litellm/tests/unit/harness/sandbox/test_snapshot.py
ishaan-berri 0f6a06a6b9
feat: add litellm.agent() to run claude code, codex, opencode and deep agents through the ai gateway (#43885)
* feat(harness): add litellm/__init__.py

* feat(harness): add litellm/constants.py

* feat(harness): add litellm/harness/__init__.py

* feat(harness): add litellm/harness/adapters/__init__.py

* feat(harness): add litellm/harness/adapters/base.py

* feat(harness): add litellm/harness/adapters/claude_code.py

* feat(harness): add litellm/harness/adapters/codex.py

* feat(harness): add litellm/harness/adapters/opencode.py

* feat(harness): add litellm/harness/endpoint.py

* feat(harness): add litellm/harness/errors.py

* feat(harness): add litellm/harness/options.py

* feat(harness): add litellm/harness/runtime.py

* feat(harness): add litellm/harness/sandbox/__init__.py

* feat(harness): add litellm/harness/sandbox/base.py

* feat(harness): add litellm/harness/sandbox/docker.py

* feat(harness): add litellm/harness/sandbox/local.py

* feat(harness): add litellm/harness/sandbox/snapshot.py

* feat(harness): add litellm/harness/sync.py

* feat(harness): add litellm/harness/types.py

* feat(harness): add litellm/sandbox/__init__.py

* feat(harness): add README.md

* feat(harness): add tests/harness_e2e/__init__.py

* feat(harness): add tests/harness_e2e/conftest.py

* feat(harness): add tests/harness_e2e/test_harness_e2e.py

* feat(harness): add tests/test_litellm/harness/__init__.py

* feat(harness): add tests/test_litellm/harness/adapters/__init__.py

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/claude_code/api_error.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/claude_code/max_turns.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/claude_code/resume_turn.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/claude_code/structured_output.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/claude_code/success_tools.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/codex/reasoning.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/codex/structured_output.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/codex/turn_failed.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/codex/turn1_bash.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/codex/turn2_resume_apply_patch.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/opencode/api_error.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/opencode/endpoint_requests.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/opencode/readonly_denied_bash.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/opencode/turn1_write_read.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/opencode/turn2_session_skill.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/test_claude_code.py

