From fd72a39b1b6dd15851f50cbd34f38ccd6a9b55c4 Mon Sep 17 00:00:00 2001 From: Yuneng Jiang Date: Tue, 1 Sep 2026 12:54:07 -0700 Subject: [PATCH] revert: default the proxy back to the v1 migration resolver This reverts merge commit 2b1bd208349acf06967eeb151525f65942dd51bf (#31125) Two CircleCI jobs on the staging-to-main promotion went red the moment that PR landed. proxy_multi_instance_tests boots two proxies against one database, and both now race the same migration: Error: P3018 A migration failed to apply Database error code: 40P01, deadlock detected Process 73 waits for ShareLock on virtual transaction 4/11; blocked by process 75. Process 75 waits for ExclusiveLock on advisory lock [16384,0,72707369,1]; blocked by process 73 Neither proxy comes up, so the job times out after 300s waiting on localhost:4000. The same wait took 36.5s on the last green run Timeline: #31125 merged at 18:46:14Z and the failing run started at 18:49:59Z. The merge commit is not an ancestor of the last green revision (194a3cc) and is an ancestor of the first failing one (01de2837) The v2 resolver was meant to avoid exactly this class of contention, so the deadlock looks like a bug in it rather than a reason to abandon it. Putting the default back to v1 buys time to fix it without holding up the release --- .circleci/config.yml | 15 +- CLAUDE.md | 2 +- .../litellm_proxy_extras/utils.py | 132 +--- litellm-proxy-extras/tests/__init__.py | 0 .../tests/test_setup_database_fail_fast.py | 242 ++++++++ litellm/proxy/proxy_cli.py | 30 +- .../test_setup_database_fail_fast.py | 571 ------------------ .../test_basic_python_version.py | 14 +- tests/test_litellm/proxy/test_proxy_cli.py | 39 +- 9 files changed, 303 insertions(+), 742 deletions(-) create mode 100644 litellm-proxy-extras/tests/__init__.py create mode 100644 litellm-proxy-extras/tests/test_setup_database_fail_fast.py delete mode 100644 tests/litellm-proxy-extras/test_setup_database_fail_fast.py diff --git a/.circleci/config.yml b/.circleci/config.yml index 63012ce3fc0..55fa9410845 100644 --- a/.circleci/config.yml +++ b/.circleci/config.yml @@ -1483,7 +1483,7 @@ jobs: - run: name: Run tests command: | - uv run --no-sync python -m pytest -vv tests/local_testing/test_basic_python_version.py -k "not legacy_resolver" + uv run --no-sync python -m pytest -vv tests/local_testing/test_basic_python_version.py -k "not v2_resolver" installing_litellm_on_python_3_13: docker: @@ -1507,9 +1507,9 @@ jobs: - run: name: Run tests command: | - uv run --no-sync python -m pytest -v tests/local_testing/test_basic_python_version.py -k "not legacy_resolver" + uv run --no-sync python -m pytest -v tests/local_testing/test_basic_python_version.py -k "not v2_resolver" - installing_litellm_on_python_legacy_migration_resolver: + installing_litellm_on_python_v2_migration_resolver: docker: - *python312_image - image: cimg/postgres:16.0@sha256:b125148bc76e8e8eee5eb3ad6020a3a14110a14e8192f1c645128afebe2e2f84 @@ -1536,10 +1536,10 @@ jobs: url: tcp://localhost:5432 timeout: "60" - run: - name: Run legacy migration resolver proxy smoke test + name: Run v2 migration resolver proxy smoke test command: | uv run --no-sync python -m pytest -vv \ - tests/local_testing/test_basic_python_version.py::test_litellm_proxy_server_config_no_general_settings_legacy_resolver + tests/local_testing/test_basic_python_version.py::test_litellm_proxy_server_config_no_general_settings_v2_resolver helm_chart_testing: machine: @@ -2879,8 +2879,7 @@ jobs: command: | if grep -q "Error: P1001: Can't reach database server at" docker_output.log && \ (grep -q "Database setup failed after multiple retries" docker_output.log || \ - grep -q "ERROR: Application startup failed. Exiting." docker_output.log || \ - grep -q "Database migration cannot proceed" docker_output.log); then + grep -q "ERROR: Application startup failed. Exiting." docker_output.log); then echo "Expected error found. Test passed." else echo "Expected error not found. Test failed." @@ -3012,7 +3011,7 @@ workflows: filters: *main_branches - installing_litellm_on_python_3_13: filters: *main_branches - - installing_litellm_on_python_legacy_migration_resolver: + - installing_litellm_on_python_v2_migration_resolver: filters: *main_branches - helm_chart_testing: requires: diff --git a/CLAUDE.md b/CLAUDE.md index 6af8390b1af..d9e9e8f1586 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -37,7 +37,7 @@ Same applies for filing bug reports and feature requests, with .github/ISSUE_TEM If you're resolving a linear ticket, in the "## Linear ticket" section of the PR, say "Resolves LIT-1234", replacing "LIT-1234" with the actual ticket id that you're resolving. If you don't have the ticket id, don't make one up or search for it. Just leave the section blank -Never use `pytest` commands or the like as "Screenshots / Proof of Fix". We prefer curl'ing a live proxy instance running on localhost:4000 (I like to run it with `python litellm/proxy/proxy_cli.py --config litellm/proxy/dev_config.yaml --detailed_debug --reload 2>&1 | tee litellm.log`; the Admin UI dev server is `npm run dev` in `ui/litellm-dashboard`, served on port 3000) and showing both the command run and the output. Also, it should hit real LLM provider APIs, not mocks, and cost real $$$ because that is the most realistic test. The proof of fix should be exactly what the end user / customer would see / do. The run logs in PR #27703 is a prime example of how to do it (not a huge fan of using a python test script that future me and the team will have no visibility into; I prefer just curl commands or a short list of bash commands (e.g., using `for`)). If it's a UI thing, just tell me which URLs to go to (e.g., http://localhost:4000/ui/?page=logs), where to click, what fields to fill out, etc. along with the other commands to run in an ordered list, and I'll do it myself and post the screenshots after you make the PR +Never use `pytest` commands or the like as "Screenshots / Proof of Fix". We prefer curl'ing a live proxy instance running on localhost:4000 (I like to run it with `python litellm/proxy/proxy_cli.py --config litellm/proxy/dev_config.yaml --detailed_debug --reload --use_v2_migration_resolver 2>&1 | tee litellm.log`; the Admin UI dev server is `npm run dev` in `ui/litellm-dashboard`, served on port 3000) and showing both the command run and the output. Also, it should hit real LLM provider APIs, not mocks, and cost real $$$ because that is the most realistic test. The proof of fix should be exactly what the end user / customer would see / do. The run logs in PR #27703 is a prime example of how to do it (not a huge fan of using a python test script that future me and the team will have no visibility into; I prefer just curl commands or a short list of bash commands (e.g., using `for`)). If it's a UI thing, just tell me which URLs to go to (e.g., http://localhost:4000/ui/?page=logs), where to click, what fields to fill out, etc. along with the other commands to run in an ordered list, and I'll do it myself and post the screenshots after you make the PR If you ever write any human-facing text (pull requests, issues, commit messages, discussion posts, github comments, release notes, docs, etc.), always follow these guidelines to sound less AI-y: - don't use emojis diff --git a/litellm-proxy-extras/litellm_proxy_extras/utils.py b/litellm-proxy-extras/litellm_proxy_extras/utils.py index c088609dad7..b8032dd0d28 100644 --- a/litellm-proxy-extras/litellm_proxy_extras/utils.py +++ b/litellm-proxy-extras/litellm_proxy_extras/utils.py @@ -7,8 +7,7 @@ import subprocess import tempfile import time from pathlib import Path -from types import MappingProxyType -from typing import Final, Optional +from typing import Optional from litellm_proxy_extras._logging import logger from litellm_proxy_extras.replica_identity import ( @@ -51,17 +50,6 @@ _SPEND_LOGS_PK_CLAUSE_RE = re.compile( re.IGNORECASE, ) -_PRISMA_ATTEMPTS: Final = 4 - -_TRANSIENT_PRISMA_FAILURES: Final = MappingProxyType( - { - "deadlock detected": "a deadlock on the migration advisory lock (a concurrent migrate deploy)", - "P1001": "an unreachable database server", - "P1002": "a database server that timed out", - } -) - - PARTITIONED_SPEND_LOGS_PUSH_ERROR = ( "LiteLLM_SpendLogs is a partitioned table (see db_scripts/partition_spend_logs.sql), " "so its primary key must include the partition key (\"startTime\"). `prisma db push` " @@ -286,23 +274,6 @@ class ProxyExtrasDBManager: env=prisma_env, ) - @staticmethod - def _transient_prisma_failure(stderr: str) -> str | None: - """Why a failed prisma command is worth retrying, or None. - - v1 retried every failure, so it absorbed a database that was not up yet - or another instance holding the migration lock. v2 fails fast, which is - right for a broken migration and wrong for these. - """ - return next( - ( - reason - for marker, reason in _TRANSIENT_PRISMA_FAILURES.items() - if marker in stderr - ), - None, - ) - @staticmethod def _is_permission_error(error_message: str) -> bool: """ @@ -684,7 +655,7 @@ class ProxyExtrasDBManager: @staticmethod def _setup_database_v2(use_migrate: bool) -> bool: """ - v2 migration resolver (what the proxy CLI selects by default). + v2 migration resolver (opt-in via --use_v2_migration_resolver). Runs `prisma migrate deploy` and handles standard recovery paths (P3005 baseline, P3009/P3018 idempotent errors). Critically, it does @@ -705,46 +676,20 @@ class ProxyExtrasDBManager: original_dir = os.getcwd() os.chdir(migrations_dir) try: - for attempt in range(_PRISMA_ATTEMPTS): - try: - subprocess.run( - [_get_prisma_command(), "db", "push", "--accept-data-loss"], - timeout=prisma_command_timeout(), - check=True, - capture_output=True, - text=True, - env=_get_prisma_env(), - ) - return True - except subprocess.TimeoutExpired: - logger.info( - "prisma db push attempt %s timed out, retrying", - attempt + 1, - ) - time.sleep(random.randrange(5, 15)) - except subprocess.CalledProcessError as e: - stderr = e.stderr or "" - transient = ProxyExtrasDBManager._transient_prisma_failure( - stderr - ) - # Re-raise as RuntimeError so proxy_cli.py's - # `except RuntimeError` catches it and exits cleanly. - if transient is None or attempt == _PRISMA_ATTEMPTS - 1: - raise RuntimeError( - f"prisma db push failed.\n\nDetail: {e}" - f"\n\nPrisma error:\n{stderr}" - ) from e - logger.info( - "prisma db push attempt %s failed on %s, retrying. " - "Prisma error:\n%s", - attempt + 1, - transient, - stderr, - ) - time.sleep(random.randrange(5, 15)) - raise RuntimeError( - f"prisma db push failed after {_PRISMA_ATTEMPTS} attempts." + subprocess.run( + [_get_prisma_command(), "db", "push", "--accept-data-loss"], + timeout=prisma_command_timeout(), + check=True, + env=_get_prisma_env(), ) + return True + except ( + subprocess.CalledProcessError, + subprocess.TimeoutExpired, + ) as e: + # Re-raise as RuntimeError so proxy_cli.py's + # `except RuntimeError` catches it and exits cleanly. + raise RuntimeError(f"prisma db push failed.\n\nDetail: {e}") from e finally: os.chdir(original_dir) @@ -754,7 +699,7 @@ class ProxyExtrasDBManager: original_dir = os.getcwd() os.chdir(migrations_dir) try: - for attempt in range(_PRISMA_ATTEMPTS): + for attempt in range(4): try: result = subprocess.run( [_get_prisma_command(), "migrate", "deploy"], @@ -869,36 +814,16 @@ class ProxyExtrasDBManager: f"Manual intervention required.\n\nPrisma error:\n{stderr}" ) from e - transient = ProxyExtrasDBManager._transient_prisma_failure(stderr) - if transient is None: - raise RuntimeError( - "Database migration failed and cannot be auto-recovered. " - f"Manual intervention required.\n\nPrisma error:\n{stderr}" - ) from e - - if attempt == _PRISMA_ATTEMPTS - 1: - raise RuntimeError( - f"Database migration failed after " - f"{_PRISMA_ATTEMPTS} attempts on {transient}. " - "Check database connectivity and load." - f"\n\nPrisma error:\n{stderr}" - ) from e - - logger.info( - "prisma migrate deploy attempt %s failed on %s, retrying. " - "Prisma error:\n%s", - attempt + 1, - transient, - stderr, - ) - time.sleep(random.randrange(5, 15)) - continue + raise RuntimeError( + "Database migration failed and cannot be auto-recovered. " + f"Manual intervention required.