sql-dialect-master 1.1.7__tar.gz → 1.1.9__tar.gz

{sql_dialect_master-1.1.7 → sql_dialect_master-1.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sql-dialect-master
-Version: 1.1.7
+Version: 1.1.9
 Summary: SQL Dialect Master - Multi-database SQL conversion engine
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
@@ -10,6 +10,7 @@ Requires-Dist: fastapi>=0.115.0
 Requires-Dist: uvicorn>=0.30.0
 Requires-Dist: pydantic>=2.9.0
 Requires-Dist: pydantic-settings>=2.0.0
+Requires-Dist: prometheus-client<1.0.0,>=0.20.0
 Provides-Extra: dev
 Requires-Dist: hypothesis>=6.112.0; extra == "dev"
 Requires-Dist: pytest>=8.3.0; extra == "dev"
@@ -35,7 +36,7 @@ Dynamic: license-file
 
 Enterprise-grade multi-database SQL conversion engine supporting 12 database dialects.
 
-Current release: 1.1.7
+Current release: 1.1.9
 
 [![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
@@ -293,6 +294,7 @@ sql-dialect-master/
 | Endpoint | Method | Description |
 |----------|--------|-------------|
 | `/api/convert` | POST | Convert SQL between dialects; response includes `error_code` on failure |
+| `/api/convert/batch` | POST | Convert an ordered batch with one dialect pair and per-item results |
 | `/api/parse` | POST | Parse SQL and extract structural elements |
 | `/api/nl2sql` | POST | Generate SQL from natural language |
 | `/api/functions` | GET | Search SQL functions |
@@ -304,6 +306,24 @@ sql-dialect-master/
 | `/health/deep` | GET | Deep health check |
 | `/api/stats` | GET | Service and dataset statistics |
 
+For example, send this JSON body to `POST /api/convert/batch`:
+
+```json
+{
+  "statements": ["SELECT id FROM users", "SELECT user_id FROM orders"],
+  "source_dialect": "postgres",
+  "target_dialect": "mysql",
+  "pretty": true
+}
+```
+
+Results retain input order and include a zero-based `index` alongside the
+single-conversion response fields. The summary includes `count`, `succeeded`,
+and `failed`; top-level `success` is true only when every item succeeds.
+Ordinary item failures, including a batch where every item fails, return HTTP
+200 with per-item `error` and `error_code`. Request-level errors use the
+existing error envelope; 503/504 responses do not include partial results.
+
 ## 🧪 Quality, Validation & Performance
 
 The project maintains a 12 × 12 source-to-target dialect regression matrix, semantic regression tests, post-processing safety regressions, security boundary checks, deterministic rule-engine tests, cache-versioning tests, async concurrency tests, and stable error-code tests.
@@ -316,7 +336,14 @@ The semantic CI gate executes representative conversions against PostgreSQL and
 
 Security validation structurally detects stacked SQL statements using the parser when available, with configurable policy controlling whether dangerous input is blocked or only warned about.
 
-The async batch API bounds concurrent work and preserves input order. A reproducible transpiler benchmark is available under `backend/benchmarks/` and is also executed in CI for performance observability. The benchmark intentionally reports measurements without failing the build on a fixed latency threshold because hosted CI timing is variable.
+The SDK's `batch_transpile_async` bounds concurrent work and preserves input
+order. REST batch conversion runs sequentially in one API worker slot, and the
+entire batch shares the default 30-second queue-plus-execution budget
+(`SDM_REQUEST_TIMEOUT`). HTTP 504 does not cancel the background batch. See
+the [deployment limits](docs/deployment.md#1-deployment-model) for capacity
+and timeout behavior.
+
+A reproducible transpiler benchmark is available under `backend/benchmarks/` and is also executed in CI for performance observability. The benchmark intentionally reports measurements without failing the build on a fixed latency threshold because hosted CI timing is variable.
 
 README source-of-truth checks run in CI and verify the release version, Python requirement, supported dialect list, and benchmark references against repository sources.
 
@@ -372,3 +399,4 @@ public catalog responses use short `private` caching. Full deployment details
 will be documented in `docs/deployment.md`.
 
 See [`docs/deployment.md`](docs/deployment.md) for production deployment guidance.
+Metrics configuration and scraping guidance are documented in the same guide.

{sql_dialect_master-1.1.7 → sql_dialect_master-1.1.9}/README.md

@@ -2,7 +2,7 @@
 
 Enterprise-grade multi-database SQL conversion engine supporting 12 database dialects.
 
