litellm/tests/e2e/claude_code/pdf_input/test_azure.py
mubashir1osmani 3f5ed5a9c8
fix(e2e/claude_code): unblock stage collection, align proxy env names, register compat models (#33433)
* refactor(e2e/claude_code): align proxy env names with the rest of tests/e2e

Every claude_code compat cell used to read its own `LITELLM_PROXY_BASE_URL` and `LITELLM_PROXY_API_KEY` and duplicate the same 12-line "missing env, hard fail" block. The rest of `tests/e2e/` reads `LITELLM_PROXY_URL` and `LITELLM_MASTER_KEY` from `e2e_config.py`, so anyone standing up a live proxy for one suite had to export a second spelling for claude_code, and every cell repeated the same boilerplate.

Centralize the resolution in `claude_code/_env.py`. `resolve_proxy()` prefers the suite-wide `LITELLM_PROXY_URL` / `LITELLM_MASTER_KEY` names and falls back to the legacy pair so existing CI wiring on stage keeps working during the roll-out. `require_proxy(compat_result)` is the one-liner cells call to bind `(base_url, api_key)` or hard-fail with a message that names both spellings.

55 cell files, `_basic_messaging.py`, and the driver's own unit-test fixture now go through the helper. `run_compat.sh` accepts either spelling and normalizes to the primary names before invoking pytest. `cron_vm/run_daily.sh` exports the primary names when launching pytest.

`_pr_gate_unit_tests/test_env_resolution.py` pins the resolution rules so a future edit cannot silently reintroduce the drift: primary names win on tie, legacy names still resolve when primary is unset, mixed URL-primary key-legacy still resolves, empty-string exports are treated as unset, `require_proxy` names both spellings in its error message.

Net diff: 71 files, +370/-1240.

* fix(e2e): anchor claude_code Bash pin at parents[1] so container run collects

`test_bash_tool_restrictions.py` derived `REPO_ROOT = Path(__file__).resolve().parents[4]` and then joined `tests/e2e/claude_code/<feature>`. That works locally, but the stage container mounts tests/e2e/ at /app/e2e/, so parents[4] resolves to filesystem root and the `_bash_cells()` assertion looks for `/tests/e2e/claude_code/tool_use` — a path that doesn't exist. Collection interrupts before any test runs, so the entire e2e suite appears broken.

Fix: `CLAUDE_CODE_DIR = Path(__file__).resolve().parents[1]` resolves to the sibling `claude_code/` dir in either layout, and the `relative_to(REPO_ROOT)` calls become `relative_to(CLAUDE_CODE_DIR)` so test IDs and error messages read the same.

Adds `test_claude_code_dir_anchor_is_layout_independent` as a regression pin: it checks the anchor lands on a directory named `claude_code` that contains this test file, which would fail under the old parents[4] anchor when run from /app/e2e/.

* feat(e2e/claude_code): register compat deployments via /model/new from a session fixture

Every compat cell hardcodes a virtual model name like `claude-sonnet-4-6` or `claude-sonnet-4-6-bedrock-invoke` and hits the proxy expecting it to be routable. On stage those live in the deployed model_list; locally the `docker-config.yaml` under tests/e2e/ only declares one of them, so anything past haiku 400s with `Invalid model name`.

`claude_code/test_config.yaml` is the ground-truth compat matrix config the deployment already uses. `_compat_models.py` loads it, normalizes the yaml keys pydantic would silently drop (vertex_ai_* → vertex_*), and selects the subset whose provider credentials are present in the environment. An autouse session fixture in `conftest.py` POSTs each selected deployment to `/model/new`, blocks until it is servable on the data plane, and tears them all down on session exit. Skips silently when the proxy env is unset so pure-unit runs stay hermetic.

`test_compat_models.py` pins the invariants that keep this safe. Every cell-referenced name must have a yaml entry (drift check catches a cell probing a name the fixture never registered); the yaml has no unused declarations; the fixture registers exactly 15 deployments (3 tiers × 5 provider surfaces); vertex_ai_* yaml keys populate the pydantic body's vertex_* fields (they got silently dropped historically); Azure needs both AZURE_FOUNDRY_* env vars; Bedrock lifts creds from the ambient AWS chain; Vertex needs both the yaml refs AND ambient GCP credentials.

* refactor(e2e/claude_code): inject env + runner instead of monkeypatching

`require_proxy` and `_basic_messaging.run_basic_messaging_cell` now take the env mapping (and the CLI runner) as constructor-style arguments with `os.environ` and `run_claude_models_parallel` as defaults. Tests exercise the branching by passing dicts and callables directly, so `monkeypatch.setenv` and `monkeypatch.setattr(_basic_messaging, "run_claude_models_parallel", ...)` are gone from every unit test in this refactor's blast radius.

`test_env_resolution.py` drops the `monkeypatch.setenv`/`delenv` fixtures and passes `env={...}` dicts to `require_proxy`. Added a new pinned check that a successful resolution leaves `compat_result` untouched, and split the "unset env" test into three explicit shapes (empty, primary-only, legacy-only) so a regression that swaps the precedence rule can no longer hide behind a single monkeypatched fixture.

