2026-06-10 21:53:18 -04:00
|
|
|
"""Tests for CLI proxy command improvements: help text, exception handling, validation.
|
|
|
|
|
|
|
|
|
|
Covers:
|
|
|
|
|
- --learn + --no-learn conflict warning
|
|
|
|
|
- --subscription-poll-interval range validation (1-3600)
|
|
|
|
|
- --retry-max-attempts range validation (0-10)
|
|
|
|
|
- --connect-timeout-seconds range validation (1-300)
|
|
|
|
|
- --budget non-negative validation
|
|
|
|
|
- --memory-top-k range validation (1-100)
|
|
|
|
|
- ImportError path (missing proxy dependencies)
|
|
|
|
|
- KeyboardInterrupt exits with code 130
|
|
|
|
|
- env var wiring for newly-added envvars
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
fix(proxy): add an Anthropic buffered read-timeout override (#1331)
## Description
Buffered Anthropic `/v1/messages` requests still use Headroom's generic
300-second read timeout, which can produce proxy-generated `502
ReadTimeout` errors on long turns. This adds a dedicated buffered
Anthropic timeout, keeps it applied across CCR and memory continuations
plus batch paths, and makes the direct server entrypoint enforce the
same positive-integer contract as the Click CLI. Closes #1261.
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
## Changes Made
- Added `anthropic_buffered_request_timeout_seconds` for buffered
Anthropic reads.
- Routed `/v1/messages`, CCR continuation, memory continuation, batch
create, batch passthrough, and batch results through that timeout.
- Enforced the same positive-integer validation for
`HEADROOM_ANTHROPIC_BUFFERED_REQUEST_TIMEOUT_SECONDS` and
`--anthropic-buffered-request-timeout-seconds` in both startup paths.
- Added focused regressions and updated `CHANGELOG.md`.
## Testing
- [x] `uv run pytest tests/test_proxy/test_anthropic_buffered_timeout.py
tests/test_cli_proxy_improvements.py::TestNewEnvVarWiring`
- [x] `uv run ruff check .`
- [x] `uv run ruff format . --check`
### Test Output
```text
$ uv run pytest tests/test_proxy/test_anthropic_buffered_timeout.py tests/test_cli_proxy_improvements.py::TestNewEnvVarWiring
17 passed in 3.42s
$ uv run ruff check .
All checks passed!
$ uv run ruff format . --check
966 files already formatted
```
## Real Behavior Proof
- Environment: local FastAPI `TestClient` with stubbed retry and HTTP
client seams
- Exact command / steps: run `uv run pytest
tests/test_proxy/test_anthropic_buffered_timeout.py
tests/test_cli_proxy_improvements.py::TestNewEnvVarWiring`; the tests
build `ProxyConfig(request_timeout_seconds=7, connect_timeout_seconds=3,
anthropic_buffered_request_timeout_seconds=19)`, drive `/v1/messages`,
`/v1/messages/batches`, `/v1/messages/batches/{batch_id}/results`, a CCR
continuation, and a memory continuation through `TestClient`, then
verify `HEADROOM_ANTHROPIC_BUFFERED_REQUEST_TIMEOUT_SECONDS=0` falls
back to `600`, `--anthropic-buffered-request-timeout-seconds 0` is
rejected, and default proxy timeouts stay `read=300` and `write=300`
- Observed result: buffered Anthropic paths use
`httpx.Timeout(connect=3, read=19, write=7, pool=3)`, continuation
requests stay on that same budget, invalid zero-valued startup config is
rejected or ignored back to the default, and unrelated proxy timeout
defaults stay unchanged
- Not tested: live upstream Anthropic latency beyond the focused
stubbed-timeout regression
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have added tests that prove the fix
- [x] New and existing unit tests pass locally with my changes
- [x] I have updated the CHANGELOG.md if applicable
2026-06-23 23:46:31 -04:00
|
|
|
import argparse
|
2026-06-10 21:53:18 -04:00
|
|
|
from unittest.mock import patch
|
|
|
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
|
click = pytest.importorskip("click")
|
|
|
|
|
pytest.importorskip("fastapi")
|
|
|
|
|
|
|
|
|
|
from click.testing import CliRunner # noqa: E402
|
|
|
|
|
|
|
|
|
|
from headroom.cli.main import main # noqa: E402
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture
|
|
|
|
|
def runner() -> CliRunner:
|
|
|
|
|
return CliRunner()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture
|
|
|
|
|
def mock_run_server():
|
|
|
|
|
"""Patch run_server to a no-op and capture the ProxyConfig passed to it."""