\n\nPrisma error:\n{stderr}" + ) from e raise RuntimeError( - f"Database migration failed after {_PRISMA_ATTEMPTS} " - "attempts (retry loop exhausted by timeouts or repeated " - "idempotent-recovery continues). Check database connectivity, " - "load, and _prisma_migrations ledger state." + "Database migration failed after 4 attempts (retry loop " + "exhausted by timeouts or repeated idempotent-recovery " + "continues). Check database connectivity, load, and " + "_prisma_migrations ledger state." ) finally: os.chdir(original_dir) @@ -946,11 +871,10 @@ class ProxyExtrasDBManager: Args: use_migrate: Whether to use prisma migrate instead of db push - use_v2_resolver: Run the v2 migration resolver (safer during + use_v2_resolver: Opt into the v2 migration resolver (safer during rolling deploys; does not run the diff-and-force recovery - that causes schema thrashing). Defaults to False here so - direct callers keep the old behavior; the proxy CLI passes - True, so the proxy's runtime default is v2. + that causes schema thrashing). Defaults to False for + backwards compatibility. Returns: bool: True if setup was successful, False otherwise @@ -968,7 +892,7 @@ class ProxyExtrasDBManager: @staticmethod def _run_migrations(use_migrate: bool, use_v2_resolver: bool) -> bool: if use_v2_resolver: - logger.info("Using v2 migration resolver") + logger.info("Using v2 migration resolver (--use_v2_migration_resolver)") return ProxyExtrasDBManager._setup_database_v2(use_migrate=use_migrate) schema_path = ProxyExtrasDBManager._get_prisma_dir() + "/schema.prisma" diff --git a/litellm-proxy-extras/tests/__init__.py b/litellm-proxy-extras/tests/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/litellm-proxy-extras/tests/test_setup_database_fail_fast.py b/litellm-proxy-extras/tests/test_setup_database_fail_fast.py new file mode 100644 index 00000000000..8d66bf872de --- /dev/null +++ b/litellm-proxy-extras/tests/test_setup_database_fail_fast.py @@ -0,0 +1,242 @@ +"""Regression tests for ProxyExtrasDBManager v2 migration resolver. + +The v2 resolver is opt-in via `--use_v2_migration_resolver` / the +`use_v2_resolver=True` kwarg. These tests exercise the v2 path; the v1 +(default) behavior is unchanged from pre-fix. +""" + +import subprocess +from unittest.mock import patch + +import pytest + +from litellm_proxy_extras.utils import ( + ProxyExtrasDBManager, + _max_migration_timestamp, + _migration_timestamp, +) + + +def _fake_migrate_deploy_failure(returncode: int, stderr: str): + def _run(*args, **kwargs): + raise subprocess.CalledProcessError( + returncode=returncode, + cmd=args[0], + stderr=stderr, + output="", + ) + + return _run + + +def test_v2_p3018_permission_error_raises_runtime_error(monkeypatch, tmp_path): + """v2: a permission failure during migrate deploy raises RuntimeError.""" + monkeypatch.setenv("DATABASE_URL", "postgresql://u:p@localhost:9/x") + monkeypatch.setattr( + ProxyExtrasDBManager, "_warn_if_db_ahead_of_head", lambda _: None + ) + monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) + (tmp_path / "schema.prisma").write_text("// stub") + + stderr = ( + "Error: P3018\nMigration name: 20250326162113_baseline\n" + "Database error code: 42501\npermission denied for schema public" + ) + with patch("subprocess.run", side_effect=_fake_migrate_deploy_failure(1, stderr)): + with pytest.raises(RuntimeError, match="permission"): + ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) + + +def test_v2_non_idempotent_p3009_raises_runtime_error(monkeypatch, tmp_path): + """v2: a non-idempotent migration failure raises (no silent recovery).""" + monkeypatch.setenv("DATABASE_URL", "postgresql://u:p@localhost:9/x") + monkeypatch.setattr( + ProxyExtrasDBManager, "_warn_if_db_ahead_of_head", lambda _: None + ) + monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) + (tmp_path / "schema.prisma").write_text("// stub") + + stderr = ( + "Error: P3009\nMigration `20260101000000_genuinely_broken` failed\n" + 'Reason: syntax error at or near "BRKN" LINE 42' + ) + with patch("subprocess.run", side_effect=_fake_migrate_deploy_failure(1, stderr)): + with pytest.raises(RuntimeError, match="cannot be auto-recovered"): + ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) + + +def test_strip_prisma_query_params_removes_connection_limit(): + """DATABASE_URLs with Prisma-specific params should be parseable by psycopg.""" + url = "postgresql://u:p@h:5432/db?connection_limit=100&pool_timeout=60&sslmode=require" + stripped = ProxyExtrasDBManager._strip_prisma_query_params(url) + assert "connection_limit" not in stripped + assert "pool_timeout" not in stripped + assert "sslmode=require" in stripped + + +def test_strip_prisma_query_params_passthrough_no_query(): + """URLs without query strings are returned unchanged.""" + url = "postgresql://u:p@h:5432/db" + assert ProxyExtrasDBManager._strip_prisma_query_params(url) == url + + +def test_migration_timestamp_extracts_leading_digits(): + assert _migration_timestamp("20260101000000_add_foo") == 20260101000000 + assert _migration_timestamp("20250326162113_baseline") == 20250326162113 + + +def test_migration_timestamp_returns_zero_on_malformed(): + assert _migration_timestamp("0_init") == 0 + assert _migration_timestamp("not_a_migration") == 0 + + +def test_max_migration_timestamp(): + names = {"20250326000000_a", "20260415000000_b", "20251115000000_c"} + assert _max_migration_timestamp(names) == 20260415000000 + + +def test_max_migration_timestamp_empty_set(): + assert _max_migration_timestamp(set()) == 0 + + +def test_v1_default_still_calls_resolve_all_migrations(monkeypatch, tmp_path): + """v1 (default) continues to call _resolve_all_migrations on the happy path. + + This is the existing buggy behavior — we're not fixing it in v1, only + offering v2 as opt-in. This test pins the default so that a future + inadvertent default flip is caught. + """ + monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) + (tmp_path / "schema.prisma").write_text("// stub") + + # Stub `prisma migrate deploy` to claim success with pending migrations + # applied, which is the code path that triggers the legacy post-migration + # sanity check (a call to _resolve_all_migrations). + class FakeResult: + stdout = "Applied migration.