-Current release: 1.1.7
+Current release: 1.1.9
 
 [![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
@@ -260,6 +260,7 @@ sql-dialect-master/
 | Endpoint | Method | Description |
 |----------|--------|-------------|
 | `/api/convert` | POST | Convert SQL between dialects; response includes `error_code` on failure |
+| `/api/convert/batch` | POST | Convert an ordered batch with one dialect pair and per-item results |
 | `/api/parse` | POST | Parse SQL and extract structural elements |
 | `/api/nl2sql` | POST | Generate SQL from natural language |
 | `/api/functions` | GET | Search SQL functions |
@@ -271,6 +272,24 @@ sql-dialect-master/
 | `/health/deep` | GET | Deep health check |
 | `/api/stats` | GET | Service and dataset statistics |
 
+For example, send this JSON body to `POST /api/convert/batch`:
+
+```json
+{
+  "statements": ["SELECT id FROM users", "SELECT user_id FROM orders"],
+  "source_dialect": "postgres",
+  "target_dialect": "mysql",
+  "pretty": true
+}
+```
+
+Results retain input order and include a zero-based `index` alongside the
+single-conversion response fields. The summary includes `count`, `succeeded`,
+and `failed`; top-level `success` is true only when every item succeeds.
+Ordinary item failures, including a batch where every item fails, return HTTP
+200 with per-item `error` and `error_code`. Request-level errors use the
+existing error envelope; 503/504 responses do not include partial results.
+
 ## 🧪 Quality, Validation & Performance
 
 The project maintains a 12 × 12 source-to-target dialect regression matrix, semantic regression tests, post-processing safety regressions, security boundary checks, deterministic rule-engine tests, cache-versioning tests, async concurrency tests, and stable error-code tests.
@@ -283,7 +302,14 @@ The semantic CI gate executes representative conversions against PostgreSQL and
 
 Security validation structurally detects stacked SQL statements using the parser when available, with configurable policy controlling whether dangerous input is blocked or only warned about.
 
-The async batch API bounds concurrent work and preserves input order. A reproducible transpiler benchmark is available under `backend/benchmarks/` and is also executed in CI for performance observability. The benchmark intentionally reports measurements without failing the build on a fixed latency threshold because hosted CI timing is variable.
+The SDK's `batch_transpile_async` bounds concurrent work and preserves input
+order. REST batch conversion runs sequentially in one API worker slot, and the
+entire batch shares the default 30-second queue-plus-execution budget
+(`SDM_REQUEST_TIMEOUT`). HTTP 504 does not cancel the background batch. See
+the [deployment limits](docs/deployment.md#1-deployment-model) for capacity
+and timeout behavior.
+
+A reproducible transpiler benchmark is available under `backend/benchmarks/` and is also executed in CI for performance observability. The benchmark intentionally reports measurements without failing the build on a fixed latency threshold because hosted CI timing is variable.
 
 README source-of-truth checks run in CI and verify the release version, Python requirement, supported dialect list, and benchmark references against repository sources.
 
@@ -339,3 +365,4 @@ public catalog responses use short `private` caching. Full deployment details
 will be documented in `docs/deployment.md`.
 
 See [`docs/deployment.md`](docs/deployment.md) for production deployment guidance.
+Metrics configuration and scraping guidance are documented in the same guide.

{sql_dialect_master-1.1.7 → sql_dialect_master-1.1.9}/backend/api/main.py

@@ -27,9 +27,18 @@ from fastapi import Depends, FastAPI, HTTPException, Query, Request
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.middleware.gzip import GZipMiddleware
 from fastapi.responses import JSONResponse
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import BaseModel, ConfigDict, Field, StrictStr
 
 from backend.api.auth import require_api_access
+from backend.api.metrics import (
+    MetricsMiddleware,
+    configure_runtime_metrics,
+    metrics_response,
+    observe_transpile_batch_size,
+    record_transpile_batch_items,
+    record_transpile_batch_request,
+    record_transpile_request,
+)
 from backend.api.rate_limit_store import InMemoryRateLimitStore
 from backend.api.readiness import health_probe_response
 from backend.api.workers import BoundedWorkerPool, WorkerCapacityError
@@ -303,6 +312,12 @@ func_encyclopedia = FunctionEncyclopedia()
 type_mapper = TypeMapper()
 nl2sql_generator = NL2SQLGenerator()
 
