aether-quant 0.7.0__tar.gz → 0.8.0__tar.gz

{aether_quant-0.7.0 → aether_quant-0.8.0}/Dockerfile.retraining_worker

@@ -7,6 +7,7 @@ COPY experience/ ./experience/
 COPY performance/ ./performance/
 COPY regime/ ./regime/
 COPY experts/ ./experts/
+COPY features/ ./features/
 COPY topology/ ./topology/
 COPY moe/ ./moe/
 COPY inference/ ./inference/

{aether_quant-0.7.0 → aether_quant-0.8.0}/PKG-INFO

@@ -1,5 +1,5 @@
 Metadata-Version: 2.4
 Name: aether-quant
-Version: 0.7.0
+Version: 0.8.0
 Summary: Aether Quant convenience CLI
 Requires-Python: >=3.10

{aether_quant-0.7.0 → aether_quant-0.8.0}/README.md

@@ -10,7 +10,7 @@
 
 <p align="center">
   <img src="https://img.shields.io/badge/python-3.10%2B-FF8C00?style=flat-square&labelColor=1A1A1A&logo=python&logoColor=white" alt="Python 3.10+">
-  <!-- AQ:TEST_BADGE_START --><img src="https://img.shields.io/badge/tests-642%2F642%20passing-brightgreen?style=flat-square&labelColor=1A1A1A" alt="642 of 642 tests passing"><!-- AQ:TEST_BADGE_END -->
+  <!-- AQ:TEST_BADGE_START --><img src="https://img.shields.io/badge/tests-934%2F945%20passing-red?style=flat-square&labelColor=1A1A1A" alt="934 of 945 tests passing"><!-- AQ:TEST_BADGE_END -->
   <img src="https://img.shields.io/pypi/v/aether-quant?style=flat-square&labelColor=1A1A1A&color=FF8C00" alt="PyPI version">
   <img src="https://img.shields.io/badge/docker-ghcr.io%2Faether--quant-2496ED?style=flat-square&labelColor=1A1A1A&logo=docker&logoColor=white" alt="Docker image on GHCR">
 </p>
@@ -32,14 +32,16 @@ Mixture-of-Experts ensemble (bullish/bearish/sideways/volatility specialists)
 routed by a learned gating network, a market-regime detector, a 3D market
 topology layer that combines a deterministic correlation embedding with a
 learned probabilistic overlay, a liquidity/market-impact engine that adjusts
-position sizing to real trading conditions, and a controlled retraining loop
-that lets the model itself evolve as markets do — all wired together and
-validated end-to-end inside QuantConnect's Lean engine. The thesis this
-project exists to test is simple to state and hard to prove: **markets are
-non-stationary, so a trading model should be too.** Every subsystem here
-exists to make the model adapt — to regime shifts, to changing correlation
-structure, to liquidity conditions — rather than to fit one historical
-window and hope it generalizes.
+position sizing to real trading conditions, a cross-sectional ranking signal
+that sizes each position by its predicted relative strength against the rest
+of the trading universe, and a controlled retraining loop that lets the
+model itself evolve as markets do — all wired together and validated
+end-to-end inside QuantConnect's Lean engine. The thesis this project exists
+to test is simple to state and hard to prove: **markets are non-stationary,
+so a trading model should be too.** Every subsystem here exists to make the
+model adapt — to regime shifts, to changing correlation structure, to
+liquidity conditions — rather than to fit one historical window and hope it
+generalizes.
 