\n" + stderr = "" + + def fake_run(cmd, *args, **kwargs): + return FakeResult() + + resolve_called = {"n": 0} + + def fake_resolve(*args, **kwargs): + resolve_called["n"] += 1 + + monkeypatch.setattr("subprocess.run", fake_run) + monkeypatch.setattr(ProxyExtrasDBManager, "_resolve_all_migrations", fake_resolve) + + ok = ProxyExtrasDBManager.setup_database(use_migrate=True) # v2 flag NOT set + assert ok is True + assert resolve_called["n"] == 1, "v1 default should still invoke the legacy path" + + +def test_v2_db_push_wraps_subprocess_error_as_runtime_error(monkeypatch, tmp_path): + """v2: a failing `prisma db push` must raise RuntimeError, not leak + CalledProcessError past proxy_cli.py's `except RuntimeError`.""" + monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) + (tmp_path / "schema.prisma").write_text("// stub") + + stderr = "db push error" + with patch("subprocess.run", side_effect=_fake_migrate_deploy_failure(1, stderr)): + with pytest.raises(RuntimeError, match="prisma db push failed"): + ProxyExtrasDBManager.setup_database(use_migrate=False, use_v2_resolver=True) + + +def test_v2_warn_ahead_of_head_swallows_db_errors(monkeypatch, tmp_path): + """_warn_if_db_ahead_of_head must never raise — it's informational. + + Non-connection DB errors (e.g. InsufficientPrivilege from a user + without SELECT on _prisma_migrations) must be caught, not propagated. + """ + import psycopg + + monkeypatch.setenv("DATABASE_URL", "postgresql://u:p@localhost:9/x") + monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) + (tmp_path / "schema.prisma").write_text("// stub") + + class _FakeConn: + def __enter__(self): + return self + + def __exit__(self, *a): + return False + + def execute(self, *a, **kw): + # Simulate an InsufficientPrivilege (subclass of DatabaseError). + raise psycopg.errors.InsufficientPrivilege("permission denied") + + def _fake_connect(*a, **kw): + return _FakeConn() + + monkeypatch.setattr("psycopg.connect", _fake_connect) + + # Must not raise. + ProxyExtrasDBManager._warn_if_db_ahead_of_head(str(tmp_path)) + + +def test_v2_resolve_specific_migration_failure_raises_runtime_error( + monkeypatch, tmp_path +): + """If marking a migration as applied fails inside P3009 idempotent + recovery, the subprocess error must be re-raised as RuntimeError so + proxy_cli.py catches it cleanly (instead of leaking CalledProcessError).""" + monkeypatch.setattr( + ProxyExtrasDBManager, "_warn_if_db_ahead_of_head", lambda _: None + ) + monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) + (tmp_path / "schema.prisma").write_text("// stub") + monkeypatch.setattr( + ProxyExtrasDBManager, "_roll_back_migration", lambda *a, **kw: None + ) + + # First call: migrate deploy -> P3009 idempotent error. + # Recovery path tries _resolve_specific_migration; that also raises. + def _failing_resolve(*a, **kw): + raise subprocess.CalledProcessError( + returncode=1, + cmd="prisma migrate resolve --applied", + stderr="resolve failed", + output="", + ) + + monkeypatch.setattr( + ProxyExtrasDBManager, "_resolve_specific_migration", _failing_resolve + ) + + stderr = ( + "Error: P3009\nMigration `20260101000000_some_migration` failed\n" + "relation already exists" + ) + with patch("subprocess.run", side_effect=_fake_migrate_deploy_failure(1, stderr)): + with pytest.raises( + RuntimeError, match="Failed to mark migration .* as applied" + ): + ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) + + +def test_v2_does_not_call_resolve_all_migrations(monkeypatch, tmp_path): + """v2 must never call _resolve_all_migrations — that's the bug it fixes.""" + monkeypatch.setattr( + ProxyExtrasDBManager, "_warn_if_db_ahead_of_head", lambda _: None + ) + monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) + (tmp_path / "schema.prisma").write_text("// stub") + + class FakeResult: + stdout = "Applied migration.\n" + stderr = "" + + monkeypatch.setattr("subprocess.run", lambda *a, **kw: FakeResult()) + + resolve_called = {"n": 0} + monkeypatch.setattr( + ProxyExtrasDBManager, + "_resolve_all_migrations", + lambda *a, **kw: resolve_called.__setitem__("n", resolve_called["n"] + 1), + ) + + ok = ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) + assert ok is True + assert resolve_called["n"] == 0, "v2 must not invoke the diff-and-force recovery" diff --git a/litellm/proxy/proxy_cli.py b/litellm/proxy/proxy_cli.py index 86f6853a625..8ac63ba25c9 100644 --- a/litellm/proxy/proxy_cli.py +++ b/litellm/proxy/proxy_cli.py @@ -913,14 +913,13 @@ class ProxyInitializationHelpers: envvar="ENFORCE_PRISMA_MIGRATION_CHECK", ) @click.option( - "--use_v2_migration_resolver/--use_legacy_migration_resolver", - default=True, + "--use_v2_migration_resolver", + is_flag=True, + default=False, help=( - "Which database migration resolver to run at startup. The default v2 " - "resolver avoids the diff-and-force recovery path that can cause schema " - "thrashing during rolling deploys where two LiteLLM versions contend for " - "the same DB. Pass --use_legacy_migration_resolver, or set " - "USE_V2_MIGRATION_RESOLVER=false, to fall back to v1." + "Opt into the v2 migration resolver. Avoids the diff-and-force recovery " + "path that can cause schema thrashing during rolling deploys where two " + "LiteLLM versions contend for the same DB. Default is the v1 resolver." ), envvar="USE_V2_MIGRATION_RESOLVER", ) @@ -1311,11 +1310,10 @@ def run_server( else: if not use_v2_migration_resolver: print( - "\033[1;33mLiteLLM Proxy: Using the legacy (v1) migration resolver. " - "The default v2 resolver is safer: it avoids the diff-and-force " - "recovery that caused schema thrashing during rolling deploys. " - "Remove --use_legacy_migration_resolver / " - "USE_V2_MIGRATION_RESOLVER=false to switch back to it.