* feat(harness): add tests/test_litellm/harness/adapters/test_codex.py

* feat(harness): add tests/test_litellm/harness/adapters/test_opencode.py

* feat(harness): add tests/test_litellm/harness/core_fakes.py

* feat(harness): add tests/test_litellm/harness/sandbox/__init__.py

* feat(harness): add tests/test_litellm/harness/sandbox/test_docker.py

* feat(harness): add tests/test_litellm/harness/sandbox/test_local.py

* feat(harness): add tests/test_litellm/harness/sandbox/test_snapshot.py

* feat(harness): add tests/test_litellm/harness/test_endpoint.py

* feat(harness): add tests/test_litellm/harness/test_init.py

* feat(harness): add tests/test_litellm/harness/test_runtime.py

* feat(harness): add tests/test_litellm/harness/test_sync.py

* feat(harness): add tests/test_litellm/harness/test_types.py

* test(harness): use word recall in stream e2e test

* refactor(harness): update litellm/__init__.py

* refactor(harness): update litellm/constants.py

* refactor(harness): update litellm/harness/__init__.py

* refactor(harness): remove litellm/harness/adapters/__init__.py

* refactor(harness): update litellm/harness/context.py

* refactor(harness): update litellm/harness/endpoint.py

* refactor(harness): update litellm/harness/handlers/__init__.py

* refactor(harness): update litellm/harness/handlers/base.py

* refactor(harness): update litellm/harness/handlers/cli_handler.py

* refactor(harness): update litellm/harness/handlers/deepagents_handler.py

* refactor(harness): update litellm/harness/runtime.py

* refactor(harness): update litellm/harness/sandbox/docker.py

* refactor(harness): update litellm/harness/sandbox/local.py

* refactor(harness): update litellm/harness/sync.py

* refactor(harness): update litellm/harness/types.py

* refactor(harness): update litellm/llms/base_llm/harness/__init__.py

* refactor(harness): update litellm/llms/base_llm/harness/transformation.py

* refactor(harness): update litellm/llms/base_llm/harness/utils.py

* refactor(harness): update litellm/llms/claude_code/__init__.py

* refactor(harness): update litellm/llms/claude_code/harness/__init__.py

* refactor(harness): update litellm/llms/claude_code/harness/transformation.py

* refactor(harness): update litellm/llms/codex/__init__.py

* refactor(harness): update litellm/llms/codex/harness/__init__.py

* refactor(harness): update litellm/llms/codex/harness/transformation.py

* refactor(harness): update litellm/llms/deepagents/__init__.py

* refactor(harness): update litellm/llms/deepagents/harness/__init__.py

* refactor(harness): update litellm/llms/deepagents/harness/sandbox_backend.py

* refactor(harness): update litellm/llms/deepagents/harness/transformation.py

* refactor(harness): update litellm/llms/opencode/__init__.py

* refactor(harness): update litellm/llms/opencode/harness/__init__.py

* refactor(harness): update litellm/llms/opencode/harness/transformation.py

* refactor(harness): update litellm/utils.py

* refactor(harness): update README.md

* refactor(harness): update tests/harness_e2e/conftest.py

* refactor(harness): update tests/harness_e2e/test_harness_e2e.py

* refactor(harness): remove tests/test_litellm/harness/__init__.py

* refactor(harness): remove tests/test_litellm/harness/adapters/__init__.py

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/claude_code/api_error.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/claude_code/max_turns.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/claude_code/resume_turn.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/claude_code/structured_output.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/claude_code/success_tools.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/codex/reasoning.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/codex/structured_output.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/codex/turn_failed.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/codex/turn1_bash.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/codex/turn2_resume_apply_patch.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/opencode/api_error.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/opencode/endpoint_requests.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/opencode/readonly_denied_bash.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/opencode/turn1_write_read.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/opencode/turn2_session_skill.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/test_claude_code.py

* refactor(harness): remove tests/test_litellm/harness/adapters/test_codex.py

* refactor(harness): remove tests/test_litellm/harness/adapters/test_opencode.py

* refactor(harness): remove tests/test_litellm/harness/core_fakes.py

* refactor(harness): remove tests/test_litellm/harness/sandbox/__init__.py

* refactor(harness): remove tests/test_litellm/harness/sandbox/test_docker.py

* refactor(harness): remove tests/test_litellm/harness/sandbox/test_local.py

* refactor(harness): remove tests/test_litellm/harness/sandbox/test_snapshot.py

* refactor(harness): remove tests/test_litellm/harness/test_endpoint.py

* refactor(harness): remove tests/test_litellm/harness/test_init.py

* refactor(harness): remove tests/test_litellm/harness/test_runtime.py

* refactor(harness): remove tests/test_litellm/harness/test_sync.py

* refactor(harness): remove tests/test_litellm/harness/test_types.py

* refactor(harness): update tests/unit/harness/__init__.py

* refactor(harness): update tests/unit/harness/core_fakes.py

* refactor(harness): update tests/unit/harness/handlers/__init__.py

* refactor(harness): update tests/unit/harness/handlers/test_deepagents_handler.py

* refactor(harness): update tests/unit/harness/sandbox/__init__.py

* refactor(harness): update tests/unit/harness/sandbox/test_docker.py

* refactor(harness): update tests/unit/harness/sandbox/test_local.py

* refactor(harness): update tests/unit/harness/sandbox/test_snapshot.py

* refactor(harness): update tests/unit/harness/test_endpoint.py

* refactor(harness): update tests/unit/harness/test_init.py

* refactor(harness): update tests/unit/harness/test_runtime.py

* refactor(harness): update tests/unit/harness/test_sync.py

* refactor(harness): update tests/unit/harness/test_types.py

* refactor(harness): update tests/unit/llms/claude_code/__init__.py

* refactor(harness): update tests/unit/llms/claude_code/harness/__init__.py

* refactor(harness): update tests/unit/llms/claude_code/harness/fixtures/api_error.jsonl

