agentevals-cli 0.8.3__tar.gz → 0.8.4__tar.gz

{agentevals_cli-0.8.3 → agentevals_cli-0.8.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentevals-cli
-Version: 0.8.3
+Version: 0.8.4
 Summary: Standalone framework to evaluate agent correctness based on portable OpenTelemetry traces
 License-File: LICENSE
 Requires-Python: >=3.11

{agentevals_cli-0.8.3 → agentevals_cli-0.8.4}/charts/agentevals/templates/deployment.yaml

@@ -77,6 +77,8 @@ spec:
               value: {{ .Values.database.postgres.schema | quote }}
             - name: AGENTEVALS_AUTO_MIGRATE
               value: {{ .Values.database.postgres.autoMigrate | quote }}
+            - name: AGENTEVALS_DB_CONNECT_TIMEOUT_S
+              value: {{ .Values.database.postgres.connectTimeoutSeconds | quote }}
             {{- if .Values.database.postgres.urlFile }}
             - name: AGENTEVALS_DATABASE_URL_FILE
               value: {{ .Values.database.postgres.urlFile | quote }}

{agentevals_cli-0.8.3 → agentevals_cli-0.8.4}/charts/agentevals/values.yaml

@@ -211,6 +211,12 @@ database:
     # false the server refuses to start if the schema is behind or dirty;
     # run "agentevals migrate up" manually in that case.
     autoMigrate: true
+    # -- Seconds the startup will spend retrying the initial Postgres
+    # connection before the pod aborts. Default 600s matches the chart's
+    # hard-coded startupProbe budget (failureThreshold 60 x periodSeconds
+    # 10). Going above 600s requires overriding the probe in your own
+    # downstream template.
+    connectTimeoutSeconds: 600
     # -- Bundled Postgres instance for development and evaluation only.
     # Not suitable for production. Deployed when enabled is true and url /
     # urlFile are not set.

{agentevals_cli-0.8.3 → agentevals_cli-0.8.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "agentevals-cli"
-version = "0.8.3"
+version = "0.8.4"
 description = "Standalone framework to evaluate agent correctness based on portable OpenTelemetry traces"
 readme = "README.md"
 requires-python = ">=3.11"

{agentevals_cli-0.8.3 → agentevals_cli-0.8.4}/src/agentevals/storage/postgres/migrator.py

@@ -13,6 +13,8 @@ from __future__ import annotations
 
 import asyncio
 import logging
+import math
+import os
 import re
 from dataclasses import dataclass
 from importlib.resources import files
@@ -252,23 +254,58 @@ def discover_migrations() -> list[Migration]:
     return _discover_migrations()
 
 
-CONNECT_RETRY_DEADLINE_S = 60.0
-"""Total wall-clock budget for the initial Postgres connection. Bundled PG
-in Kubernetes typically takes 5-15s to be ready (PVC bind, initdb, listener
-bind), so the agentevals lifespan can race the database on a fresh deploy.
-Retrying tolerates that gap rather than failing pod startup and relying on
-CrashLoopBackOff timing to eventually line up."""
+CONNECT_RETRY_DEADLINE_S = 600.0
+"""Default total wall-clock budget for the initial Postgres connection.
+Sized to span Kubernetes bring-up of a freshly provisioned database (PVC
+bind, initdb, listener bind, network policy propagation). Override at
+runtime by setting ``AGENTEVALS_DB_CONNECT_TIMEOUT_S`` to a positive
+number of seconds; an invalid value logs a warning and falls back to this
+default."""
+
+
+def connect_deadline_seconds() -> float:
+    """Resolve the connect-retry budget. Reads ``AGENTEVALS_DB_CONNECT_TIMEOUT_S``
+    and falls back to :data:`CONNECT_RETRY_DEADLINE_S` if the env var is
+    unset, empty, non-numeric, non-finite, or non-positive."""
+    raw = os.getenv("AGENTEVALS_DB_CONNECT_TIMEOUT_S")
+    if raw is None or raw == "":
+        return CONNECT_RETRY_DEADLINE_S
+    try:
+        val = float(raw)
+    except ValueError:
+        logger.warning(
+            "Invalid AGENTEVALS_DB_CONNECT_TIMEOUT_S=%r (not a number); using default %.0fs",
+            raw,
+            CONNECT_RETRY_DEADLINE_S,
+        )
+        return CONNECT_RETRY_DEADLINE_S
+    if not math.isfinite(val):
+        logger.warning(
+            "Invalid AGENTEVALS_DB_CONNECT_TIMEOUT_S=%r (must be finite); using default %.0fs",
+            raw,
+            CONNECT_RETRY_DEADLINE_S,
+        )
+        return CONNECT_RETRY_DEADLINE_S
+    if val <= 0:
+        logger.warning(
+            "Invalid AGENTEVALS_DB_CONNECT_TIMEOUT_S=%r (must be positive); using default %.0fs",
+            raw,
+            CONNECT_RETRY_DEADLINE_S,
+        )
+        return CONNECT_RETRY_DEADLINE_S
+    return val
 
 
 async def connect_with_retry(dsn: str, asyncpg_module) -> "asyncpg.Connection":
     """Open a single asyncpg connection, retrying on connection-refused or
-    server-not-ready errors for up to ``CONNECT_RETRY_DEADLINE_S`` seconds.
+    server-not-ready errors for up to :func:`connect_deadline_seconds`
+    seconds.
 
