\";"
+    classification: price_qty_logic
+    migration_action: MIGRATE_PRICEBASIS_TO_PYTHON
+    target_file: formulas/price_basis_v1.py
+    status: TODO
+    blocking_on: F03 F04 (same function, migrate together)
+
+  - id: F03
+    file: src/gas_adapter_parts/gdf_01_price_metrics.gs
+    line: 665
+    text: "priceBasis = Number.isFinite(tp2Price) ? \"TAKE_PROFIT_TIER2_PRICE\" : \"PRIOR_CLOSE_X_0.998\";"
+    classification: price_qty_logic
+    migration_action: MIGRATE_PRICEBASIS_TO_PYTHON
+    target_file: formulas/price_basis_v1.py
+    status: TODO
+    blocking_on: F02 F04
+
+  - id: F04
+    file: src/gas_adapter_parts/gdf_01_price_metrics.gs
+    line: 674
+    text: "priceBasis = Number.isFinite(tp1Price) ? \"TAKE_PROFIT_TIER1_PRICE\" : \"PRIOR_CLOSE_X_0.998\";"
+    classification: price_qty_logic
+    migration_action: MIGRATE_PRICEBASIS_TO_PYTHON
+    target_file: formulas/price_basis_v1.py
+    status: TODO
+
+  - id: F05
+    file: src/gas_adapter_parts/gdf_01_price_metrics.gs
+    line: 678
+    text: "action = \"TAKE_PROFIT_TIER1\";"
+    classification: decision_logic
+    migration_action: MIGRATE_DECISIONS_ROUTING
+    target_file: formulas/execution_decision_v1.py
+    status: TODO
+
+  - id: F06
+    file: src/gas_adapter_parts/gdf_01_price_metrics.gs
+    line: 683
+    text: "priceBasis = Number.isFinite(tp1Price) ? \"TAKE_PROFIT_TIER1_PRICE\" : \"PRIOR_CLOSE_X_0.998\";"
+    classification: price_qty_logic
+    migration_action: MIGRATE_PRICEBASIS_TO_PYTHON
+    target_file: formulas/price_basis_v1.py
+    status: TODO
+
+  - id: F07
+    file: src/gas_adapter_parts/gdf_01_price_metrics.gs
+    line: 1577
+    text: "score += THRESHOLDS[\"SP_TAKE_PROFIT\"];"
+    classification: score_logic
+    migration_action: MIGRATE_SCORE_CALCULATION
+    target_file: formulas/score_thresholds_v1.py
+    status: TODO
+
+  - id: F08
+    file: src/gas_adapter_parts/gdf_01_price_metrics.gs
+    line: 1578
+    text: "breakdown.push(`take_profit:+${THRESHOLDS[\"SP_TAKE_PROFIT\"]}`)"
+    classification: display_text
+    migration_action: DISPLAY_TEXT_PASSTHROUGH
+    notes: display_text stays in GAS adapter as rendering concern
+    status: KEEP_IN_GAS
+
+  - id: F09
+    file: src/gas_adapter_parts/gdf_01_price_metrics.gs
+    line: 2164
+    text: "TAKE_PROFIT_BASE:    10,"
+    classification: score_logic
+    migration_action: REGISTER_TAKE_PROFIT_BASE
+    target_file: formulas/score_thresholds_v1.py
+    status: TODO
+
+  - id: F10
+    file: src/gas_adapter_parts/gdf_03_portfolio_gates.gs
+    line: 1335
+    text: "return { [\"decisions\"]: routes, traces: traces, lock: true };"
+    classification: decision_logic
+    migration_action: MIGRATE_DECISIONS_ROUTING
+    target_file: formulas/routing_decision_v1.py
+    status: TODO
+
+  - id: F11
+    file: src/gas_adapter_parts/gdf_03_portfolio_gates.gs
+    line: 1360
+    text: "if (holding && holding.stopBreach) return 'STOP_LOSS';"
+    classification: decision_logic
+    migration_action: MIGRATE_STOP_BREACH_DECISION
+    target_file: formulas/stop_loss_gate_v1.py
+    status: TODO
+
+  - id: F12
+    file: src/gas_adapter_parts/gdf_03_portfolio_gates.gs
+    line: 2128
+    text: "[\"distribution_risk_score\"]: Math.min(100, Math.max(0, score)),"
+    classification: score_logic
+    migration_action: DELETE_DISTRIBUTION_RISK_GAS
+    target_file: formulas/distribution_risk_v1.py
+    status: TODO
+    notes: Python canonical (build_distribution_risk_v1.py) already exists; GAS version is duplicate
+
+  - id: F13
+    file: src/gas_adapter_parts/gdf_03_portfolio_gates.gs
+    line: 2132
+    text: "formula_id: 'DISTRIBUTION_RISK_SCORE_V1'"
+    classification: pure_mapping
+    migration_action: DELETE_DISTRIBUTION_RISK_GAS
+    status: TODO
+    notes: formula_id tag stays with Python canonical; remove from GAS
+
+  - id: F14
+    file: src/gas_adapter_parts/gdf_03_portfolio_gates.gs
+    line: 2214
+    text: "[\"late_chase_risk_score\"]: Math.min(100, Math.max(0, Math.round(lateChaseRisk))),"
+    classification: score_logic
+    migration_action: DELETE_LATE_CHASE_RISK_GAS
+    target_file: formulas/late_chase_risk_v1.py
+    status: TODO
+    notes: Python canonical (build_alpha_lead_table_v1.py) computes late_chase_risk; GAS version is duplicate
+
+  - id: F15
+    file: src/gas_adapter_parts/gdf_04_execution_quality.gs
+    line: 479
+    text: "if (bqRow.breakout_quality_gate === 'BLOCKED_LATE_CHASE' || alphaRow[\"late_chase_risk_score\"] >= 70)"
+    classification: decision_logic
+    migration_action: MIGRATE_LATE_CHASE_GATE
+    target_file: formulas/late_chase_gate_v1.py