 ## Table of Contents
 
@@ -158,7 +160,7 @@ that a controlled retraining loop reads from to evolve the model over time.
 
 ```mermaid
 flowchart LR
-    A["Lean data folder<br/>stocks, ETFs, crypto"] --> B["Feature pipeline<br/>train.py<br/>48-dim: price/volume +<br/>regime + liquidity + topology"]
+    A["Lean data folder<br/>stocks, ETFs, bonds, crypto"] --> B["Feature pipeline<br/>train.py<br/>62-dim: price/volume + indicators +<br/>regime + liquidity + topology + peer returns + macro"]
     B --> C["Regime detection<br/>trend, volatility, drawdown, correlation"]
     B --> D["3D topology modeling<br/>market structure and clusters"]
     B -.-> U["Sequence encoder (Phase 2)<br/>causal-TCN, 30-bar window<br/>informational only"]
@@ -250,6 +252,52 @@ topology correlation/risk state are all computed offline
 (`main.py::_build_model_input()`, reordered so regime is computed
 *before* the model runs) with verified train/runtime parity.
 
+**Multi-horizon direction, cross-sectional ranking, correlated-peer
+returns and technical indicators (model input 48 → 59).** A root-cause
+investigation found every model — baseline, all 4 experts, the multitask
+heads, the sequence encoder — sitting at backtest MCC 0.02-0.07 (noise) on
+next-day binary direction, and traced (and fixed) real data bugs
+confounding those numbers: an unadjusted-split bug in `train.py`'s own
+Lean-zip reader (Lean's live/backtest engine was never affected — see
+`development/Problems.md` #24) and a data-feed volume-unit discontinuity
+that blew up the sequence model's RMSE 31x (#23). Beyond the fixes,
+`AetherNetMultiTaskHorizons`/`AetherNetSequenceMultiTaskHorizons` (new
+sibling classes to the originals — experts/baseline/gating stay
+1d-direction-only by design) add 4 heads: `direction_5d`/`direction_20d`
+(longer-horizon direction) and `rank_5d`/`rank_20d` (per-date
+cross-sectional percentile rank of forward return — the most learnable
+target this investigation found, maps directly onto a long/short
+portfolio, evaluated via rank-IC, `train.py::compute_rank_ic()`, not MCC).
+11 new scaled input features: 4 correlated-peer lagged-return features
+(`topology/market_topology.py`'s `top_peers`/`top_peer_returns`, a genuine
+new information channel from correlation data the model previously only
+saw as a compressed scalar) and 7 technical indicators (`features/`
+package — RSI, ATR%, Bollinger %B, volume z-score, MACD histogram,
+distance-from-52-week-high, cross-sectional momentum rank), all computed
+identically offline and at runtime by construction (shared pure
+functions, not hand-matched duplicated formulas). All new signals are
+visible on `/neural-network` and in `*_training_metrics.json`; see
+`development/Changelog.md`'s "Frontier-model edge investigation" entry
+for the full build and the real rank-IC results.
+
+**`rank_20d` now sizes positions (opt-in).** A follow-up pass wired the
+one Phase-4 signal with a statistically significant full-series result —
+`rank_20d`, sequence model mean IC `0.073`/t-stat `4.40` — into an actual
+trading decision: `risk/position_sizing.py::rank_sizing_multiplier()`
+adds a fourth, bounded, direction-preserving factor to the sizing chain,
+scaling an already-approved trade UP toward `max_rank_multiplier` (default
+`1.25`) when the model predicts this asset near the top of the universe's
+20-day forward-return ranking, and DOWN toward `min_rank_multiplier`
+(default `0.75`) near the bottom — never flipping direction, same
+convention as the existing `topology_sizing_multiplier()`. **Off by
+default** (`phase_v2.dynamic_risk.rank_sizing_enabled: false`): the
+signal's non-overlapping-date subsample (28 independent 20-day windows)
+was not yet independently significant on its own (t-stat `1.20`), so it
+ships wired end-to-end but not promoted to on-by-default until validated
+on more out-of-sample data. `direction_5d`/`direction_20d`/`rank_5d`
+remain informational-only. See `risk/README.md`'s "Cross-sectional
+rank_20d → position sizing" section.
+
 **A causal-TCN sequence encoder (Phase 2) now exists alongside the
 flat-MLP trunk**, replacing the "zero temporal structure" limitation the
 original root-cause investigation flagged — `train.py::AetherNetSequenceMultiTask`,
@@ -269,10 +317,21 @@ writeup.
 
 ## Universe Size
 
-The trading universe currently spans **20 assets** — 15 equities and 5
-crypto pairs — defined in `config.json`'s `phase1.universe.assets` and
-shared across training, validation, and backtesting
-(`phase1.universe.common_window`: `2014-12-01` to `2021-03-31`).
+The trading universe currently spans **30 assets** — 15 stocks/broad-market
+ETFs, 10 fixed-income (bond) ETFs, and 5 crypto pairs — defined in
+`config.json`'s `phase1.universe.assets` and shared across training,
+validation, and backtesting (`phase1.universe.common_window`: `2014-12-01`
+to `2021-03-31`). The bond ETF sleeve (Phase 1 of the 5/10 -> 9/10 roadmap,
+see [`development/Changelog.md`](development/Changelog.md)) was added
+specifically as a new, genuinely different information channel — not more
+of the same equity cross-section — and deliberately spans the duration
+curve (short/intermediate/long/aggregate) and credit spectrum
+(Treasury/investment-grade/high-yield/municipal/emerging-market) so the
+yield-curve-slope and credit-spread macro proxies computed from it
+(`features/macro_features.py`) are meaningful. Bond ETFs are registered
+with `security_type: "equity"` (they trade through Lean's ordinary equity
+subscription path, like every other ETF already in the universe, e.g.
+SPY/QQQ/IWM/EEM — not a new Lean security type).
 
 | Ticker | Type | Role |
 |---|---|---|
@@ -291,6 +350,16 @@ shared across training, validation, and backtesting
 | USO | Equity | Trading |
 | WM | Equity | Trading |
 | AAA | Equity | Observation-only (thin history) |
+| SHY | Equity (Fixed Income ETF) | Trading — short-duration Treasury (1-3y) |
+| IEF | Equity (Fixed Income ETF) | Trading — intermediate-duration Treasury (7-10y) |
+| TLT | Equity (Fixed Income ETF) | Trading — long-duration Treasury (20y+) |
+| AGG | Equity (Fixed Income ETF) | Trading — broad aggregate bond benchmark |
+| LQD | Equity (Fixed Income ETF) | Trading — investment-grade corporate |
+| HYG | Equity (Fixed Income ETF) | Trading — high-yield corporate |
+| TIP | Equity (Fixed Income ETF) | Trading — inflation-protected (TIPS) |
+| MBB | Equity (Fixed Income ETF) | Trading — mortgage-backed |
+| EMB | Equity (Fixed Income ETF) | Trading — emerging-market sovereign debt |
+| MUB | Equity (Fixed Income ETF) | Trading — municipal |
 | BTCUSD | Crypto | Trading |
 | ETHUSD | Crypto | Observation-only (thin history) |
 | LTCUSD | Crypto | Trading |
@@ -328,6 +397,19 @@ flowchart TD
         AAA["AAA"]
     end
 
+    subgraph FixedIncome["Fixed Income ETFs (10)"]
+        SHY["SHY"]
+        IEF["IEF"]
+        TLT["TLT"]
+        AGG["AGG"]
+        LQD["LQD"]
+        HYG["HYG"]
+        TIP["TIP"]
+        MBB["MBB"]
+        EMB["EMB"]
+        MUB["MUB"]
+    end
+
     subgraph Crypto["Crypto (5)"]
         BTCUSD["BTCUSD"]
         ETHUSD["ETHUSD"]
@@ -351,6 +433,16 @@ flowchart TD
     USO --- DNN
     WM --- DNN
     AAA --- DNN
+    SHY --- DNN
+    IEF --- DNN
+    TLT --- DNN
+    AGG --- DNN
+    LQD --- DNN
+    HYG --- DNN
+    TIP --- DNN
+    MBB --- DNN
+    EMB --- DNN
+    MUB --- DNN
     BTCUSD --- DNN
     ETHUSD --- DNN
     LTCUSD --- DNN
@@ -362,7 +454,7 @@ flowchart TD
     classDef observation fill:#3A3A3A,stroke:#FF8C00,color:#FF8C00,stroke-width:1px,stroke-dasharray: 4 2;
 
     class DNN hub;
-    class AAPL,SPY,QQQ,IWM,EEM,BAC,IBM,AIG,BNO,FB,GOOG,GOOGL,USO,WM,BTCUSD,LTCUSD trading;
+    class AAPL,SPY,QQQ,IWM,EEM,BAC,IBM,AIG,BNO,FB,GOOG,GOOGL,USO,WM,SHY,IEF,TLT,AGG,LQD,HYG,TIP,MBB,EMB,MUB,BTCUSD,LTCUSD trading;
     class AAA,ETHUSD,XRPUSD,ADAUSD observation;
 ```
 