+configure_runtime_metrics(
+    transpiler_provider=lambda: transpiler,
+    worker_provider=_get_worker_pool,
+    limiter_provider=lambda: rate_limiter,
+)
+
 # Request timing middleware with logging
 @app.middleware("http")
 async def add_process_time_header(request: Request, call_next):
@@ -320,6 +335,11 @@ async def add_process_time_header(request: Request, call_next):
                     response.status_code, process_time)
     return response
 
+
+# This is the outermost application middleware, so it also observes short
+# circuit responses returned by rate limiting and worker-capacity guards.
+app.add_middleware(MetricsMiddleware)
+
 # Dialect info for enhanced responses (from centralized config)
 DIALECT_INFO = get_dialect_api_info()
 
@@ -380,6 +400,38 @@ class ConvertResponse(BaseModel):
     )
     timestamp: str = Field(default_factory=lambda: datetime.now().isoformat(), description="Response timestamp")
 
+
+class BatchConvertRequest(BaseModel):
+    """Convert an ordered, bounded list using one dialect pair."""
+
+    statements: List[StrictStr] = Field(
+        ...,
+        min_length=1,
+        max_length=settings.max_batch_size,
+        description="SQL statements in input order; each item is converted independently",
+    )
+    source_dialect: str
+    target_dialect: str
+    pretty: bool = settings.transpiler_pretty_default
+
+
+class BatchConvertItemResponse(ConvertResponse):
+    """A conversion result associated with its original input position."""
+
+    index: int = Field(..., ge=0, description="Zero-based index in the input statements")
+
+
+class BatchConvertResponse(BaseModel):
+    """Ordered conversion results, including ordinary per-item failures."""
+
+    success: bool
+    results: List[BatchConvertItemResponse]
+    count: int
+    succeeded: int
+    failed: int
+    timestamp: str = Field(default_factory=lambda: datetime.now().isoformat())
+
+
 class NL2SQLRequest(BaseModel):
     """Natural language to SQL request model."""
     text: str = Field(..., description="Natural language query (Chinese or English)")
@@ -460,6 +512,10 @@ class APIResponse(BaseModel):
 
 # === API Endpoints ===
 
+@app.get("/metrics", include_in_schema=False)
+async def metrics_endpoint(request: Request):
+    return await metrics_response(request)
+
 @app.get("/", tags=["system"])
 async def root():
     """
@@ -560,11 +616,13 @@ async def convert_sql(request: ConvertRequest):
     source_dialect = request.source_dialect.strip().lower()
     target_dialect = request.target_dialect.strip().lower()
     if source_dialect not in SUPPORTED_DIALECTS:
+        record_transpile_request("unknown", "unknown", "validation_error")
         raise HTTPException(
             status_code=400,
             detail=f"Unsupported source dialect: {request.source_dialect}. Supported: {SUPPORTED_DIALECTS}"
         )
     if target_dialect not in SUPPORTED_DIALECTS:
+        record_transpile_request(source_dialect, "unknown", "validation_error")
         raise HTTPException(
             status_code=400,
             detail=f"Unsupported target dialect: {request.target_dialect}. Supported: {SUPPORTED_DIALECTS}"
@@ -572,12 +630,21 @@ async def convert_sql(request: ConvertRequest):
 
     # sqlglot parsing/transpilation is CPU-bound.  Keep it off the event loop
     # so one large request cannot stall unrelated async requests.
-    result = await _run_cpu_bound(
-        transpiler.transpile,
-        request.sql,
+    try:
+        result = await _run_cpu_bound(
+            transpiler.transpile,
+            request.sql,
+            source_dialect,
+            target_dialect,
+            request.pretty,
+        )
+    except HTTPException:
+        record_transpile_request(source_dialect, target_dialect, "error")
+        raise
+    record_transpile_request(
         source_dialect,
         target_dialect,
-        request.pretty,
+        "success" if result.success else "error",
     )
     return ConvertResponse(
         success=result.success,
@@ -593,6 +660,60 @@ async def convert_sql(request: ConvertRequest):
         target_validation_state=result.target_validation_state,
     )
 