|
|
|
|
|
captured: dict = {}
|
|
|
|
|
|
|
|
|
|
def _mock(config, **kwargs):
|
|
|
|
|
captured["config"] = config
|
|
|
|
|
captured["kwargs"] = kwargs
|
|
|
|
|
|
|
|
|
|
with patch("headroom.proxy.server.run_server", _mock):
|
|
|
|
|
yield captured
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestLearnNoLearnConflict:
|
|
|
|
|
"""--learn and --no-learn together should warn but not fail."""
|
|
|
|
|
|
|
|
|
|
def test_both_flags_warns_and_exits_zero(
|
|
|
|
|
self, runner: CliRunner, mock_run_server: dict
|
|
|
|
|
) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--learn", "--no-learn"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
# Warning must go to stderr via click.secho(err=True)
|
|
|
|
|
assert "both --learn and --no-learn" in result.output or (result.output is not None), (
|
|
|
|
|
result.output
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
def test_no_learn_wins_over_learn(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
"""When both are set, learning must be disabled (--no-learn takes precedence)."""
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--learn", "--no-learn"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
cfg = mock_run_server["config"]
|
|
|
|
|
assert cfg.traffic_learning_enabled is False
|
|
|
|
|
|
|
|
|
|
def test_learn_alone_enables_learning(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--learn"], catch_exceptions=False)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
cfg = mock_run_server["config"]
|
|
|
|
|
assert cfg.traffic_learning_enabled is True
|
|
|
|
|
assert cfg.memory_enabled is True
|
|
|
|
|
|
|
|
|
|
def test_no_learn_alone_disables_learning(
|
|
|
|
|
self, runner: CliRunner, mock_run_server: dict
|
|
|
|
|
) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--memory", "--no-learn"], catch_exceptions=False)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
cfg = mock_run_server["config"]
|
|
|
|
|
assert cfg.traffic_learning_enabled is False
|
|
|
|
|
|
|
|
|
|
|
feat(proxy): add provider-only HTTP proxy (#1807)
## Description
Adds provider-only HTTP proxy configuration for upstream LLM calls
without setting process-wide proxy environment variables.
`--http-proxy` and `HEADROOM_HTTP_PROXY` are scoped to the proxy
server's provider HTTPX clients, and HTTP/2 is disabled for those
clients when the proxy is set so HTTPS provider APIs can tunnel through
CONNECT. Using process env vars such as `HTTP_PROXY`, `HTTPS_PROXY`,
`ALL_PROXY`, or `NO_PROXY` would also affect HTTPX, but those vars are
inherited by tool executions, so this keeps proxy routing out of the
global environment.
Closes: N/A
## Type of Change
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [x] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
- Added `--http-proxy` with `HEADROOM_HTTP_PROXY` fallback.
- Passed the proxy URL only into provider HTTPX clients.
- Disabled provider HTTP/2 when the proxy is configured.
- Preserved the new setting through direct server startup and
multi-worker config serialization.
- Documented the flag/env var and why global `HTTP_PROXY`-style vars are
not suitable for provider-only routing.
- Added an Unreleased changelog entry.
- Added coverage for CLI/env wiring, worker serialization, and HTTPX
client options.
## Testing
<!-- Check what you actually ran, then paste the real command output
below. -->
- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ uv run --frozen pytest tests/test_cli_proxy_improvements.py tests/test_proxy_scalability.py
============================== 72 passed in 5.95s ==============================
$ uv run --frozen ruff check headroom/cli/proxy.py headroom/proxy/models.py headroom/proxy/server.py tests/test_cli_proxy_improvements.py tests/test_proxy_scalability.py
All checks passed!
$ uv run --frozen mypy headroom --ignore-missing-imports
Success: no issues found in 406 source files
$ env -u HTTP_PROXY -u http_proxy npm --prefix docs run types:check
[MDX] generated files in 6.351916000000074ms
Generating route types...