* refactor(harness): update tests/unit/llms/claude_code/harness/fixtures/max_turns.jsonl

* refactor(harness): update tests/unit/llms/claude_code/harness/fixtures/resume_turn.jsonl

* refactor(harness): update tests/unit/llms/claude_code/harness/fixtures/structured_output.jsonl

* refactor(harness): update tests/unit/llms/claude_code/harness/fixtures/success_tools.jsonl

* refactor(harness): update tests/unit/llms/claude_code/harness/test_transformation.py

* refactor(harness): update tests/unit/llms/codex/__init__.py

* refactor(harness): update tests/unit/llms/codex/harness/__init__.py

* refactor(harness): update tests/unit/llms/codex/harness/fixtures/reasoning.jsonl

* refactor(harness): update tests/unit/llms/codex/harness/fixtures/structured_output.jsonl

* refactor(harness): update tests/unit/llms/codex/harness/fixtures/turn1_bash.jsonl

* refactor(harness): update tests/unit/llms/codex/harness/fixtures/turn2_resume_apply_patch.jsonl

* refactor(harness): update tests/unit/llms/codex/harness/fixtures/turn_failed.jsonl

* refactor(harness): update tests/unit/llms/codex/harness/test_transformation.py

* refactor(harness): update tests/unit/llms/deepagents/__init__.py

* refactor(harness): update tests/unit/llms/deepagents/harness/__init__.py

* refactor(harness): update tests/unit/llms/deepagents/harness/test_transformation.py

* refactor(harness): update tests/unit/llms/opencode/__init__.py

* refactor(harness): update tests/unit/llms/opencode/harness/__init__.py

* refactor(harness): update tests/unit/llms/opencode/harness/fixtures/api_error.jsonl

* refactor(harness): update tests/unit/llms/opencode/harness/fixtures/endpoint_requests.jsonl

* refactor(harness): update tests/unit/llms/opencode/harness/fixtures/readonly_denied_bash.jsonl

* refactor(harness): update tests/unit/llms/opencode/harness/fixtures/turn1_write_read.jsonl

* refactor(harness): update tests/unit/llms/opencode/harness/fixtures/turn2_session_skill.jsonl

* refactor(harness): update tests/unit/llms/opencode/harness/test_transformation.py

* ci: allowlist tests/harness_e2e, which needs live runtimes and a gateway

* fix(harness): bound the turn event queue

* fix(harness): bound the turn event queue with backpressure

* style: sort imports in utils

* ci: exclude agent-harness config folders from provider docs check

* refactor(harness): update tests/harness_e2e/conftest.py

* refactor(harness): update tests/harness_e2e/test_harness_e2e.py

* refactor(harness): update tests/unit/harness/core_fakes.py

* refactor(harness): update tests/unit/harness/handlers/test_deepagents_handler.py

* refactor(harness): update tests/unit/harness/test_runtime.py

* refactor(harness): update tests/unit/harness/test_sync.py

* refactor(harness): update tests/unit/llms/deepagents/harness/test_transformation.py

* refactor(harness): update tests/unit/llms/opencode/harness/test_transformation.py