+@app.post("/api/convert/batch", response_model=BatchConvertResponse, tags=["conversion"])
+async def convert_sql_batch(request: BatchConvertRequest):
+    """Convert statements sequentially in one worker slot, preserving input order.
+
+    Ordinary item failures, including a batch where every item fails, return
+    HTTP 200 with per-item errors. Request-level failures use the existing
+    error envelope. A 504 ends the wait but does not cancel the worker batch.
+    """
+    source_dialect = target_dialect = "unknown"
+    try:
+        source_dialect = normalize_dialect(request.source_dialect, "source dialect")
+        target_dialect = normalize_dialect(request.target_dialect, "target dialect")
+        observe_transpile_batch_size(len(request.statements))
+        batch_results = await _run_cpu_bound(
+            transpiler.batch_transpile,
+            list(request.statements),
+            source_dialect,
+            target_dialect,
+            request.pretty,
+        )
+        results = [
+            BatchConvertItemResponse(index=index, **result.to_dict())
+            for index, result in enumerate(batch_results)
+        ]
+        count = len(results)
+        succeeded = sum(item.success for item in results)
+        failed = count - succeeded
+        response = BatchConvertResponse(
+            success=failed == 0,
+            results=results,
+            count=count,
+            succeeded=succeeded,
+            failed=failed,
+        )
+    except HTTPException as exc:
+        record_transpile_batch_request(
+            source_dialect,
+            target_dialect,
+            "validation_error" if exc.status_code == 400 else "error",
+        )
+        raise
+    except Exception:
+        record_transpile_batch_request(source_dialect, target_dialect, "error")
+        raise
+
+    record_transpile_batch_items(source_dialect, target_dialect, succeeded, failed)
+    record_transpile_batch_request(
+        source_dialect,
+        target_dialect,
+        "success" if failed == 0 else "partial_failure" if succeeded else "error",
+    )
+    return response
+
+
 @app.post("/api/parse", tags=["conversion"])
 async def parse_sql(request: ParseRequest):
     """