@@ -393,7 +485,7 @@ aether-quant/
 ├── ml/                          # Model weights, datasets, versioned retraining candidates
 ├── storage/                     # Reserved for future persistent artifact storage
 ├── requirements/                # All requirements*.txt variants
-├── tests/                       # Full pytest suite (507 tests)
+├── tests/                       # Full pytest suite (828 tests)
 ├── backtests/                   # Lean backtest run outputs (gitignored)
 ├── Aether-quant-Obsidian-Vault/ # Auto-generated code-graph / architecture vault
 ├── main.py                      # Lean algorithm: inference, signal engine, risk controls
@@ -435,7 +527,7 @@ and how it's wired in — this table is the index.
 | `retraining/` | Controlled retraining — plan/train/validate/backtest/commit/promote/rollback | [README](retraining/README.md) |
 | `risk/` | Dynamic position sizing, leverage caps, drawdown-aware sizing | [README](risk/README.md) |
 | `storage/` | Reserved placeholder for future persistent artifact storage | [README](storage/README.md) |
-| `tests/` | Pytest suite conventions (507 tests) | [README](tests/README.md) |
+| `tests/` | Pytest suite conventions (828 tests) | [README](tests/README.md) |
 | `topology/` | 3D market topology — deterministic SMACOF embedding + learned overlay | [README](topology/README.md) |
 | `visualization/` | Shared runtime-state JSON/CSV exports | [README](visualization/README.md) |
 | `webui/` | React/Vite dashboard (Overview, Risk, Topology, Neural Network, Tracing) | [README](webui/README.md) |
@@ -543,7 +635,7 @@ genuinely halted trading exactly as designed.
 