\033[0m" + "\033[1;33mLiteLLM Proxy: Using default (v1) migration resolver. " + "If your deployment has seen schema thrashing during rolling " + "deploys, try --use_v2_migration_resolver (safer: avoids the " + "diff-and-force recovery that caused the thrash).\033[0m" ) try: setup_ok: Final = PrismaManager.setup_database( @@ -1323,10 +1321,10 @@ def run_server( use_v2_resolver=use_v2_migration_resolver, ) except RuntimeError as e: - # Raised on unrecoverable migration errors: permission - # failures from either resolver, the v2 resolver's - # non-idempotent failures, and any `prisma db push` - # against a partitioned LiteLLM_SpendLogs. + # Raised on unrecoverable migration errors: the v2 + # resolver's non-idempotent failures and permission + # issues, and any `prisma db push` against a + # partitioned LiteLLM_SpendLogs. print( f"\033[1;31mLiteLLM Proxy: Database migration cannot proceed. {e}\033[0m", file=sys.stderr, diff --git a/tests/litellm-proxy-extras/test_setup_database_fail_fast.py b/tests/litellm-proxy-extras/test_setup_database_fail_fast.py deleted file mode 100644 index ef447315a8c..00000000000 --- a/tests/litellm-proxy-extras/test_setup_database_fail_fast.py +++ /dev/null @@ -1,571 +0,0 @@ -"""Regression tests for ProxyExtrasDBManager's v2 migration resolver. - -v2 is the proxy CLI default; v1 stays reachable via the `use_v2_resolver` -kwarg, which still defaults to False for direct callers. -""" - -import subprocess -from unittest.mock import patch - -import pytest - -from litellm_proxy_extras.utils import ( - _PRISMA_ATTEMPTS, - ProxyExtrasDBManager, - _max_migration_timestamp, - _migration_timestamp, -) - - -def _fake_migrate_deploy_failure(returncode: int, stderr: str): - def _run(*args, **kwargs): - raise subprocess.CalledProcessError( - returncode=returncode, - cmd=args[0], - stderr=stderr, - output="", - ) - - return _run - - -def test_v2_p3018_permission_error_raises_runtime_error(monkeypatch, tmp_path): - """v2: a permission failure during migrate deploy raises RuntimeError.""" - monkeypatch.setenv("DATABASE_URL", "postgresql://u:p@localhost:9/x") - monkeypatch.setattr( - ProxyExtrasDBManager, "_warn_if_db_ahead_of_head", lambda _: None - ) - monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) - (tmp_path / "schema.prisma").write_text("// stub") - - stderr = ( - "Error: P3018\nMigration name: 20250326162113_baseline\n" - "Database error code: 42501\npermission denied for schema public" - ) - with patch("subprocess.run", side_effect=_fake_migrate_deploy_failure(1, stderr)): - with pytest.raises(RuntimeError, match="permission"): - ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) - - -def test_v2_non_idempotent_p3009_raises_runtime_error(monkeypatch, tmp_path): - """v2: a non-idempotent migration failure raises (no silent recovery).""" - monkeypatch.setenv("DATABASE_URL", "postgresql://u:p@localhost:9/x") - monkeypatch.setattr( - ProxyExtrasDBManager, "_warn_if_db_ahead_of_head", lambda _: None - ) - monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) - (tmp_path / "schema.prisma").write_text("// stub") - - stderr = ( - "Error: P3009\nMigration `20260101000000_genuinely_broken` failed\n" - 'Reason: syntax error at or near "BRKN" LINE 42' - ) - with patch("subprocess.run", side_effect=_fake_migrate_deploy_failure(1, stderr)): - with pytest.raises(RuntimeError, match="cannot be auto-recovered"): - ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) - - -def test_strip_prisma_query_params_removes_connection_limit(): - """DATABASE_URLs with Prisma-specific params should be parseable by psycopg.""" - url = "postgresql://u:p@h:5432/db?connection_limit=100&pool_timeout=60&sslmode=require" - stripped = ProxyExtrasDBManager._strip_prisma_query_params(url) - assert "connection_limit" not in stripped - assert "pool_timeout" not in stripped - assert "sslmode=require" in stripped - - -def test_strip_prisma_query_params_passthrough_no_query(): - """URLs without query strings are returned unchanged.""" - url = "postgresql://u:p@h:5432/db" - assert ProxyExtrasDBManager._strip_prisma_query_params(url) == url - - -def test_migration_timestamp_extracts_leading_digits(): - assert _migration_timestamp("20260101000000_add_foo") == 20260101000000 - assert _migration_timestamp("20250326162113_baseline") == 20250326162113 - - -def test_migration_timestamp_returns_zero_on_malformed(): - assert _migration_timestamp("0_init") == 0 - assert _migration_timestamp("not_a_migration") == 0 - - -def test_max_migration_timestamp(): - names = {"20250326000000_a", "20260415000000_b", "20251115000000_c"} - assert _max_migration_timestamp(names) == 20260415000000 - - -def test_max_migration_timestamp_empty_set(): - assert _max_migration_timestamp(set()) == 0 - - -def test_v1_default_still_calls_resolve_all_migrations(monkeypatch, tmp_path): - """v1 (default) continues to call _resolve_all_migrations on the happy path. - - This is the existing buggy behavior — we're not fixing it in v1, only - offering v2 as opt-in. This test pins the default so that a future - inadvertent default flip is caught. - """ - monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) - (tmp_path / "schema.prisma").write_text("// stub") - - # Stub `prisma migrate deploy` to claim success with pending migrations - # applied, which is the code path that triggers the legacy post-migration - # sanity check (a call to _resolve_all_migrations). - class FakeResult: - stdout = "Applied migration.