[MDX] generated files in 5.813166999999794ms
✓ Types generated successfully
$ git diff --check
# no output
```
## Real Behavior Proof
- Environment: local provider setup that requires outbound LLM traffic
through an HTTP proxy
- Exact command / steps: ran focused pytest, Ruff, mypy, docs
`types:check`, and `git diff --check` after rebasing the branch onto
`origin/main`; reviewed the docs and changelog diffs; actively used the
new proxy setting locally for a provider that requires proxied egress
- Observed result: CLI/env/config tests passed; static checks passed;
docs type generation passed; local provider traffic can be routed
through the provider-only proxy setting without exporting global proxy
variables to tool executions
- Not tested: broad provider matrix across every supported upstream
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] I have updated the CHANGELOG.md if applicable
## Screenshots (if applicable)
N/A. CLI/backend/docs update only.
## Additional Notes
The branch keeps implementation, docs, changelog, and formatting changes
in separate commits.
2026-07-05 15:56:59 -07:00
|
|
|
class TestHttpProxyOption:
|
|
|
|
|
"""--http-proxy should configure only the provider HTTPX clients."""
|
|
|
|
|
|
|
|
|
|
def test_http_proxy_cli_flag(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--http-proxy", "http://proxy.local:8080"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].http_proxy == "http://proxy.local:8080"
|
|
|
|
|
|
|
|
|
|
def test_http_proxy_env_var(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy"],
|
|
|
|
|
env={"HEADROOM_HTTP_PROXY": "http://proxy.local:8080"},
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].http_proxy == "http://proxy.local:8080"
|
|
|
|
|
|
|
|
|
|
def test_direct_server_env_http_proxy(self, monkeypatch: pytest.MonkeyPatch) -> None:
|
|
|
|
|
import headroom.proxy.server as server_mod
|
|
|
|
|
|
|
|
|
|
monkeypatch.delenv(server_mod._MULTI_WORKER_CONFIG_ENV, raising=False)
|
|
|
|
|
monkeypatch.setenv("HEADROOM_HTTP_PROXY", "http://proxy.local:8080")
|
|
|
|
|
|
|
|
|
|
config = server_mod._proxy_config_from_env()
|
|
|
|
|
assert config.http_proxy == "http://proxy.local:8080"
|
|
|
|
|
|
|
|
|
|
|
2026-06-10 21:53:18 -04:00
|
|
|
class TestSubscriptionPollIntervalValidation:
|
|
|
|
|
"""--subscription-poll-interval should reject values outside 1-3600."""
|
|
|
|
|
|
|
|
|
|
def test_valid_lower_bound(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--subscription-poll-interval", "1"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
|
|
|
|
|
def test_valid_upper_bound(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--subscription-poll-interval", "3600"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
|
|
|
|
|
def test_zero_is_rejected(self, runner: CliRunner) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--subscription-poll-interval", "0"])
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
assert (
|
|
|
|
|
"invalid" in result.output.lower()
|
|
|
|
|
or "range" in result.output.lower()
|
|
|
|
|
or "error" in result.output.lower()
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
def test_above_max_is_rejected(self, runner: CliRunner) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--subscription-poll-interval", "3601"])
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
|
|
|
|
|
def test_negative_is_rejected(self, runner: CliRunner) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--subscription-poll-interval", "-1"])
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestRetryMaxAttemptsValidation:
|
|
|
|
|
"""--retry-max-attempts should accept 1-10, reject outside that range."""
|
|
|
|
|
|
|
|
|
|
def test_one_is_valid(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--retry-max-attempts", "1"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].retry_max_attempts == 1
|
|
|
|
|
|
|
|
|
|
def test_ten_is_valid(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--retry-max-attempts", "10"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].retry_max_attempts == 10
|
|
|
|
|
|
|
|
|
|
def test_zero_is_rejected(self, runner: CliRunner) -> None:
|
|
|
|
|
"""0 is not valid because ProxyConfig requires retry_max_attempts >= 1."""
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--retry-max-attempts", "0"])
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
|
|
|
|
|
def test_negative_is_rejected(self, runner: CliRunner) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--retry-max-attempts", "-1"])
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
|
|
|
|
|
def test_above_max_is_rejected(self, runner: CliRunner) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--retry-max-attempts", "11"])
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestConnectTimeoutSecondsValidation:
|
|
|
|
|
"""--connect-timeout-seconds should accept 1-300, reject outside that range."""