 ## Test Suite
 
-507 tests, one file per source module, run via:
+828 tests, one file per source module, run via:
 
 ```powershell
 aq test
@@ -576,7 +668,7 @@ command already documented elsewhere in this README:
 
 #### `aq train`
 ```text
-aq train [--dataset-only|--init-only|--experts-only|--gating-only|--multitask-only|--sequence-only]
+aq train [--dataset-only|--init-only|--experts-only|--gating-only|--multitask-only|--sequence-only|--walk-forward] [--step-days N] [--mode rolling|expanding]
 ```
 Runs `train.py`: builds the dataset and trains the baseline + expert
 models. `--gating-only` trains just the learned gating blend
@@ -586,7 +678,15 @@ mirroring what `--experts-only` already does for the expert models — see
 direction+magnitude+volatility model (`train_multitask.py`) — see
 `inference/README.md`/`risk/README.md`. `--sequence-only` does the same
 for the Phase 2 causal-TCN sequence encoder (`train_sequence.py`) — see
-`inference/README.md`.
+`inference/README.md`. `--walk-forward` (Phase 4 of the 5/10 -> 9/10
+roadmap) wraps `python train.py --walk-forward`, running the dataset-build
++ training pipeline once per rolling/expanding window instead of once on
+the fixed `phase1.windows` — diagnostic only, never touches active `ml/`
+(each window writes to `ml/versions/<run-id>/window_<i>/`, same as
+`--candidate`); `--step-days`/`--mode` override
+`phase_v2.retraining.walk_forward`'s `step_days`/`mode` defaults — see
+`retraining/README.md`'s "Walk-forward retraining is a separate, scheduled
+mechanism" section.
 
 #### `aq test`
 ```text

{aether_quant-0.7.0 → aether_quant-0.8.0}/aether_quant.egg-info/PKG-INFO

@@ -1,5 +1,5 @@
 Metadata-Version: 2.4
 Name: aether-quant
-Version: 0.7.0
+Version: 0.8.0
 Summary: Aether Quant convenience CLI
 Requires-Python: >=3.10