sql_dialect_master-1.1.9/backend/api/metrics.py

@@ -0,0 +1,204 @@
+"""Protected Prometheus metrics for the API process."""
+
+from __future__ import annotations
+
+import secrets
+from collections.abc import Callable
+
+from fastapi import Request
+from fastapi.responses import PlainTextResponse, Response
+from prometheus_client import (
+    CONTENT_TYPE_LATEST,
+    CollectorRegistry,
+    Counter,
+    Gauge,
+    Histogram,
+    generate_latest,
+)
+from prometheus_client.core import CounterMetricFamily, GaugeMetricFamily
+
+from backend.core.config import settings
+from backend.core.metadata import PROJECT_VERSION
+
+REGISTRY = CollectorRegistry(auto_describe=True)
+
+BUILD_INFO = Gauge("sdm_build_info", "SQL Dialect Master build information", ["version"], registry=REGISTRY)
+BUILD_INFO.labels(version=PROJECT_VERSION).set(1)
+
+HTTP_REQUESTS = Counter(
+    "sdm_http_requests_total",
+    "HTTP requests handled by the API",
+    ["method", "route", "status_class"],
+    registry=REGISTRY,
+)
+HTTP_DURATION = Histogram(
+    "sdm_http_request_duration_seconds",
+    "HTTP request duration in seconds",
+    ["method", "route", "status_class"],
+    registry=REGISTRY,
+)
+RATE_LIMIT_REJECTIONS = Counter(
+    "sdm_rate_limit_rejections_total",
+    "Rate-limited requests",
+    registry=REGISTRY,
+)
+TRANSPILE_REQUESTS = Counter(
+    "sdm_transpile_requests_total",
+    "Conversion requests by dialect pair and result",
+    ["source", "target", "result"],
+    registry=REGISTRY,
+)
+TRANSPILE_BATCH_REQUESTS = Counter(
+    "sdm_transpile_batch_requests_total",
+    "Batch conversion handler outcomes by dialect pair and result",
+    ["source", "target", "result"],
+    registry=REGISTRY,
+)
+TRANSPILE_BATCH_ITEMS = Counter(
+    "sdm_transpile_batch_items_total",
+    "Items in complete batch results received by the API handler",
+    ["source", "target", "result"],
+    registry=REGISTRY,
+)
+TRANSPILE_BATCH_SIZE = Histogram(
+    "sdm_transpile_batch_size",
+    "Statement count of validated batches before worker admission",
+    buckets=(1, 2, 5, 10, 20, 50, 100),
+    registry=REGISTRY,
+)
+
+_transpiler_provider: Callable[[], object] | None = None
+_worker_provider: Callable[[], object] | None = None
+_limiter_provider: Callable[[], object] | None = None
+
+
+def configure_runtime_metrics(*, transpiler_provider=None, worker_provider=None, limiter_provider=None) -> None:
+    """Register process-local runtime providers used when /metrics is scraped."""
+    global _transpiler_provider, _worker_provider, _limiter_provider
+    _transpiler_provider = transpiler_provider
+    _worker_provider = worker_provider
+    _limiter_provider = limiter_provider
+
+
+class RuntimeCollector:
+    """Read low-frequency runtime snapshots without copying them per request."""
+
+    def collect(self):
+        if _transpiler_provider is not None:
+            try:
+                stats = _transpiler_provider().get_stats()
+                cache = stats.get("cache", {})
+                if cache.get("enabled", True) is not False:
+                    yield CounterMetricFamily("sdm_transpile_cache_hits_total", "Transpiler cache hits", value=cache.get("hits", 0))
+                    yield CounterMetricFamily("sdm_transpile_cache_misses_total", "Transpiler cache misses", value=cache.get("misses", 0))
+                    yield CounterMetricFamily("sdm_transpile_cache_evictions_total", "Transpiler cache evictions", value=cache.get("evictions", 0))
+                    yield GaugeMetricFamily("sdm_transpile_cache_size", "Current transpiler cache size", value=cache.get("size", 0))
+            except Exception:
+                pass
+
+        if _worker_provider is not None:
+            try:
+                stats = _worker_provider().stats()
+                yield GaugeMetricFamily("sdm_api_worker_capacity", "API worker pool capacity", value=stats["capacity"])
+                yield GaugeMetricFamily("sdm_api_worker_in_use", "API worker slots in use", value=stats["in_use"])
+                yield CounterMetricFamily("sdm_api_worker_rejections_total", "API worker capacity rejections", value=stats["rejections"])
+                yield CounterMetricFamily("sdm_api_request_timeouts_total", "API request timeouts", value=stats["timeouts"])
+            except Exception:
+                pass
+
+        if _limiter_provider is not None:
+            try:
+                stats = _limiter_provider().get_stats()
+                if stats.get("backend") == "memory":
+                    yield GaugeMetricFamily("sdm_rate_limit_active_clients", "Active in-memory rate-limit clients", value=stats.get("active_clients", 0))
+            except Exception:
+                pass
+
+
+REGISTRY.register(RuntimeCollector())
+
+
+def normalize_method(method: str) -> str:
+    return method if method in {"GET", "POST", "HEAD", "OPTIONS"} else "other"
+
+
+def route_template(request: Request) -> str:
+    route = request.scope.get("route")
+    template = getattr(route, "path_format", None) or getattr(route, "path", None)
+    return template if template else "other"
+
+
+def status_class(status_code: int) -> str:
+    return f"{status_code // 100}xx" if 100 <= status_code < 600 else "other"
+
+
+def record_http_request(request: Request, status_code: int, duration: float) -> None:
+    if request.url.path == "/metrics":
+        return
+    labels = (normalize_method(request.method), route_template(request), status_class(status_code))
+    HTTP_REQUESTS.labels(*labels).inc()
+    HTTP_DURATION.labels(*labels).observe(duration)
+
+
+def record_rate_limit_rejection() -> None:
+    RATE_LIMIT_REJECTIONS.inc()
+
+
+def record_transpile_request(source: str, target: str, result: str) -> None:
+    TRANSPILE_REQUESTS.labels(source=source, target=target, result=result).inc()
+
+
+def record_transpile_batch_request(source: str, target: str, result: str) -> None:
+    TRANSPILE_BATCH_REQUESTS.labels(source=source, target=target, result=result).inc()
+
+
+def record_transpile_batch_items(source: str, target: str, succeeded: int, failed: int) -> None:
+    if succeeded:
+        TRANSPILE_BATCH_ITEMS.labels(source=source, target=target, result="success").inc(succeeded)
+    if failed:
+        TRANSPILE_BATCH_ITEMS.labels(source=source, target=target, result="error").inc(failed)
+
+
+def observe_transpile_batch_size(size: int) -> None:
+    TRANSPILE_BATCH_SIZE.observe(size)
+
+
+def _authorized(request: Request) -> bool:
+    configured = settings.metrics_token
+    expected = configured.get_secret_value().strip() if configured else ""
+    supplied = request.headers.get("X-Metrics-Token", "")
+    return bool(expected and supplied and secrets.compare_digest(supplied, expected))
+
+
+async def metrics_response(request: Request) -> Response:
+    if not settings.metrics_enabled:
+        return Response(status_code=404)
+    if not _authorized(request):
+        return Response(status_code=401, content="Metrics token required")
+    return PlainTextResponse(generate_latest(REGISTRY), media_type=CONTENT_TYPE_LATEST)
+
+
+class MetricsMiddleware:
+    """ASGI middleware that records final HTTP status and elapsed time."""
+
+    def __init__(self, app):
+        self.app = app
+
+    async def __call__(self, scope, receive, send):
+        if scope.get("type") != "http":
+            await self.app(scope, receive, send)
+            return
+        import time
+
+        started = time.perf_counter()
+        status_code = 500
+
+        async def send_wrapper(message):
+            nonlocal status_code
+            if message.get("type") == "http.response.start":
+                status_code = message.get("status", 500)
+            await send(message)
+
+        await self.app(scope, receive, send_wrapper)
+        request = Request(scope)
+        record_http_request(request, status_code, time.perf_counter() - started)