* refactor(harness): update litellm/harness/endpoint.py

* refactor(harness): update litellm/harness/handlers/deepagents_handler.py

* refactor(harness): update litellm/harness/options.py

* refactor(harness): update litellm/harness/runtime.py

* refactor(harness): update litellm/harness/sandbox/snapshot.py

* refactor(harness): update litellm/llms/base_llm/harness/transformation.py

* refactor(harness): update litellm/llms/base_llm/harness/utils.py

* refactor(harness): update litellm/llms/claude_code/harness/transformation.py

* refactor(harness): update litellm/llms/codex/harness/transformation.py

* refactor(harness): update litellm/llms/deepagents/harness/sandbox_backend.py

* refactor(harness): update litellm/llms/deepagents/harness/transformation.py

* refactor(harness): update litellm/llms/opencode/harness/transformation.py

* refactor(harness): update litellm/sandbox/__init__.py

* refactor(harness): update tests/unit/llms/claude_code/harness/test_transformation.py

* refactor(harness): update tests/unit/llms/deepagents/harness/test_sandbox_backend_symlinks.py

* refactor(harness): update tests/unit/llms/opencode/harness/test_transformation.py

* refactor(harness): update litellm/llms/base_llm/harness/utils.py

* refactor(harness): update litellm/llms/codex/harness/transformation.py

* refactor(harness): update tests/code_coverage_tests/recursive_detector.py

* refactor(harness): update tests/unit/llms/base_llm/harness/__init__.py

* refactor(harness): update tests/unit/llms/claude_code/harness/fixtures/__init__.py

* refactor(harness): update tests/unit/llms/codex/harness/fixtures/__init__.py

* refactor(harness): update tests/unit/llms/opencode/harness/fixtures/__init__.py

* refactor(harness): update litellm/harness/__init__.py

* refactor(harness): update litellm/harness/context.py

* refactor(harness): update litellm/harness/endpoint.py

* refactor(harness): update litellm/harness/handlers/__init__.py

* refactor(harness): update litellm/harness/handlers/base.py

* refactor(harness): update litellm/harness/handlers/cli_handler.py

* refactor(harness): update litellm/harness/handlers/deepagents_handler.py

* refactor(harness): update litellm/harness/runtime.py

* refactor(harness): update litellm/harness/sandbox/__init__.py

* refactor(harness): update litellm/harness/sandbox/base.py

* refactor(harness): update litellm/harness/sandbox/docker.py

* refactor(harness): update litellm/harness/sandbox/local.py

* refactor(harness): update litellm/harness/sandbox/snapshot.py

* refactor(harness): update litellm/harness/sync.py

* refactor(harness): update litellm/harness/types.py

* refactor(harness): update litellm/llms/base_llm/harness/transformation.py

* refactor(harness): update litellm/llms/base_llm/harness/utils.py

* refactor(harness): update litellm/llms/claude_code/harness/transformation.py

* refactor(harness): update litellm/llms/codex/harness/transformation.py

* refactor(harness): update litellm/llms/deepagents/harness/sandbox_backend.py

* refactor(harness): update litellm/llms/deepagents/harness/transformation.py

* refactor(harness): update litellm/llms/opencode/harness/transformation.py

* refactor(harness): update litellm/types/llms/custom_http.py

* refactor(harness): update tests/unit/harness/test_endpoint.py

* refactor(harness): update litellm/harness/runtime.py

* refactor(harness): update litellm/llms/deepagents/harness/sandbox_backend.py

* refactor(harness): update tests/unit/harness/test_init.py

* refactor(harness): update tests/unit/harness/test_runtime.py

* refactor(harness): update tests/unit/llms/deepagents/harness/test_sandbox_backend_symlinks.py
2026-10-01 22:27:49 +00:00