{aether_quant-0.7.0 → aether_quant-0.8.0}/aether_quant.egg-info/SOURCES.txt

@@ -62,6 +62,7 @@ execution/order_gate.py
 execution/paper_readiness.py
 execution/paper_readiness_io.py
 execution/paper_readiness_report.py
+execution/paper_readiness_scheduler.py
 execution/runtime_config_io.py
 experience/README.md
 experience/__init__.py
@@ -72,6 +73,9 @@ experience/simulated_portfolio.py
 experts/README.md
 experts/__init__.py
 experts/expert_datasets.py
+features/__init__.py
+features/macro_features.py
+features/technical_indicators.py
 inference/README.md
 inference/__init__.py
 inference/exported_model.py
@@ -88,9 +92,15 @@ ml/multitask_training_metrics.json
 ml/sequence_feature_schema.json
 ml/sequence_model.json
 ml/sequence_training_metrics.json
+ml/versions/gating-only-05c572c8-9566-4152-805c-fa57142a3f8c/gating_feature_schema.json
+ml/versions/gating-only-05c572c8-9566-4152-805c-fa57142a3f8c/gating_model.json
+ml/versions/gating-only-05c572c8-9566-4152-805c-fa57142a3f8c/gating_training_metrics.json
 ml/versions/gating-only-26218402-34d9-4a0a-add8-ee5d50dd0459/gating_feature_schema.json
 ml/versions/gating-only-26218402-34d9-4a0a-add8-ee5d50dd0459/gating_model.json
 ml/versions/gating-only-26218402-34d9-4a0a-add8-ee5d50dd0459/gating_training_metrics.json
+ml/versions/multitask-only-f5708084-512b-4484-a47b-0720f9c1460c/multitask_feature_schema.json
+ml/versions/multitask-only-f5708084-512b-4484-a47b-0720f9c1460c/multitask_model.json
+ml/versions/multitask-only-f5708084-512b-4484-a47b-0720f9c1460c/multitask_training_metrics.json
 ml/versions/stage123-1783709428/gating_feature_schema.json
 ml/versions/stage123-1783709428/gating_model.json
 ml/versions/stage123-1783709428/gating_training_metrics.json
@@ -128,8 +138,12 @@ notifications/telegram_worker.py
 performance/README.md
 performance/__init__.py
 performance/postgres_triggers.py
+performance/rank_ic_monitor.py
 performance/trigger_worker.py
 performance/triggers.py
+portfolio/README.md
+portfolio/__init__.py
+portfolio/book_construction.py
 regime/README.md
 regime/__init__.py
 regime/market_regime.py
@@ -172,6 +186,7 @@ tests/test_lean_backtest_ml_coverage.py
 tests/test_learned_topology.py
 tests/test_live_credentials.py
 tests/test_live_credentials_io.py
+tests/test_macro_features.py
 tests/test_manual_override.py
 tests/test_market_analyzer.py
 tests/test_market_liquidity.py
@@ -183,10 +198,13 @@ tests/test_order_gate.py
 tests/test_paper_readiness.py
 tests/test_paper_readiness_io.py
 tests/test_paper_readiness_report.py
+tests/test_paper_readiness_scheduler.py
+tests/test_portfolio_book_construction.py
 tests/test_position_sizing.py
 tests/test_postgres_telegram.py
 tests/test_postgres_triggers.py
 tests/test_postgres_worker.py
+tests/test_rank_ic_monitor.py
 tests/test_retraining_artifacts.py
 tests/test_retraining_orchestrator.py
 tests/test_retraining_planning.py
@@ -196,16 +214,22 @@ tests/test_risk_controls.py
 tests/test_runtime_config_io.py
 tests/test_simulated_portfolio.py
 tests/test_status_export.py
+tests/test_technical_indicators.py
 tests/test_telegram_alerts.py
 tests/test_telegram_client.py
 tests/test_telegram_worker.py
 tests/test_train_cross_sectional_features.py
 tests/test_train_gating.py
+tests/test_train_indicators.py
+tests/test_train_macro_features.py
 tests/test_train_multitask.py
 tests/test_train_multitask_architecture.py
 tests/test_train_pipeline.py
+tests/test_train_ranking_validation.py
+tests/test_train_sequence.py
 tests/test_train_sequence_architecture.py
 tests/test_train_topology.py
+tests/test_train_walk_forward_windows.py
 tests/test_trigger_worker.py
 tests/test_triggers.py
 tests/test_v2_pipeline_manifest.py

{aether_quant-0.7.0 → aether_quant-0.8.0}/aether_quant.egg-info/scm_file_list.json