{sql_dialect_master-1.1.7 → sql_dialect_master-1.1.9}/backend/api/middleware.py

@@ -20,6 +20,7 @@ from starlette.concurrency import run_in_threadpool
 from backend.core.exceptions import ErrorCode
 
 from .client_identity import resolve_client_ip
+from .metrics import record_rate_limit_rejection
 from .rate_limit_store import InMemoryRateLimitStore, RateLimitStore, create_rate_limit_store
 from .readiness import health_probe_response
 
@@ -108,7 +109,7 @@ class RateLimitMiddleware(BaseHTTPMiddleware):
 
     async def dispatch(self, request: Request, call_next) -> Response:
         is_health_probe = (
-            request.url.path in {"/health", "/", "/ready", "/health/deep"}
+            request.url.path in {"/health", "/", "/ready", "/health/deep", "/metrics"}
             and request.method in {"GET", "HEAD"}
         )
         # Browser CORS preflight requests carry no business payload and are
@@ -133,6 +134,7 @@ class RateLimitMiddleware(BaseHTTPMiddleware):
             is_allowed, remaining, reset_time = await run_in_threadpool(self.limiter.is_allowed, client_id)
             rate_limit_checked = True
             if not is_allowed:
+                record_rate_limit_rejection()
                 logger.warning("Rate limit exceeded for client: %s", _sanitize_log_value(client_id))
                 return JSONResponse(
                     status_code=429,
@@ -164,6 +166,9 @@ class RateLimitMiddleware(BaseHTTPMiddleware):
         if is_health_probe:
             if request.url.path in {"/ready", "/health/deep"}:
                 return await health_probe_response(request)
+            if request.url.path == "/metrics":
+                from .metrics import metrics_response
+                return await metrics_response(request)
             return await call_next(request)
         response = await call_next(request)
         if rate_limit_checked:
@@ -386,6 +391,8 @@ class CacheControlMiddleware(BaseHTTPMiddleware):
         if request.method == "OPTIONS":
             return None
         path = request.url.path
+        if path == "/metrics":
+            return "no-store"
         if path in {"/docs", "/redoc", "/openapi.json"}:
             return None
         if request.method == "POST" and path.startswith("/api/"):

{sql_dialect_master-1.1.7 → sql_dialect_master-1.1.9}/backend/api/workers.py

@@ -24,22 +24,54 @@ class BoundedWorkerPool:
         self._slots = BoundedSemaphore(workers + queue_size)
         self._executor = ThreadPoolExecutor(max_workers=workers, thread_name_prefix="sdm-api")
         self._shutdown_lock = Lock()
+        self._stats_lock = Lock()
+        self._capacity = workers + queue_size
+        self._in_use = 0
+        self._rejections = 0
+        self._timeouts = 0
         self._shutdown = False
 