|
|
|
|
|
|
|
|
|
|
def test_one_is_valid(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--connect-timeout-seconds", "1"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].connect_timeout_seconds == 1
|
|
|
|
|
|
|
|
|
|
def test_three_hundred_is_valid(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--connect-timeout-seconds", "300"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].connect_timeout_seconds == 300
|
|
|
|
|
|
|
|
|
|
def test_zero_is_rejected(self, runner: CliRunner) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--connect-timeout-seconds", "0"])
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
|
|
|
|
|
def test_above_max_is_rejected(self, runner: CliRunner) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--connect-timeout-seconds", "301"])
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestBudgetValidation:
|
|
|
|
|
"""--budget should accept non-negative floats, reject negative values."""
|
|
|
|
|
|
|
|
|
|
def test_zero_budget_is_valid(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--budget", "0.0"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].budget_limit_usd == 0.0
|
|
|
|
|
|
|
|
|
|
def test_positive_budget_is_valid(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--budget", "50.0"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].budget_limit_usd == 50.0
|
|
|
|
|
|
|
|
|
|
def test_negative_budget_is_rejected(self, runner: CliRunner) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--budget", "-1.0"])
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestMemoryTopKValidation:
|
|
|
|
|
"""--memory-top-k should accept 1-100, reject outside that range."""
|
|
|
|
|
|
|
|
|
|
def test_one_is_valid(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--memory", "--memory-top-k", "1"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].memory_top_k == 1
|
|
|
|
|
|
|
|
|
|
def test_hundred_is_valid(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--memory", "--memory-top-k", "100"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].memory_top_k == 100
|
|
|
|
|
|
|
|
|
|
def test_zero_is_rejected(self, runner: CliRunner) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--memory-top-k", "0"])
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
|
|
|
|
|
def test_above_max_is_rejected(self, runner: CliRunner) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--memory-top-k", "101"])
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestMissingProxyDepsError:
|
|
|
|
|
"""When proxy dependencies are absent the CLI should print an actionable error and exit 1."""
|
|
|
|
|
|
|
|
|
|
def test_import_error_exits_nonzero(self, runner: CliRunner) -> None:
|
|
|
|
|
with patch.dict(
|
|
|
|
|
"sys.modules",
|
|
|
|
|
{"headroom.proxy.server": None},
|
|
|
|
|
):
|
|
|
|
|
result = runner.invoke(main, ["proxy"])
|
|
|
|
|
# Click CliRunner may raise SystemExit or catch it; exit code must be non-zero
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
|
|
|
|
|
def test_import_error_message_is_actionable(self, runner: CliRunner) -> None:
|
|
|
|
|
"""The error message should tell the user how to fix the problem."""
|
|
|
|
|
original_import = (
|
|
|
|
|
__builtins__.__import__ if hasattr(__builtins__, "__import__") else __import__
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
def patched_import(name, *args, **kwargs):
|
|
|
|
|
if name == "headroom.proxy.server":
|
|
|
|
|
raise ImportError("No module named 'headroom.proxy.server'")
|
|
|
|
|
return original_import(name, *args, **kwargs)
|
|
|
|
|
|
|
|
|
|
with patch("builtins.__import__", side_effect=patched_import):
|
|
|
|
|
result = runner.invoke(main, ["proxy"])
|
|
|
|
|
|
|
|
|
|
# Either exit code 1 or output with actionable guidance
|
|
|
|
|
# (some test environments may shadow the import differently)
|
|
|
|
|
assert result.exit_code != 0 or "proxy" in result.output.lower()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestKeyboardInterruptExitCode:
|
|
|
|
|
"""Ctrl+C during proxy run should exit 130 (SIGINT convention)."""
|
|
|
|
|
|
|
|
|
|
def test_keyboard_interrupt_exits_130(self, runner: CliRunner) -> None:
|
|
|
|
|
def _run_server_raises(*args, **kwargs):
|
|
|
|
|
raise KeyboardInterrupt
|
|
|
|
|
|
|
|
|
|
with patch("headroom.proxy.server.run_server", _run_server_raises):
|
|
|
|
|
result = runner.invoke(main, ["proxy"])
|
|
|
|
|
|
|
|
|
|
assert result.exit_code == 130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestNewEnvVarWiring:
|
|
|
|
|
"""Verify newly-added envvar= wiring works for options that lacked it."""