@@ -32,6 +32,9 @@
     "risk/__init__.py",
     "risk/manual_override.py",
     "risk/position_sizing.py",
+    "features/__init__.py",
+    "features/macro_features.py",
+    "features/technical_indicators.py",
     "notifications/telegram_client.py",
     "notifications/README.md",
     "notifications/__init__.py",
@@ -84,6 +87,7 @@
     "execution/live_credentials_io.py",
     "execution/paper_readiness_io.py",
     "execution/live_credentials.py",
+    "execution/paper_readiness_scheduler.py",
     "monitoring/neural_network_state.py",
     "monitoring/README.md",
     "monitoring/__init__.py",
@@ -92,7 +96,11 @@
     "performance/__init__.py",
     "performance/triggers.py",
     "performance/postgres_triggers.py",
+    "performance/rank_ic_monitor.py",
     "performance/trigger_worker.py",
+    "portfolio/README.md",
+    "portfolio/__init__.py",
+    "portfolio/book_construction.py",
     "liquidity/README.md",
     "liquidity/__init__.py",
     "liquidity/market_liquidity.py",
@@ -165,10 +173,12 @@
     "development/Changelog.md",
     "development/v2_architecture.md",
     "development/infrastructure.md",
+    "tests/test_train_sequence.py",
     "tests/test_order_gate.py",
     "tests/test_config_cache.py",
     "tests/test_train_sequence_architecture.py",
     "tests/test_telegram_alerts.py",
+    "tests/test_train_walk_forward_windows.py",
     "tests/test_trigger_worker.py",
     "tests/test_v2_pipeline_manifest.py",
     "tests/test_paper_readiness_report.py",
@@ -183,9 +193,11 @@
     "tests/test_expert_datasets.py",
     "tests/test_expert_models.py",
     "tests/test_live_credentials.py",
+    "tests/test_paper_readiness_scheduler.py",
     "tests/test_retraining_orchestrator.py",
     "tests/test_telegram_client.py",
     "tests/test_yfinance_backfill.py",
+    "tests/test_technical_indicators.py",
     "tests/test_neural_network_state.py",
     "tests/test_market_regime.py",
     "tests/test_vault_client.py",
@@ -193,10 +205,13 @@
     "tests/test_train_multitask.py",
     "tests/test_observation_metrics.py",
     "tests/test_paper_readiness_io.py",
+    "tests/test_train_ranking_validation.py",
+    "tests/test_portfolio_book_construction.py",
     "tests/test_exported_model.py",
     "tests/test_train_topology.py",
     "tests/test_telegram_worker.py",
     "tests/test_paper_readiness.py",
+    "tests/test_train_indicators.py",
     "tests/test_train_multitask_architecture.py",
     "tests/test_triggers.py",
     "tests/test_simulated_portfolio.py",
@@ -214,8 +229,11 @@
     "tests/test_manual_override.py",
     "tests/test_postgres_telegram.py",
     "tests/test_retraining_worker.py",
+    "tests/test_macro_features.py",
+    "tests/test_rank_ic_monitor.py",
     "tests/test_retraining_postgres_registry.py",
     "tests/test_learned_topology.py",
+    "tests/test_train_macro_features.py",
     "tests/test_gating_network.py",
     "tests/test_train_pipeline.py",
     "tests/test_experience_queue.py",
@@ -249,6 +267,9 @@
     "ml/versions/stage5-1783715333/sequence_feature_schema.json",
     "ml/versions/stage5-1783715333/sequence_model.json",
     "ml/versions/stage5-1783715333/sequence_training_metrics.json",
+    "ml/versions/multitask-only-f5708084-512b-4484-a47b-0720f9c1460c/multitask_feature_schema.json",
+    "ml/versions/multitask-only-f5708084-512b-4484-a47b-0720f9c1460c/multitask_model.json",
+    "ml/versions/multitask-only-f5708084-512b-4484-a47b-0720f9c1460c/multitask_training_metrics.json",
     "ml/versions/v1/sequence_feature_schema.json",
     "ml/versions/v1/multitask_feature_schema.json",
     "ml/versions/v1/multitask_model.json",
@@ -261,6 +282,9 @@
     "ml/versions/stage4-1783711025/multitask_training_metrics.json",
     "ml/versions/stage4-1783711025/gating_feature_schema.json",
     "ml/versions/stage4-1783711025/gating_training_metrics.json",
+    "ml/versions/gating-only-05c572c8-9566-4152-805c-fa57142a3f8c/gating_model.json",
+    "ml/versions/gating-only-05c572c8-9566-4152-805c-fa57142a3f8c/gating_feature_schema.json",
+    "ml/versions/gating-only-05c572c8-9566-4152-805c-fa57142a3f8c/gating_training_metrics.json",
     "ml/versions/gating-only-26218402-34d9-4a0a-add8-ee5d50dd0459/gating_model.json",
     "ml/versions/gating-only-26218402-34d9-4a0a-add8-ee5d50dd0459/gating_feature_schema.json",
     "ml/versions/gating-only-26218402-34d9-4a0a-add8-ee5d50dd0459/gating_training_metrics.json",