+    status: TODO
+
+# Migration action summary (9 actions)
+migration_actions:
+  - action_id: REGISTER_SP_TAKE_PROFIT
+    findings: [F01]
+    description: Register SP_TAKE_PROFIT threshold (value=10) in Python score_thresholds canonical
+    priority: LOW
+
+  - action_id: REGISTER_TAKE_PROFIT_BASE
+    findings: [F09]
+    description: Register TAKE_PROFIT_BASE threshold (value=10) in Python score_thresholds canonical
+    priority: LOW
+
+  - action_id: DELETE_DISTRIBUTION_RISK_GAS
+    findings: [F12, F13]
+    description: Remove distribution_risk_score calculation from gdf_03; Python canonical exists
+    priority: HIGH
+    blocker: verify build_distribution_risk_v1.py output matches GAS output before delete
+
+  - action_id: DELETE_LATE_CHASE_RISK_GAS
+    findings: [F14]
+    description: Remove late_chase_risk_score from gdf_03; Python canonical in alpha_lead_table_v1
+    priority: HIGH
+    blocker: verify parity before delete
+
+  - action_id: MIGRATE_PRICEBASIS_TO_PYTHON
+    findings: [F02, F03, F04, F06]
+    description: priceBasis string selection (TIER1/TIER2 or PRIOR_CLOSE_X_0.998) → Python canonical
+    priority: MEDIUM
+
+  - action_id: MIGRATE_SCORE_CALCULATION
+    findings: [F07]
+    description: score += THRESHOLDS["SP_TAKE_PROFIT"] pattern → Python canonical scorer
+    priority: MEDIUM
+
+  - action_id: MIGRATE_STOP_BREACH_DECISION
+    findings: [F11]
+    description: holding.stopBreach → STOP_LOSS decision → Python canonical stop_loss_gate
+    priority: HIGH
+    notes: critical path — must match validate_stop_loss_policy_v1 spec
+
+  - action_id: MIGRATE_DECISIONS_ROUTING
+    findings: [F05, F10]
+    description: TAKE_PROFIT_TIER1 action assignment and routing lock decision → Python canonical
+    priority: MEDIUM
+
+  - action_id: MIGRATE_LATE_CHASE_GATE
+    findings: [F15]
+    description: BLOCKED_LATE_CHASE gate check (threshold 70) → Python canonical gate formula
+    priority: HIGH
+    blocker: late_chase_risk_score must come from Python before GAS gate can be removed
@@ -0,0 +1,8 @@
+schema_version: rule_lifecycle.v1
+states:
+  - shadow
+  - evidence
+  - active
+  - retire
+transition_policy:
+  require_change_request: true
@@ -0,0 +1,9 @@
+schema_version: agents_rule.v1
+rule_id: CORE_LOCKS_V1
+title: Core locks and no-hallucination rules
+summary:
+  - Use spec/13_formula_registry.yaml for all prices, stops, targets, quantities.
+  - Do not invent prices, quantities, or formulas.
+  - If harness data is missing, print DATA_MISSING — 하네스 업데이트 필요.
+  - Preserve transparency for blocked items; never hide computed fields.
+  - Use only registered formulas and source-of-truth artifacts.
@@ -0,0 +1,8 @@
+schema_version: agents_rule.v1
+rule_id: HARNESS_CONTRACT_V1
+title: Harness and validation contract
+summary:
+  - Harness output must be validated before it is trusted.
+  - LLM must not override harness verdicts.
+  - Source-of-truth precedence follows runtime manifest and schema contracts.
+  - Live T+20 readiness cannot be faked from replay data.
@@ -0,0 +1,8 @@
+schema_version: agents_rule.v1
+rule_id: PORTFOLIO_POLICY_V1
+title: Portfolio policy contract
+summary:
+  - Heat, cash floor, stop loss, TP, and sell priority come from specs only.
+  - Do not bypass hard stops with narrative justification.
+  - For multiple sell candidates, show sell priority table first.
+  - Keep blocked positions transparent in shadow ledger outputs.
@@ -0,0 +1,8 @@
+schema_version: agents_rule.v1
+rule_id: ORDER_GRAMMAR_V1
+title: HTS order grammar
+summary:
+  - Single numeric price per order row.
+  - No multi-condition conjunctions in order text.
+  - Normalize all prices to KRX tick units.
+  - Remove stale TP prices when TP1 already triggered.
@@ -0,0 +1,8 @@
+schema_version: agents_rule.v1
+rule_id: REPORTING_CONTRACT_V1
+title: Reporting and provenance contract
+summary:
+  - All rendered numbers require provenance tags.
+  - Reports must keep source and runtime artifact references explicit.
+  - Narrative must not soften or override numeric gates.
+  - Output schema and final packets are authoritative.
@@ -0,0 +1,8 @@
+schema_version: agents_rule.v1
+rule_id: RULE_HASH_MIGRATION_V1
+title: Rule hash migration map
+summary:
+  - AGENTS.md is the index only.
+  - Rule files carry the detailed instructions.
+  - Hash each rule file and track the set in governance/agents_index.yaml.
+  - Update hashes whenever rule files change.
@@ -0,0 +1,10 @@
+# Weekly Engine Review
+
+## Engine Health
+## Data Quality
+## Formula Parity
+## Outcome Drift
+## Active Rule Changes
+## Emergency Patch Notes
+## Normal Patch Notes
+