     async def run(self, function, *args, timeout: float):
         if not self._slots.acquire(blocking=False):
+            with self._stats_lock:
+                self._rejections += 1
             raise WorkerCapacityError("Request processing capacity is exhausted")
+        with self._stats_lock:
+            self._in_use += 1
         try:
             future = self._executor.submit(function, *args)
         except BaseException:
             self._slots.release()
+            with self._stats_lock:
+                self._in_use -= 1
             raise
-        future.add_done_callback(lambda _future: self._slots.release())
+
+        def release_slot(_future):
+            self._slots.release()
+            with self._stats_lock:
+                self._in_use -= 1
+
+        future.add_done_callback(release_slot)
         wrapped = asyncio.wrap_future(future)
         # A timed-out caller no longer awaits this result. Retrieve exceptions
         # to avoid an unhandled-future warning when background work later fails.
         wrapped.add_done_callback(lambda completed: None if completed.cancelled() else completed.exception())
-        return await asyncio.wait_for(asyncio.shield(wrapped), timeout=timeout)
+        try:
+            return await asyncio.wait_for(asyncio.shield(wrapped), timeout=timeout)
+        except asyncio.TimeoutError:
+            with self._stats_lock:
+                self._timeouts += 1
+            raise
+
+    def stats(self) -> dict[str, int]:
+        """Return a thread-safe snapshot of pool capacity counters."""
+        with self._stats_lock:
+            return {
+                "capacity": self._capacity,
+                "in_use": self._in_use,
+                "rejections": self._rejections,
+                "timeouts": self._timeouts,
+            }
 
     def shutdown(self) -> None:
         """Cancel queued work; already-running calls retain their slots."""

{sql_dialect_master-1.1.7 → sql_dialect_master-1.1.9}/backend/core/config.py

@@ -276,6 +276,10 @@ class AppSettings(BaseSettings):
     # Readiness probes.  SecretStr keeps the value out of settings reprs and
     # structured logs while still allowing deployment through SDM_ env vars.
     health_probe_token: Optional[SecretStr] = None
+
+    # Prometheus metrics are opt-in and use a dedicated secret.
+    metrics_enabled: bool = False
+    metrics_token: Optional[SecretStr] = None
     
     # Security settings
     security_check_enabled: bool = True
@@ -292,6 +296,14 @@ class AppSettings(BaseSettings):
             self.parser_max_sql_length = self.transpiler_max_sql_length
         return self
 
+    @model_validator(mode="after")
+    def _validate_metrics_token(self) -> "AppSettings":
+        """Require a non-blank dedicated token when metrics are enabled."""
+        token = self.metrics_token.get_secret_value().strip() if self.metrics_token else ""
+        if self.metrics_enabled and not token:
+            raise ValueError("metrics_token is required when metrics_enabled is true")
+        return self
+
     @field_validator("log_level", mode="before")
     @classmethod
     def _normalize_log_level(cls, value: str) -> str:

{sql_dialect_master-1.1.7 → sql_dialect_master-1.1.9}/backend/core/metadata.py

@@ -17,8 +17,8 @@ Design rules:
 from __future__ import annotations
 
 # ── Release version facts (sole source of truth) ────────────────────────
-PROJECT_VERSION = "1.1.7"
-API_VERSION = "1.1.7"
+PROJECT_VERSION = "1.1.9"
+API_VERSION = "1.1.9"
 # Frontend v2 architecture — independent of the product release version.
 FRONTEND_ARCHITECTURE_VERSION = 2
 

{sql_dialect_master-1.1.7 → sql_dialect_master-1.1.9}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "sql-dialect-master"
-version = "1.1.7"
+version = "1.1.9"
 description = "SQL Dialect Master - Multi-database SQL conversion engine"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -10,6 +10,7 @@ dependencies = [
     "uvicorn>=0.30.0",
     "pydantic>=2.9.0",
     "pydantic-settings>=2.0.0",
+    "prometheus-client>=0.20.0,<1.0.0",
 ]
 
 [project.optional-dependencies]
@@ -51,3 +52,19 @@ exclude = ["backend.tests*", "backend.benchmarks*"]
 testpaths = ["backend/tests"]
 python_files = ["test_*.py"]
 addopts = "-v --tb=short"
+
+[tool.coverage.run]
+source = ["backend"]
+omit = [
+    "backend/tests/*",
+    "backend/benchmarks/*",
+]
+
+[tool.coverage.report]
+show_missing = true
+skip_covered = false
+fail_under = 93
+exclude_lines = [
+    "pragma: no cover",
+    "if __name__ == .__main__.:",
+]

{sql_dialect_master-1.1.7 → sql_dialect_master-1.1.9}/sql_dialect_master.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sql-dialect-master
-Version: 1.1.7
+Version: 1.1.9
 Summary: SQL Dialect Master - Multi-database SQL conversion engine
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
@@ -10,6 +10,7 @@ Requires-Dist: fastapi>=0.115.0
 Requires-Dist: uvicorn>=0.30.0
 Requires-Dist: pydantic>=2.9.0
 Requires-Dist: pydantic-settings>=2.0.0
+Requires-Dist: prometheus-client<1.0.0,>=0.20.0
 Provides-Extra: dev
 Requires-Dist: hypothesis>=6.112.0; extra == "dev"
 Requires-Dist: pytest>=8.3.0; extra == "dev"
@@ -35,7 +36,7 @@ Dynamic: license-file
 
 Enterprise-grade multi-database SQL conversion engine supporting 12 database dialects.
 