aether_quant-0.8.0/aether_quant.egg-info/scm_version.json

@@ -0,0 +1,8 @@
+{
+  "tag": "0.8.0",
+  "distance": 0,
+  "node": "g545067e0905efd61eb38f96d308e85744be233e7",
+  "dirty": false,
+  "branch": "HEAD",
+  "node_date": "2026-07-12"
+}

{aether_quant-0.7.0 → aether_quant-0.8.0}/analyzer/README.md

@@ -94,3 +94,23 @@ risk engine, and before action categorization / Lean order placement.
   enabled. Always `None` when no multitask model is loaded (or the model
   call failed), matching every other optional-model fallback contract in
   this codebase.
+  - **Follow-up:** these two fields now transitively reflect the Phase 2
+    sequence encoder too, whenever `phase_v2.gating_network.sequence_weight`
+    is enabled (`moe/README.md`'s "Phase 2 sequence encoder now optionally
+    blends into the gating decision" section) — `main.py` reads them from
+    `gating_payload["final_magnitude"/"final_volatility"]`, which the
+    sequence blend adjusts before this module ever sees them. No change
+    to this module was needed or made: it was evaluated as a candidate
+    direct-integration point for the sequence model and deliberately
+    passed over in favor of gating, for the same "stay fully
+    deterministic" reason the topology-elevated/isolated rules and the
+    composite signal score above already establish.
+  - **Follow-up (Phase 3 of the 5/10 -> 9/10 roadmap):** `signal_name` can
+    now also be `"short"` (`portfolio/book_construction.py`'s Stage-2
+    long/short book) — every safety-tier check in this module that used
+    to test `signal_name in {"buy", "sell"}` now tests
+    `{"buy", "sell", "short"}`, so a book-selected short passes through
+    the exact same deterministic trade-lock/risk-off/topology/liquidity
+    categorization as any other directional signal, never bypassing it.
+    See `portfolio/README.md` for why book construction lives in its own
+    package rather than here.

{aether_quant-0.7.0 → aether_quant-0.8.0}/analyzer/market_analyzer.py

@@ -93,6 +93,13 @@ def build_market_analysis_decision(
     predicted_return_magnitude: float | None = None,
     predicted_volatility: float | None = None,
 ) -> MarketAnalysisDecision:
+    # signal_name == "short" (Phase 3 of the 5/10 -> 9/10 roadmap,
+    # portfolio/book_construction.py) is treated identically to "buy"/"sell"
+    # by every safety-tier check below (`in {"buy", "sell", "short"}`) - a
+    # book-selected short position passes through the exact same
+    # deterministic trade-lock/risk-off/topology/liquidity categorization
+    # as any other directional signal, never bypassing it. See
+    # analyzer/README.md for why this categorization stays deterministic.
     reasons: list[str] = []
     decision_source = str(gating.get("decision_source", "unknown"))
     regime_confidence = float(regime.get("confidence", 0.0) or 0.0)
@@ -140,7 +147,7 @@ def build_market_analysis_decision(
 
