fix(ci): drop empty LOOP_MODEL env that blanked the model → LLM 400

`LOOP_MODEL: ${{ inputs.model }}` sets the env var to "" when no model input is
given. An env var set-but-empty is NOT unset, so it overrode loop.py's
berget/gemma4-31b default, and every agent call POSTed "model":"" → HTTP 400
Bad Request. The loop ran but optimized nothing (best == baseline, delta 0).

Real overrides already flow through the conditional `--model` arg, so this env
line was redundant as well as harmful. Remove it; loop.py's default applies.

.gitea/workflows/autoresearch.yml

@@ -0,0 +1,75 @@
+name: Autoresearch Loop
+
+on:
+  workflow_dispatch:
+    inputs:
+      fixture:
+        description: 'Fixture name in fixtures/ (without .json)'
+        required: true
+        default: 'phase-a-toy'
+      rq_id:
+        description: 'Run ID — defaults to fixture name if blank'
+        required: false
+        default: ''
+      iters:
+        description: 'Max iterations'
+        required: false
+        default: '3'
+      model:
+        description: 'LiteLLM model override (leave blank for default berget/gemma4-31b)'
+        required: false
+        default: ''
+
+jobs:
+  run:
+    name: Autoresearch — ${{ inputs.fixture }}
+    runs-on: self-hosted
+    timeout-minutes: 90
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Resolve run ID
+        id: vars
+        run: |
+          RQ_ID="${{ inputs.rq_id }}"
+          [ -z "$RQ_ID" ] && RQ_ID="${{ inputs.fixture }}"
+          echo "rq_id=$RQ_ID" >> "$GITHUB_OUTPUT"
+
+      - name: Clean stale run dir
+        run: rm -rf "runs/${{ steps.vars.outputs.rq_id }}"
+
+      - name: Set up Python venv
+        run: |
+          [ -d .venv ] || python3 -m venv .venv
+          # torch must come from the cu130 wheel index (koala Blackwell sm_120);
+          # requirements.txt deliberately excludes it. Install it first.
+          .venv/bin/pip install -q torch --index-url https://download.pytorch.org/whl/cu130
+          .venv/bin/pip install -q -r requirements.txt
+
+      - name: Scaffold run dir
+        run: |
+          .venv/bin/python scripts/autoresearch_start.py \
+            "fixtures/${{ inputs.fixture }}.json" \
+            "${{ steps.vars.outputs.rq_id }}"
+
+      - name: Run autoresearch loop
+        env:
+          LITELLM_KEY: ${{ secrets.LITELLM_KEY }}
+          LITELLM_BASE: ${{ secrets.LITELLM_BASE }}
+          NTFY_URL: ${{ secrets.NTFY_URL }}
+        run: |
+          ARGS="--run-dir runs/${{ steps.vars.outputs.rq_id }} --iters ${{ inputs.iters }}"
+          [ -n "${{ inputs.model }}" ] && ARGS="$ARGS --model ${{ inputs.model }}"
+          .venv/bin/python loop.py $ARGS
+
+      - name: Upload run artifacts
+        if: always()
+        uses: https://gitea.com/actions/upload-artifact@v3
+        with:
+          name: run-${{ steps.vars.outputs.rq_id }}-${{ github.run_number }}
+          path: |
+            runs/${{ steps.vars.outputs.rq_id }}/STATUS.md
+            runs/${{ steps.vars.outputs.rq_id }}/metrics.json
+            runs/${{ steps.vars.outputs.rq_id }}/program.md
+          retention-days: 30

.gitignore

@@ -34,3 +34,20 @@ bin/
 
 # downloaded + processed market data (track via DVC/MinIO, #10 — not git)
 data/
+
+# autoresearch run dirs (ephemeral; each scaffold rebuilds from fixtures/)
+runs/
+
+# ephemeral experiment outputs (generated by train.py / loop.py)
+metrics.json
+embeddings.json
+HEARTBEAT
+STATUS.md
+
+# python caches
+__pycache__/
+*.pyc
+.pytest_cache/
+
+# built Go binaries
+eval

fixtures/phase-a-toy.json

@@ -0,0 +1,11 @@
+{
+  "strategic_question": "What is the highest-leverage path to a JEPA-based FX tail-risk system that beats a GARCH/EWMA baseline on out-of-sample VaR-breach calibration, given one GPU and a solo researcher?",
+  "nodes": [
+    {
+      "id": "phase-a-toy",
+      "status": "autoresearch-ready",
+      "question": "Improve the OOS linear-probe R² (val_vol_r2) of the HEPA encoder on EUR/USD daily realized vol. The encoder is a small causal transformer trained with VICReg. Vary one hyperparameter or architectural choice per iteration — model size, learning rate, window, patch length, depth, VICReg loss weights — to push val_vol_r2 as high as possible on the 2022-2023 OOS slice.",
+      "candidate_metric": "val_vol_r2"
+    }
+  ]
+}

loop.py

@@ -84,6 +84,10 @@ def run_train() -> "tuple[float | None, float, str]":
     t0 = time.time()
     env = dict(os.environ)
     env["METRICS_OUT"] = str(METRICS_JSON.resolve())
+    # train.py is copied into the run dir, so sys.path[0] is that run dir — which
+    # has no scripts/. Put the project root (where loop.py + scripts/ live) on
+    # PYTHONPATH so train.py's `from scripts.var_breach import ...` resolves.
+    env["PYTHONPATH"] = str(Path(__file__).resolve().parent) + os.pathsep + env.get("PYTHONPATH", "")
     try:
         r = subprocess.run(
             [sys.executable, str(TRAIN_PY.resolve())],

metrics.json

@@ -1,14 +0,0 @@
-{
-  "val_vol_r2": 0.3641397896593044,
-  "phase1_r2": 0.3908407688140869,
-  "n_test": 11641,
-  "knobs": {
-    "WINDOW": 120,
-    "PATCH_LEN": 24,
-    "D_MODEL": 128,
-    "DEPTH": 2,
-    "ALPHA": 0.1,
-    "DELTA_T_MAX": 3,
-    "EPOCHS": 300
-  }
-}

requirements.txt

@@ -5,6 +5,6 @@
 numpy>=2.0
 pandas>=2.2
 pyarrow>=16
-histdata>=1.3        # histdata.com downloader (handles the tk token politely)
+histdata>=1.1        # histdata.com downloader (1.1 is newest on PyPI; 1.3 never existed)
 hmmlearn>=0.3        # regime detector (prepare_regime.py, jepa-fx-risk#13)
 scikit-learn>=1.4    # HMM dependency