`test_basic_messaging.py` (driver) replaces the `_install_fake_runner(monkeypatch, ...)` helper with `_make_fake_runner(...)` that returns a `(callable, captured_dict)` pair the test passes in via the helper's new `runner=` kwarg. Also drops the autouse `_proxy_env` fixture in favor of a module-level `_PROXY_ENV` dict each test wires through the helper's new `env=` kwarg. Added a regression pin that a missing-env call hard-fails without ever invoking the runner (so the guard order stays correct).

`test_run_daily_pytest_scrubs_env.py` updates its pin to assert the new suite-wide env spellings (`LITELLM_PROXY_URL` / `LITELLM_MASTER_KEY`) instead of the legacy `LITELLM_PROXY_BASE_URL` / `LITELLM_PROXY_API_KEY` that `run_daily.sh` used to export.

* handwrote rules
2026-07-16 11:05:31 -07:00

130 lines
4 KiB
Python

"""pdf_input x Microsoft Foundry (Azure).
Drive the real `claude` CLI against a running LiteLLM proxy that routes
Claude requests to Microsoft Foundry's Anthropic deployments on Azure,
write a tiny valid PDF to disk, allow the built-in `Read` tool, and
ask Claude to read the PDF and report what it contains.
The (feature, provider) for this cell is inferred from the file path by
`tests/e2e/claude_code/conftest.py`:
tests/e2e/claude_code/pdf_input/test_azure.py
^^^^^^^^^ ^^^^^
feature_id provider
"""
from __future__ import annotations
import pytest
from claude_code._env import require_proxy
from claude_code.cli_driver import (
ClaudeCLIError,
failure_diagnostic,
run_claude_models_parallel,
)
AZURE_MODELS = [
"claude-haiku-4-5-azure",
"claude-sonnet-4-5-azure",
"claude-opus-4-7-azure",
]
PDF_MARKER = "PONG"
def _build_minimal_pdf(marker: str) -> bytes:
"""Return a single-page PDF whose only visible text is `marker`."""
objects = [
b"<< /Type /Catalog /Pages 2 0 R >>",
b"<< /Type /Pages /Kids [3 0 R] /Count 1 >>",
(
b"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 200 200] "
b"/Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>"
),
(
b"<< /Length %d >>\nstream\nBT /F1 24 Tf 50 100 Td ("
+ marker.encode("ascii")
+ b") Tj ET\nendstream"
),
b"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>",
]
body_open = objects[3].index(b"\nstream\n") + len(b"\nstream\n")
body_close = objects[3].index(b"\nendstream")
body_len = body_close - body_open
objects[3] = (
b"<< /Length "
+ str(body_len).encode("ascii")
+ b" >>\nstream\n"
+ objects[3][body_open:body_close]
+ b"\nendstream"
)
out = bytearray(b"%PDF-1.4\n")
offsets = []
for i, obj in enumerate(objects, start=1):
offsets.append(len(out))
out += f"{i} 0 obj\n".encode("ascii") + obj + b"\nendobj\n"
xref_offset = len(out)
out += b"xref\n0 %d\n" % (len(objects) + 1)
out += b"0000000000 65535 f \n"
for off in offsets:
out += f"{off:010d} 00000 n \n".encode("ascii")
out += (
b"trailer\n<< /Size "
+ str(len(objects) + 1).encode("ascii")
+ b" /Root 1 0 R >>\nstartxref\n"
+ str(xref_offset).encode("ascii")
+ b"\n%%EOF\n"
)
return bytes(out)
@pytest.mark.covers("llm.messages.azure_foundry.pdf_input.nonstream.works")
def test_pdf_input_azure(compat_result, tmp_path):
base_url, api_key = require_proxy(compat_result)
pdf_path = tmp_path / "marker.pdf"
pdf_path.write_bytes(_build_minimal_pdf(PDF_MARKER))
outcomes = run_claude_models_parallel(
models=AZURE_MODELS,
prompt=(
f"Use the Read tool to read the file at {pdf_path}. "
"Report the single word that appears in the document."
),
base_url=base_url,
api_key=api_key,
extra_args=["--allowed-tools", "Read"],
)
failures = []
for model in AZURE_MODELS:
outcome = outcomes[model]
if isinstance(outcome, ClaudeCLIError):
error = f"[{model}] {outcome}"
compat_result.add({"status": "fail", "error": error})
failures.append(error)
continue
if outcome.exit_code != 0:
error = f"[{model}] claude CLI failed: {failure_diagnostic(outcome)}"
compat_result.add({"status": "fail", "error": error})
failures.append(error)
continue
if PDF_MARKER not in outcome.text.upper():
error = (
f"[{model}] reply did not reference the PDF marker {PDF_MARKER!r}; "
f"got: {outcome.text.strip()!r}"
)
compat_result.add({"status": "fail", "error": error})
failures.append(error)
continue
compat_result.add({"status": "pass"})
if failures:
pytest.fail("; ".join(failures), pytrace=False)