     # Priority 2: reduce_risk - asset-level risk regime override even
     # without a portfolio-wide lock (e.g. risk_off + would-be trade).
-    if risk_regime == "risk_off" and signal_name in {"buy", "sell"}:
+    if risk_regime == "risk_off" and signal_name in {"buy", "sell", "short"}:
         reasons.append("risk_off_regime_overrides_directional_signal")
         return MarketAnalysisDecision(
             action="reduce_risk",
@@ -164,7 +171,7 @@ def build_market_analysis_decision(
     # feeding the retrain-trigger/retraining pipeline, but deliberately left
     # this rule reading only the deterministic topology_risk - see
     # analyzer/README.md and development/v2_architecture.md's V2-17.5 section.
-    if topology_risk == "elevated" and signal_name in {"buy", "sell"}:
+    if topology_risk == "elevated" and signal_name in {"buy", "sell", "short"}:
         reasons.append("topology_elevated_volatility_pressure_overrides_directional_signal")
         return MarketAnalysisDecision(
             action="reduce_risk",
@@ -208,7 +215,7 @@ def build_market_analysis_decision(
     # Priority 5: simulate - liquidity blocked (zero volume or DDV below
     # the floor). An unexecutable order must not reach the order book.
     # See V2-18 for future data-driven calibration of these thresholds.
-    if liquidity_action == "block" and signal_name in {"buy", "sell"}:
+    if liquidity_action == "block" and signal_name in {"buy", "sell", "short"}:
         reasons.append("liquidity_blocked_insufficient_volume_simulate_instead")
         return MarketAnalysisDecision(
             action="simulate",
@@ -228,7 +235,7 @@ def build_market_analysis_decision(
 
     # Priority 6: simulate - thin market; participation rate would be
     # uncomfortably large relative to daily volume.
-    if liquidity_action == "simulate_instead" and signal_name in {"buy", "sell"}:
+    if liquidity_action == "simulate_instead" and signal_name in {"buy", "sell", "short"}:
         reasons.append("liquidity_thin_market_simulate_instead")
         return MarketAnalysisDecision(
             action="simulate",
@@ -254,7 +261,7 @@ def build_market_analysis_decision(
     # use_composite_signal_score=True).
     if (
         trading_eligible
-        and signal_name in {"buy", "sell"}
+        and signal_name in {"buy", "sell", "short"}
         and trade_metric >= min_confidence_to_trade
         and topology_risk != "isolated"
         and liquidity_action not in {"block", "simulate_instead"}
@@ -277,7 +284,7 @@ def build_market_analysis_decision(
         )
 
     # Priority 8: simulate vs observe.
-    if signal_name in {"buy", "sell"} and regime_confidence >= low_regime_confidence_threshold:
+    if signal_name in {"buy", "sell", "short"} and regime_confidence >= low_regime_confidence_threshold:
         if topology_risk == "isolated":
             reasons.append("topology_isolated_asset_lacks_peer_confirmation_simulate_instead")
         elif trading_eligible:

{aether_quant-0.7.0 → aether_quant-0.8.0}/aq_cli.py

@@ -192,6 +192,12 @@ def cmd_train(args: argparse.Namespace) -> int:
         cmd.append("--init-only")
     elif args.experts_only:
         cmd.append("--experts-only")
+    elif args.walk_forward:
+        cmd.append("--walk-forward")
+        if args.step_days is not None:
+            cmd += ["--step-days", str(args.step_days)]
+        if args.mode is not None:
+            cmd += ["--mode", args.mode]
     return _run(cmd)
 
 
@@ -612,6 +618,25 @@ def build_parser() -> argparse.ArgumentParser:
         action="store_true",
         help="Train the Phase 2 causal-TCN sequence encoder only (wraps python train_sequence.py)",
     )
+    train_group.add_argument(
+        "--walk-forward",
+        action="store_true",
+        help=(
+            "Phase 4 of the 5/10 -> 9/10 roadmap: run the dataset-build + training pipeline once per "
+            "walk-forward window (wraps python train.py --walk-forward). Never touches active ml/ - "
+            "diagnostic only, writes to ml/versions/<run-id>/window_<i>/."
+        ),
+    )
+    train_parser.add_argument(
+        "--step-days", type=int, default=None, help="Walk-forward step size in days (only with --walk-forward)."
+    )
+    train_parser.add_argument(
+        "--mode",
+        type=str,
+        choices=("rolling", "expanding"),
+        default=None,
+        help="Walk-forward mode: rolling or expanding (only with --walk-forward).",
+    )
     train_parser.set_defaults(func=cmd_train)
 
     test_parser = subparsers.add_parser("test", help="Run the test suite (wraps pytest tests/)")