-Current release: 1.1.7
+Current release: 1.1.9
 
 [![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
@@ -293,6 +294,7 @@ sql-dialect-master/
 | Endpoint | Method | Description |
 |----------|--------|-------------|
 | `/api/convert` | POST | Convert SQL between dialects; response includes `error_code` on failure |
+| `/api/convert/batch` | POST | Convert an ordered batch with one dialect pair and per-item results |
 | `/api/parse` | POST | Parse SQL and extract structural elements |
 | `/api/nl2sql` | POST | Generate SQL from natural language |
 | `/api/functions` | GET | Search SQL functions |
@@ -304,6 +306,24 @@ sql-dialect-master/
 | `/health/deep` | GET | Deep health check |
 | `/api/stats` | GET | Service and dataset statistics |
 
+For example, send this JSON body to `POST /api/convert/batch`:
+
+```json
+{
+  "statements": ["SELECT id FROM users", "SELECT user_id FROM orders"],
+  "source_dialect": "postgres",
+  "target_dialect": "mysql",
+  "pretty": true
+}
+```
+
+Results retain input order and include a zero-based `index` alongside the
+single-conversion response fields. The summary includes `count`, `succeeded`,
+and `failed`; top-level `success` is true only when every item succeeds.
+Ordinary item failures, including a batch where every item fails, return HTTP
+200 with per-item `error` and `error_code`. Request-level errors use the
+existing error envelope; 503/504 responses do not include partial results.
+
 ## 🧪 Quality, Validation & Performance
 
 The project maintains a 12 × 12 source-to-target dialect regression matrix, semantic regression tests, post-processing safety regressions, security boundary checks, deterministic rule-engine tests, cache-versioning tests, async concurrency tests, and stable error-code tests.
@@ -316,7 +336,14 @@ The semantic CI gate executes representative conversions against PostgreSQL and
 
 Security validation structurally detects stacked SQL statements using the parser when available, with configurable policy controlling whether dangerous input is blocked or only warned about.
 
-The async batch API bounds concurrent work and preserves input order. A reproducible transpiler benchmark is available under `backend/benchmarks/` and is also executed in CI for performance observability. The benchmark intentionally reports measurements without failing the build on a fixed latency threshold because hosted CI timing is variable.
+The SDK's `batch_transpile_async` bounds concurrent work and preserves input
+order. REST batch conversion runs sequentially in one API worker slot, and the
+entire batch shares the default 30-second queue-plus-execution budget
+(`SDM_REQUEST_TIMEOUT`). HTTP 504 does not cancel the background batch. See
+the [deployment limits](docs/deployment.md#1-deployment-model) for capacity
+and timeout behavior.
+
+A reproducible transpiler benchmark is available under `backend/benchmarks/` and is also executed in CI for performance observability. The benchmark intentionally reports measurements without failing the build on a fixed latency threshold because hosted CI timing is variable.
 
 README source-of-truth checks run in CI and verify the release version, Python requirement, supported dialect list, and benchmark references against repository sources.
 
@@ -372,3 +399,4 @@ public catalog responses use short `private` caching. Full deployment details
 will be documented in `docs/deployment.md`.
 
 See [`docs/deployment.md`](docs/deployment.md) for production deployment guidance.
+Metrics configuration and scraping guidance are documented in the same guide.

{sql_dialect_master-1.1.7 → sql_dialect_master-1.1.9}/sql_dialect_master.egg-info/SOURCES.txt

@@ -6,6 +6,7 @@ backend/api/__init__.py
 backend/api/auth.py
 backend/api/client_identity.py
 backend/api/main.py
+backend/api/metrics.py
 backend/api/middleware.py
 backend/api/rate_limit_store.py
 backend/api/readiness.py

{sql_dialect_master-1.1.7 → sql_dialect_master-1.1.9}/sql_dialect_master.egg-info/requires.txt

@@ -3,6 +3,7 @@ fastapi>=0.115.0
 uvicorn>=0.30.0
 pydantic>=2.9.0
 pydantic-settings>=2.0.0
+prometheus-client<1.0.0,>=0.20.0
 
 [dev]
 hypothesis>=6.112.0