     Connection-time errors are tolerated; once a connection has been
     established and a query returned, all subsequent failures propagate
     normally.
     """
-    deadline = asyncio.get_event_loop().time() + CONNECT_RETRY_DEADLINE_S
+    deadline = asyncio.get_event_loop().time() + connect_deadline_seconds()
     delay = 0.5
     while True:
         try:

{agentevals_cli-0.8.3 → agentevals_cli-0.8.4}/src/agentevals/storage/postgres/pool.py

@@ -50,9 +50,9 @@ async def create_pool(settings: StorageSettings) -> "asyncpg.Pool":
         settings.schema_name,
     )
 
-    from .migrator import CONNECT_RETRY_DEADLINE_S
+    from .migrator import connect_deadline_seconds
 
-    deadline = asyncio.get_event_loop().time() + CONNECT_RETRY_DEADLINE_S
+    deadline = asyncio.get_event_loop().time() + connect_deadline_seconds()
     delay = 0.5
     while True:
         try:

{agentevals_cli-0.8.3 → agentevals_cli-0.8.4}/tests/storage/test_migrator.py

@@ -7,6 +7,7 @@ otherwise those tests skip so the suite stays runnable in pure-Python sandboxes.
 
 from __future__ import annotations
 
+import logging
 import os
 import re
 
@@ -14,10 +15,12 @@ import pytest
 
 from agentevals.storage.postgres.migrator import (
     ADVISORY_LOCK_KEY,
+    CONNECT_RETRY_DEADLINE_S,
     Migration,
     Migrator,
     _apply_schema,
     _discover_migrations,
+    connect_deadline_seconds,
     discover_migrations,
 )
 
@@ -71,6 +74,61 @@ class TestAdvisoryLockKey:
         assert ADVISORY_LOCK_KEY == 7259820376655812345
 
 
+class TestConnectDeadlineSeconds:
+    """``connect_deadline_seconds`` resolves AGENTEVALS_DB_CONNECT_TIMEOUT_S
+    to a float, falling back to CONNECT_RETRY_DEADLINE_S on any input the
+    retry loop cannot consume. Each failure mode logs at WARNING so the
+    cause is diagnosable from pod logs."""
+
+    @pytest.fixture(autouse=True)
+    def _clean_env(self, monkeypatch):
+        monkeypatch.delenv("AGENTEVALS_DB_CONNECT_TIMEOUT_S", raising=False)
+
+    def test_unset_returns_default(self):
+        assert connect_deadline_seconds() == CONNECT_RETRY_DEADLINE_S
+
+    def test_empty_returns_default(self, monkeypatch):
+        monkeypatch.setenv("AGENTEVALS_DB_CONNECT_TIMEOUT_S", "")
+        assert connect_deadline_seconds() == CONNECT_RETRY_DEADLINE_S
+
+    @pytest.mark.parametrize(
+        ("raw", "expected"),
+        [
+            ("42", 42.0),
+            ("120.5", 120.5),
+            ("0.1", 0.1),
+            ("3600", 3600.0),
+        ],
+    )
+    def test_parses_valid_positive_values(self, monkeypatch, raw, expected):
+        monkeypatch.setenv("AGENTEVALS_DB_CONNECT_TIMEOUT_S", raw)
+        assert connect_deadline_seconds() == expected
+
+    @pytest.mark.parametrize(
+        ("raw", "reason_substring"),
+        [
+            ("foo", "not a number"),
+            ("nan", "must be finite"),
+            ("inf", "must be finite"),
+            ("-inf", "must be finite"),
+            ("0", "must be positive"),
+            ("-5", "must be positive"),
+        ],
+    )
+    def test_invalid_values_fall_back_with_warning(self, monkeypatch, caplog, raw, reason_substring):
+        """Bad inputs return the default and log exactly one warning that
+        names the specific validation branch. The cardinality check
+        guards against a refactor that double-logs (e.g. emits both a
+        generic and a specific message)."""
+        monkeypatch.setenv("AGENTEVALS_DB_CONNECT_TIMEOUT_S", raw)
+        with caplog.at_level(logging.WARNING, logger="agentevals.storage.postgres.migrator"):
+            result = connect_deadline_seconds()
+        assert result == CONNECT_RETRY_DEADLINE_S
+        warnings = [r.getMessage() for r in caplog.records if r.levelname == "WARNING"]
+        assert len(warnings) == 1, f"expected one warning, got {warnings}"
+        assert reason_substring in warnings[0]
+
+
 class TestMigrationFilePattern:
     def test_filename_format(self):
         migrations = _discover_migrations()

{agentevals_cli-0.8.3 → agentevals_cli-0.8.4}/uv.lock

@@ -30,7 +30,7 @@ wheels = [
 
 [[package]]
 name = "agentevals-cli"
-version = "0.8.3"
+version = "0.8.4"
 source = { editable = "." }
 dependencies = [
     { name = "click" },