129 lines
4.3 KiB
Python

import hashlib
import os
import pytest
from litellm import sandbox
from litellm.constants import HARNESS_MAX_DIFF_BYTES
from litellm.harness.sandbox.snapshot import (
build_file_changes,
capture_text_contents,
diff_snapshots,
snapshot_local,
unified_diff,
)
from litellm.harness.types import FileChange
def test_diff_snapshots_kinds():
before = {"a": "1", "b": "2", "c": "3"}
after = {"a": "1", "b": "9", "d": "4"}
assert diff_snapshots(before, after) == [
("b", "modified"),
("c", "deleted"),
("d", "created"),
]
async def test_snapshot_local_hashes_and_skips(tmp_path):
(tmp_path / "x.txt").write_bytes(b"hello")
(tmp_path / "sub").mkdir()
(tmp_path / "sub" / "y.txt").write_bytes(b"y")
(tmp_path / "__pycache__").mkdir()
(tmp_path / "__pycache__" / "z.pyc").write_bytes(b"z")
os.symlink(tmp_path / "x.txt", tmp_path / "link.txt")
snap = await snapshot_local(str(tmp_path))
assert snap == {
"x.txt": hashlib.sha256(b"hello").hexdigest(),
"sub/y.txt": hashlib.sha256(b"y").hexdigest(),
}
def test_unified_diff_created():
diff = unified_diff("f.txt", None, "one\n")
assert diff.startswith("--- /dev/null\n+++ b/f.txt\n")
assert "+one\n" in diff
async def test_created_modified_deleted_end_to_end(tmp_path):
box = sandbox.local(tmp_path)
try:
await box.write("mod.txt", b"line1\nline2\n")
await box.write("gone.txt", b"bye\n")
await box.write("bin.dat", b"\x00\x01\x02")
before = await box.snapshot()
contents = await capture_text_contents(box, before)
assert set(contents) == {"mod.txt", "gone.txt"}
await box.write("mod.txt", b"line1\nchanged\n")
await box.write("new.txt", b"fresh\n")
await box.write("bin.dat", b"\x00\x09")
os.remove(os.path.join(box.workdir, "gone.txt"))
after = await box.snapshot()
changes = await build_file_changes(box, before, after, contents)
by_path = {c.path: c for c in changes}
assert all(isinstance(c, FileChange) for c in changes)
assert [(c.path, c.kind) for c in changes] == [
("bin.dat", "modified"),
("gone.txt", "deleted"),
("mod.txt", "modified"),
("new.txt", "created"),
]
assert by_path["bin.dat"].diff is None
assert "-line2\n" in by_path["mod.txt"].diff
assert "+changed\n" in by_path["mod.txt"].diff
assert "+fresh\n" in by_path["new.txt"].diff
assert "-bye\n" in by_path["gone.txt"].diff
finally:
await box.close()
async def test_modified_without_before_contents_has_no_diff(tmp_path):
box = sandbox.local(tmp_path)
try:
await box.write("f.txt", b"a\n")
before = await box.snapshot()
await box.write("f.txt", b"b\n")
after = await box.snapshot()
changes = await build_file_changes(box, before, after, None)
assert changes == [FileChange(path="f.txt", kind="modified", diff=None)]
finally:
await box.close()
async def test_large_text_file_has_no_diff(tmp_path):
box = sandbox.local(tmp_path)
try:
before = await box.snapshot()
await box.write("big.txt", b"a" * (HARNESS_MAX_DIFF_BYTES + 1))
after = await box.snapshot()
changes = await build_file_changes(box, before, after, {})
assert changes == [FileChange(path="big.txt", kind="created", diff=None)]
finally:
await box.close()
async def test_capture_respects_total_cap(tmp_path, monkeypatch):
monkeypatch.setattr(
"litellm.harness.sandbox.snapshot.HARNESS_SNAPSHOT_MAX_TOTAL_BYTES", 10
)
box = sandbox.local(tmp_path)
try:
await box.write("a.txt", b"x" * 8)
await box.write("b.txt", b"x" * 8)
await box.write("c.txt", b"x" * 8)
captured = await capture_text_contents(box, await box.snapshot())
assert set(captured) == {"a.txt", "b.txt"}
finally:
await box.close()
@pytest.mark.parametrize("data", [b"\xff\xfe bad utf8", b"has\x00nul"])
async def test_capture_skips_binary(tmp_path, data):
box = sandbox.local(tmp_path)
try:
await box.write("f", data)
assert await capture_text_contents(box, {"f": "h"}) == {}
finally:
await box.close()