\n" - stderr = "" - - def fake_run(cmd, *args, **kwargs): - return FakeResult() - - resolve_called = {"n": 0} - - def fake_resolve(*args, **kwargs): - resolve_called["n"] += 1 - - monkeypatch.setattr("subprocess.run", fake_run) - monkeypatch.setattr(ProxyExtrasDBManager, "_resolve_all_migrations", fake_resolve) - - ok = ProxyExtrasDBManager.setup_database(use_migrate=True) # v2 flag NOT set - assert ok is True - assert resolve_called["n"] == 1, "v1 default should still invoke the legacy path" - - -def test_v2_db_push_wraps_subprocess_error_as_runtime_error(monkeypatch, tmp_path): - """v2: a failing `prisma db push` must raise RuntimeError, not leak - CalledProcessError past proxy_cli.py's `except RuntimeError`.""" - monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) - (tmp_path / "schema.prisma").write_text("// stub") - - stderr = "db push error" - with patch("subprocess.run", side_effect=_fake_migrate_deploy_failure(1, stderr)): - with pytest.raises(RuntimeError, match="prisma db push failed"): - ProxyExtrasDBManager.setup_database(use_migrate=False, use_v2_resolver=True) - - -def test_v2_warn_ahead_of_head_swallows_db_errors(monkeypatch, tmp_path): - """_warn_if_db_ahead_of_head must never raise — it's informational. - - Non-connection DB errors (e.g. InsufficientPrivilege from a user - without SELECT on _prisma_migrations) must be caught, not propagated. - """ - import psycopg - - monkeypatch.setenv("DATABASE_URL", "postgresql://u:p@localhost:9/x") - monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) - (tmp_path / "schema.prisma").write_text("// stub") - - class _FakeConn: - def __enter__(self): - return self - - def __exit__(self, *a): - return False - - def execute(self, *a, **kw): - # Simulate an InsufficientPrivilege (subclass of DatabaseError). - raise psycopg.errors.InsufficientPrivilege("permission denied") - - connects = {"n": 0} - - def _fake_connect(*a, **kw): - connects["n"] += 1 - return _FakeConn() - - monkeypatch.setattr("psycopg.connect", _fake_connect) - - assert ProxyExtrasDBManager._warn_if_db_ahead_of_head(str(tmp_path)) is None - assert connects["n"] == 1, "the failing query must actually have been reached" - - -def test_v2_resolve_specific_migration_failure_raises_runtime_error( - monkeypatch, tmp_path -): - """If marking a migration as applied fails inside P3009 idempotent - recovery, the subprocess error must be re-raised as RuntimeError so - proxy_cli.py catches it cleanly (instead of leaking CalledProcessError).""" - monkeypatch.setattr( - ProxyExtrasDBManager, "_warn_if_db_ahead_of_head", lambda _: None - ) - monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) - (tmp_path / "schema.prisma").write_text("// stub") - monkeypatch.setattr( - ProxyExtrasDBManager, "_roll_back_migration", lambda *a, **kw: None - ) - - # First call: migrate deploy -> P3009 idempotent error. - # Recovery path tries _resolve_specific_migration; that also raises. - def _failing_resolve(*a, **kw): - raise subprocess.CalledProcessError( - returncode=1, - cmd="prisma migrate resolve --applied", - stderr="resolve failed", - output="", - ) - - monkeypatch.setattr( - ProxyExtrasDBManager, "_resolve_specific_migration", _failing_resolve - ) - - stderr = ( - "Error: P3009\nMigration `20260101000000_some_migration` failed\n" - "relation already exists" - ) - with patch("subprocess.run", side_effect=_fake_migrate_deploy_failure(1, stderr)): - with pytest.raises( - RuntimeError, match=r"Failed to mark migration .* as applied" - ): - ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) - - -def test_v2_does_not_call_resolve_all_migrations(monkeypatch, tmp_path): - """v2 must never call _resolve_all_migrations — that's the bug it fixes.""" - monkeypatch.setattr( - ProxyExtrasDBManager, "_warn_if_db_ahead_of_head", lambda _: None - ) - monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) - (tmp_path / "schema.prisma").write_text("// stub") - - class FakeResult: - stdout = "Applied migration.\n" - stderr = "" - - monkeypatch.setattr("subprocess.run", lambda *a, **kw: FakeResult()) - - resolve_called = {"n": 0} - monkeypatch.setattr( - ProxyExtrasDBManager, - "_resolve_all_migrations", - lambda *a, **kw: resolve_called.__setitem__("n", resolve_called["n"] + 1), - ) - - ok = ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) - assert ok is True - assert resolve_called["n"] == 0, "v2 must not invoke the diff-and-force recovery" - - -_DEADLOCK_STDERR = ( - "Error: ERROR: deadlock detected\n" - "DETAIL: Process 277 waits for ExclusiveLock on advisory lock " - "[17556,0,72707369,1]; blocked by process 278.\n" - "Process 278 waits for ShareLock on virtual transaction 3/1041; " - "blocked by process 277." -) - - -class _DeployApplied: - stdout = "All migrations have been successfully applied." - stderr = "" - returncode = 0 - - -def _deploy_only(deploy_side_effect): - """subprocess.run stand-in that only intercepts `prisma migrate deploy`. - - Scoped by argv so the Prisma toolchain check cannot consume the mock first. - """ - deploys = {"n": 0} - - def _run(*args, **kwargs): - cmd = args[0] if args else kwargs.get("args", []) - if list(cmd)[-2:] == ["migrate", "deploy"]: - deploys["n"] += 1 - return deploy_side_effect(deploys["n"], cmd) - return _DeployApplied() - - return _run, deploys - - -def _prepare_v2_resolver(monkeypatch, tmp_path): - monkeypatch.setenv("DATABASE_URL", "postgresql://u:p@localhost:9/x") - monkeypatch.setattr( - ProxyExtrasDBManager, "_warn_if_db_ahead_of_head", lambda _: None - ) - monkeypatch.setattr(ProxyExtrasDBManager, "_get_prisma_dir", lambda: str(tmp_path)) - (tmp_path / "schema.prisma").write_text("// stub") - monkeypatch.setattr("time.sleep", lambda *_a, **_k: None) - - -def test_v2_retries_transient_advisory_lock_deadlock(monkeypatch, tmp_path): - """v2: replicas racing `migrate deploy` deadlock on Prisma's advisory - lock, which is transient and must be retried rather than kill the boot.""" - _prepare_v2_resolver(monkeypatch, tmp_path) - - def _side_effect(n, cmd): - if n == 1: - raise subprocess.CalledProcessError( - returncode=1, cmd=cmd, stderr=_DEADLOCK_STDERR, output="" - ) - return _DeployApplied() - - run, deploys = _deploy_only(_side_effect) - with patch("subprocess.run", side_effect=run): - ok = ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) - - assert ok is True - assert deploys["n"] == 2, "the deadlocked deploy must be retried, not raised" - - -def test_v2_persistent_advisory_lock_deadlock_eventually_raises(monkeypatch, tmp_path): - """v2: the deadlock retry is bounded, so a deadlock that never clears - still raises instead of looping or reporting success.""" - _prepare_v2_resolver(monkeypatch, tmp_path) - - def _side_effect(n, cmd): - raise subprocess.CalledProcessError( - returncode=1, cmd=cmd, stderr=_DEADLOCK_STDERR, output="" - ) - - run, deploys = _deploy_only(_side_effect) - with patch("subprocess.run", side_effect=run): - with pytest.raises(RuntimeError, match="after 4 attempts"): - ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) - - assert deploys["n"] == 4 - - -@pytest.mark.parametrize( - "stderr", - [ - "Error: P1001: Can't reach database server at `db`:`5432`", - "Error: P1002: The database server was reached but timed out.", - ], -) -def test_v2_retries_transient_database_connectivity_errors(monkeypatch, tmp_path, stderr): - """v2: a database not accepting connections yet is retried, not fatal.""" - _prepare_v2_resolver(monkeypatch, tmp_path) - - def _side_effect(n, cmd): - if n == 1: - raise subprocess.CalledProcessError( - returncode=1, cmd=cmd, stderr=stderr, output="" - ) - return _DeployApplied() - - run, deploys = _deploy_only(_side_effect) - with patch("subprocess.run", side_effect=run): - ok = ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) - - assert ok is True - assert deploys["n"] == 2, "an unreachable database must be retried, not raised" - - -def test_v2_unreachable_database_still_fails_after_the_retries(monkeypatch, tmp_path): - """v2: a genuinely unreachable database still raises once the attempts - are spent, rather than passing as a successful migration.""" - _prepare_v2_resolver(monkeypatch, tmp_path) - - def _side_effect(n, cmd): - raise subprocess.CalledProcessError( - returncode=1, - cmd=cmd, - stderr="Error: P1001: Can't reach database server at `db`:`5432`", - output="", - ) - - run, deploys = _deploy_only(_side_effect) - with patch("subprocess.run", side_effect=run): - with pytest.raises(RuntimeError, match="after 4 attempts"): - ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) - - assert deploys["n"] == 4 - - -def test_v2_exhausted_retries_report_the_prisma_error(monkeypatch, tmp_path, caplog): - """v2: retrying must not swallow Prisma's stderr, which is captured and is - the only place the cause appears for an operator or a boot-log grep.""" - _prepare_v2_resolver(monkeypatch, tmp_path) - stderr = "Error: P1001: Can't reach database server at `wrong`:`5432`" - - def _side_effect(n, cmd): - raise subprocess.CalledProcessError( - returncode=1, cmd=cmd, stderr=stderr, output="" - ) - - run, _ = _deploy_only(_side_effect) - with caplog.at_level("INFO", logger="litellm_proxy_extras"): - with patch("subprocess.run", side_effect=run): - with pytest.raises(RuntimeError) as exc_info: - ProxyExtrasDBManager.setup_database( - use_migrate=True, use_v2_resolver=True - ) - - assert "P1001" in str(exc_info.value) - assert "P1001" in caplog.text - - -def test_v2_db_push_retries_transient_failures(monkeypatch, tmp_path): - """v2: `prisma db push` retries a transient failure like v1 did. - - Reached from the migrations Job (USE_PRISMA_DB_PUSH=true), not from the - proxy CLI, whose --use_prisma_db_push has its own loop in prisma_client. - """ - _prepare_v2_resolver(monkeypatch, tmp_path) - - pushes = {"n": 0} - - def _run(*args, **kwargs): - cmd = list(args[0] if args else kwargs.get("args", [])) - if cmd[-3:] != ["db", "push", "--accept-data-loss"]: - return _DeployApplied() - pushes["n"] += 1 - if pushes["n"] == 1: - raise subprocess.CalledProcessError( - returncode=1, - cmd=cmd, - stderr="Error: P1001: Can't reach database server at `db`:`5432`", - output="", - ) - return _DeployApplied() - - monkeypatch.setattr( - ProxyExtrasDBManager, "spend_logs_is_partitioned", lambda: False - ) - with patch("subprocess.run", side_effect=_run): - ok = ProxyExtrasDBManager.setup_database(use_migrate=False, use_v2_resolver=True) - - assert ok is True - assert pushes["n"] == 2 - - -def test_v2_db_push_retries_are_bounded_and_report_the_prisma_error( - monkeypatch, tmp_path -): - """v2: a database that never comes back stops after _PRISMA_ATTEMPTS and - surfaces the prisma error, rather than retrying the boot forever.""" - _prepare_v2_resolver(monkeypatch, tmp_path) - - pushes = {"n": 0} - - def _run(*args, **kwargs): - cmd = list(args[0] if args else kwargs.get("args", [])) - if cmd[-3:] != ["db", "push", "--accept-data-loss"]: - return _DeployApplied() - pushes["n"] += 1 - raise subprocess.CalledProcessError( - returncode=1, - cmd=cmd, - stderr="Error: P1001: Can't reach database server at `db`:`5432`", - output="", - ) - - monkeypatch.setattr( - ProxyExtrasDBManager, "spend_logs_is_partitioned", lambda: False - ) - with patch("subprocess.run", side_effect=_run): - with pytest.raises(RuntimeError) as exc: - ProxyExtrasDBManager.setup_database( - use_migrate=False, use_v2_resolver=True - ) - - assert pushes["n"] == _PRISMA_ATTEMPTS - assert "P1001" in str(exc.value) - - -def _db_push_only(push_side_effect): - """subprocess.run stand-in that only intercepts `prisma db push`.""" - pushes = {"n": 0} - - def _run(*args, **kwargs): - cmd = list(args[0] if args else kwargs.get("args", [])) - if cmd[-3:] != ["db", "push", "--accept-data-loss"]: - return _DeployApplied() - pushes["n"] += 1 - return push_side_effect(pushes["n"], cmd) - - return _run, pushes - - -def _timed_out_for_real(): - """Capture what subprocess.run really puts on a TimeoutExpired. - - Under text=True it still leaves stderr as bytes, unlike CalledProcessError, - so hardcoding a str here would test a shape production never sees. Derived - at import, before any test patches subprocess.run. - """ - try: - subprocess.run( - ["sh", "-c", "echo 'Error: P1001 unreachable' >&2; sleep 5"], - timeout=0.2, - check=True, - capture_output=True, - text=True, - ) - except subprocess.TimeoutExpired as e: - return e - raise AssertionError("the helper command was supposed to time out") - - -_TIMEOUT_TEMPLATE = _timed_out_for_real() - - -def _real_timeout_expired(cmd): - return subprocess.TimeoutExpired( - cmd=cmd, - timeout=_TIMEOUT_TEMPLATE.timeout, - output=_TIMEOUT_TEMPLATE.stdout, - stderr=_TIMEOUT_TEMPLATE.stderr, - ) - - -def test_v2_db_push_retries_a_timeout(monkeypatch, tmp_path): - """v2: