Prepare Hugging Face deployment

.github/workflows/sync-to-hf.yml

@@ -28,7 +28,8 @@ jobs:
             exit 0
           fi
 
-          space_id="${HF_SPACE_ID:-${GITHUB_REPOSITORY_OWNER}/sql-query-reviewer}"
+          owner_slug="$(printf '%s' "${GITHUB_REPOSITORY_OWNER}" | tr '[:upper:]' '[:lower:]')"
+          space_id="${HF_SPACE_ID:-${owner_slug}/sql-query-reviewer}"
 
           git config user.email "actions@github.com"
           git config user.name "github-actions[bot]"

README.md

@@ -126,6 +126,15 @@ This repo is Space-ready because:
 - the repo includes a root `Dockerfile`
 - the API listens on port `8000`
 
+Recommended setup:
+1. Create a new Space at `https://huggingface.co/new-space`
+2. Set owner to your Hugging Face namespace, name to `sql-query-reviewer`, and SDK to `Docker`
+3. In GitHub, add repository secret `HF_TOKEN` with a Hugging Face token that can write to Spaces
+4. In GitHub, add repository variable `HF_SPACE_ID` with the exact repo id, for example `hellinferno/sql-query-reviewer`
+5. Push to `main` or run the `Sync To Hugging Face` workflow manually from the Actions tab
+
+Using `HF_SPACE_ID` is the safest option because your Hugging Face namespace may not match your GitHub owner name exactly.
+
 To deploy manually from a local machine with git:
 
 ```bash
@@ -151,7 +160,7 @@ The Hugging Face sync workflow expects:
 If `HF_SPACE_ID` is not set, the workflow defaults to:
 
 ```text
-<github-repository-owner>/sql-query-reviewer
+<lowercased-github-repository-owner>/sql-query-reviewer
 ```
 
 ## Usage Example

server/environment.py

@@ -114,7 +114,7 @@ class SQLReviewEnvironment:
 
         else:
             feedback = self._schema_feedback(task)
-            info = {"context_shared": bool(task.schema)}
+            info = {"context_shared": bool(task.schema_info)}
 
         state.total_reward += reward
 

tests/test_api.py

@@ -91,3 +91,20 @@ def test_identify_then_approve_can_finish_successfully() -> None:
     assert payload["reward"] > 0
     assert payload["info"]["final_score"] is not None
 
+
+def test_request_more_context_returns_context_shared_flag() -> None:
+    client = build_client()
+    client.post("/reset", json={"task_id": "easy_001"})
+
+    response = client.post(
+        "/step",
+        json={"action_type": "request_more_context", "confidence": 0.7},
+    )
+
+    assert response.status_code == 200
+    payload = response.json()
+    assert payload["reward"] == 0.0
+    assert "context_shared" in payload["info"]
+    assert payload["info"]["context_shared"] is True
+    assert payload["done"] is False
+

tests/test_reward.py

@@ -0,0 +1,99 @@
+from __future__ import annotations
+
+import pytest
+
+from sql_query_reviewer.models import GroundTruthIssue, SQLReviewAction
+from server.reward import compute_reward
+
+
+def _action(action_type: str, confidence: float = 0.5) -> SQLReviewAction:
+    if action_type == "identify_issue":
+        return SQLReviewAction(
+            action_type="identify_issue",
+            issue_category="syntax",
+            issue_description="some issue",
+            confidence=confidence,
+        )
+    if action_type == "suggest_fix":
+        return SQLReviewAction(
+            action_type="suggest_fix",
+            suggested_fix="SELECT 1;",
+            confidence=confidence,
+        )
+    return SQLReviewAction(action_type=action_type, confidence=confidence)
+
+
+def _issue(severity: float = 0.35) -> GroundTruthIssue:
+    return GroundTruthIssue(
+        id="test_issue_001",
+        category="syntax",
+        description="A test issue.",
+        severity=severity,
+        fix="SELECT 1;",
+        keywords=["test"],
+    )
+
+
+# ── identify_issue ────────────────────────────────────────────────────────────
+
+def test_identify_issue_duplicate_returns_small_penalty() -> None:
+    assert compute_reward(_action("identify_issue"), _issue(), duplicate_issue=True) == pytest.approx(-0.02)
+
+
+def test_identify_issue_no_match_returns_penalty() -> None:
+    assert compute_reward(_action("identify_issue"), None) == pytest.approx(-0.1)
+
+
+def test_identify_issue_match_no_fix_zero_confidence() -> None:
+    # base_reward = min(0.35, 0.35) = 0.35; fix_bonus = 0; confidence_bonus = 0
+    assert compute_reward(_action("identify_issue", confidence=0.0), _issue(0.35)) == pytest.approx(0.35)
+
+
+def test_identify_issue_match_no_fix_full_confidence() -> None:
+    # base=0.35 + confidence_bonus=min(0.05, 1.0*0.05)=0.05 → 0.40, capped at 0.4
+    assert compute_reward(_action("identify_issue", confidence=1.0), _issue(0.35)) == pytest.approx(0.4)
+
+
+def test_identify_issue_match_with_fix_zero_confidence() -> None:
+    # base=0.35 + fix_bonus=0.08 → 0.43, capped at 0.4
+    assert compute_reward(_action("identify_issue", confidence=0.0), _issue(0.35), fix_valid=True) == pytest.approx(0.4)
+
+
+def test_identify_issue_high_severity_capped_at_035_base() -> None:
+    # min(0.9, 0.35) = 0.35
+    assert compute_reward(_action("identify_issue", confidence=0.0), _issue(severity=0.9)) == pytest.approx(0.35)
+
+
+# ── suggest_fix ───────────────────────────────────────────────────────────────
+
+def test_suggest_fix_without_previous_issue_is_penalized() -> None:
+    assert compute_reward(_action("suggest_fix"), None, has_previous_issue=False) == pytest.approx(-0.05)
+
+
+def test_suggest_fix_with_previous_issue_invalid_fix() -> None:
+    assert compute_reward(_action("suggest_fix"), _issue(), has_previous_issue=True, fix_valid=False) == pytest.approx(0.0)
+
+
+def test_suggest_fix_with_previous_issue_valid_fix() -> None:
+    assert compute_reward(_action("suggest_fix"), _issue(), has_previous_issue=True, fix_valid=True) == pytest.approx(0.1)
+
+
+# ── approve ───────────────────────────────────────────────────────────────────
+
+def test_approve_all_issues_found_gives_positive_reward() -> None:
+    assert compute_reward(_action("approve"), None, remaining_unfound=0) == pytest.approx(0.2)
+
+
+def test_approve_one_issue_missed_gives_penalty() -> None:
+    assert compute_reward(_action("approve"), None, remaining_unfound=1) == pytest.approx(-0.15)
+
+
+def test_approve_many_issues_missed_floors_at_negative_one() -> None:
+    # -0.15 * 7 = -1.05 → floored at -1.0
+    assert compute_reward(_action("approve"), None, remaining_unfound=7) == pytest.approx(-1.0)
+
+
+# ── request_more_context ──────────────────────────────────────────────────────
+
+def test_request_more_context_returns_zero() -> None:
+    assert compute_reward(_action("request_more_context"), None) == pytest.approx(0.0)