a `prisma db push` that times out is retried, not turned into a - TypeError by classifying its bytes stderr as if it were text.""" - _prepare_v2_resolver(monkeypatch, tmp_path) - - def _side_effect(n, cmd): - if n == 1: - raise _real_timeout_expired(cmd) - return _DeployApplied() - - monkeypatch.setattr( - ProxyExtrasDBManager, "spend_logs_is_partitioned", lambda: False - ) - run, pushes = _db_push_only(_side_effect) - with patch("subprocess.run", side_effect=run): - ok = ProxyExtrasDBManager.setup_database(use_migrate=False, use_v2_resolver=True) - - assert ok is True - assert pushes["n"] == 2 - - -def test_v2_db_push_timeouts_are_bounded(monkeypatch, tmp_path): - """v2: a `prisma db push` that never stops timing out gives up as a - RuntimeError, which is the only exception proxy_cli.py exits cleanly on.""" - _prepare_v2_resolver(monkeypatch, tmp_path) - - def _side_effect(n, cmd): - raise _real_timeout_expired(cmd) - - monkeypatch.setattr( - ProxyExtrasDBManager, "spend_logs_is_partitioned", lambda: False - ) - run, pushes = _db_push_only(_side_effect) - with patch("subprocess.run", side_effect=run): - with pytest.raises(RuntimeError, match=r"prisma db push failed after \d+"): - ProxyExtrasDBManager.setup_database(use_migrate=False, use_v2_resolver=True) - - assert pushes["n"] == _PRISMA_ATTEMPTS - - -def test_v2_unclassified_failure_is_not_treated_as_transient(monkeypatch, tmp_path): - """v2: an unrecognised deploy failure still raises on the first attempt.""" - _prepare_v2_resolver(monkeypatch, tmp_path) - - def _side_effect(n, cmd): - raise subprocess.CalledProcessError( - returncode=1, - cmd=cmd, - stderr="Error: relation \"LiteLLM_SpendLogs\" does not exist", - output="", - ) - - run, deploys = _deploy_only(_side_effect) - with patch("subprocess.run", side_effect=run): - with pytest.raises(RuntimeError, match="cannot be auto-recovered"): - ProxyExtrasDBManager.setup_database(use_migrate=True, use_v2_resolver=True) - - assert deploys["n"] == 1 - - diff --git a/tests/local_testing/test_basic_python_version.py b/tests/local_testing/test_basic_python_version.py index 506c58d26b4..fb06ed6b69d 100644 --- a/tests/local_testing/test_basic_python_version.py +++ b/tests/local_testing/test_basic_python_version.py @@ -305,16 +305,14 @@ def _run_proxy_server_smoke_test(extra_proxy_args=None): def test_litellm_proxy_server_config_no_general_settings(): - """Exercises the default (v2) migration resolver.""" + """Exercises the default (v1) migration resolver.""" _run_proxy_server_smoke_test() -def test_litellm_proxy_server_config_no_general_settings_legacy_resolver(): - """Exercises the legacy (v1) migration resolver against a real database. +def test_litellm_proxy_server_config_no_general_settings_v2_resolver(): + """Exercises the opt-in v2 migration resolver. - v2 is the default, so the no-arg test above already covers it. This one is - the only place the v1 opt-out gets real-DB migration plus proxy-boot - coverage, and it runs in a separate CI job against its own Postgres to - avoid collisions with the default variant. + Runs in a separate CI job against a local Postgres to avoid collisions + with the v1 variant when they share a database. """ - _run_proxy_server_smoke_test(extra_proxy_args=["--use_legacy_migration_resolver"]) + _run_proxy_server_smoke_test(extra_proxy_args=["--use_v2_migration_resolver"]) diff --git a/tests/test_litellm/proxy/test_proxy_cli.py b/tests/test_litellm/proxy/test_proxy_cli.py index 5e2dd358d75..6ea6f208bb5 100644 --- a/tests/test_litellm/proxy/test_proxy_cli.py +++ b/tests/test_litellm/proxy/test_proxy_cli.py @@ -1737,8 +1737,7 @@ class TestRunServerDbSetup: mock_atexit_register, mock_subprocess_run, ): - """Which resolver and which migration mode run_server hands setup_database, - across the db push flag, the v2/legacy flag pair and USE_V2_MIGRATION_RESOLVER.""" + """Test that use_prisma_db_push flag correctly controls PrismaManager.setup_database use_migrate parameter""" from litellm.proxy.proxy_cli import run_server # Mock subprocess.run to simulate prisma being available @@ -1788,7 +1787,7 @@ class TestRunServerDbSetup: # use_prisma_db_push should be False (default), so use_migrate should be True run_server.main(["--local", "--skip_server_startup"], standalone_mode=False) mock_setup_database.assert_called_with( - use_migrate=True, use_v2_resolver=True + use_migrate=True, use_v2_resolver=False ) # Reset mocks @@ -1803,38 +1802,9 @@ class TestRunServerDbSetup: standalone_mode=False, ) mock_setup_database.assert_called_with( - use_migrate=False, use_v2_resolver=True + use_migrate=False, use_v2_resolver=False ) - for argv, env_value, expected_v2 in ( - ([], None, True), - (["--use_v2_migration_resolver"], None, True), - (["--use_legacy_migration_resolver"], None, False), - ([], "false", False), - ([], "true", True), - (["--use_v2_migration_resolver"], "false", True), - (["--use_legacy_migration_resolver"], "true", False), - ): - mock_setup_database.reset_mock() - mock_should_update_schema.reset_mock() - mock_should_update_schema.return_value = True - - resolver_env = ( - {"USE_V2_MIGRATION_RESOLVER": env_value} - if env_value is not None - else {} - ) - os.environ.pop("USE_V2_MIGRATION_RESOLVER", None) - with patch.dict(os.environ, resolver_env): - run_server.main( - ["--local", "--skip_server_startup", *argv], - standalone_mode=False, - ) - assert mock_setup_database.call_args.kwargs == { - "use_migrate": True, - "use_v2_resolver": expected_v2, - }, f"argv={argv} env={env_value}" - @patch("subprocess.run") @patch("atexit.register") @patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database") @@ -1899,7 +1869,7 @@ class TestRunServerDbSetup: ) assert exc_info.value.code == 1 mock_setup_database.assert_called_once_with( - use_migrate=True, use_v2_resolver=True + use_migrate=True, use_v2_resolver=False ) @patch("subprocess.run") @@ -2011,6 +1981,7 @@ class TestRunServerDbSetup: use_migrate=True, use_v2_resolver=True ) + # --- Module-level helpers for worker startup hook tests --- _dummy_hook_called = False