|
|
|
|
|
|
|
|
|
|
def test_headroom_memory_db_path_from_env(
|
|
|
|
|
self, runner: CliRunner, mock_run_server: dict
|
|
|
|
|
) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--memory"],
|
|
|
|
|
env={"HEADROOM_MEMORY_DB_PATH": "/tmp/test-memory.db"},
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].memory_db_path == "/tmp/test-memory.db"
|
|
|
|
|
|
|
|
|
|
def test_headroom_retry_max_attempts_from_env(
|
|
|
|
|
self, runner: CliRunner, mock_run_server: dict
|
|
|
|
|
) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy"],
|
|
|
|
|
env={"HEADROOM_RETRY_MAX_ATTEMPTS": "5"},
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].retry_max_attempts == 5
|
|
|
|
|
|
|
|
|
|
def test_headroom_connect_timeout_from_env(
|
|
|
|
|
self, runner: CliRunner, mock_run_server: dict
|
|
|
|
|
) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy"],
|
|
|
|
|
env={"HEADROOM_CONNECT_TIMEOUT_SECONDS": "30"},
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].connect_timeout_seconds == 30
|
|
|
|
|
|
fix(proxy): add an Anthropic buffered read-timeout override (#1331)
## Description
Buffered Anthropic `/v1/messages` requests still use Headroom's generic
300-second read timeout, which can produce proxy-generated `502
ReadTimeout` errors on long turns. This adds a dedicated buffered
Anthropic timeout, keeps it applied across CCR and memory continuations
plus batch paths, and makes the direct server entrypoint enforce the
same positive-integer contract as the Click CLI. Closes #1261.
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
## Changes Made
- Added `anthropic_buffered_request_timeout_seconds` for buffered
Anthropic reads.
- Routed `/v1/messages`, CCR continuation, memory continuation, batch
create, batch passthrough, and batch results through that timeout.
- Enforced the same positive-integer validation for
`HEADROOM_ANTHROPIC_BUFFERED_REQUEST_TIMEOUT_SECONDS` and
`--anthropic-buffered-request-timeout-seconds` in both startup paths.
- Added focused regressions and updated `CHANGELOG.md`.
## Testing
- [x] `uv run pytest tests/test_proxy/test_anthropic_buffered_timeout.py
tests/test_cli_proxy_improvements.py::TestNewEnvVarWiring`
- [x] `uv run ruff check .`
- [x] `uv run ruff format . --check`
### Test Output
```text
$ uv run pytest tests/test_proxy/test_anthropic_buffered_timeout.py tests/test_cli_proxy_improvements.py::TestNewEnvVarWiring
17 passed in 3.42s
$ uv run ruff check .
All checks passed!
$ uv run ruff format . --check
966 files already formatted
```
## Real Behavior Proof
- Environment: local FastAPI `TestClient` with stubbed retry and HTTP
client seams
- Exact command / steps: run `uv run pytest
tests/test_proxy/test_anthropic_buffered_timeout.py
tests/test_cli_proxy_improvements.py::TestNewEnvVarWiring`; the tests
build `ProxyConfig(request_timeout_seconds=7, connect_timeout_seconds=3,
anthropic_buffered_request_timeout_seconds=19)`, drive `/v1/messages`,
`/v1/messages/batches`, `/v1/messages/batches/{batch_id}/results`, a CCR
continuation, and a memory continuation through `TestClient`, then
verify `HEADROOM_ANTHROPIC_BUFFERED_REQUEST_TIMEOUT_SECONDS=0` falls
back to `600`, `--anthropic-buffered-request-timeout-seconds 0` is
rejected, and default proxy timeouts stay `read=300` and `write=300`
- Observed result: buffered Anthropic paths use
`httpx.Timeout(connect=3, read=19, write=7, pool=3)`, continuation
requests stay on that same budget, invalid zero-valued startup config is
rejected or ignored back to the default, and unrelated proxy timeout
defaults stay unchanged
- Not tested: live upstream Anthropic latency beyond the focused
stubbed-timeout regression
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have added tests that prove the fix
- [x] New and existing unit tests pass locally with my changes
- [x] I have updated the CHANGELOG.md if applicable
2026-06-23 23:46:31 -04:00
|
|
|
def test_headroom_anthropic_buffered_timeout_from_env(
|
|
|
|
|
self, runner: CliRunner, mock_run_server: dict
|
|
|
|
|
) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy"],
|
|
|
|
|
env={"HEADROOM_ANTHROPIC_BUFFERED_REQUEST_TIMEOUT_SECONDS": "900"},
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].anthropic_buffered_request_timeout_seconds == 900
|
|
|
|
|
|
|
|
|
|
def test_anthropic_buffered_timeout_cli_flag(
|
|
|
|
|
self, runner: CliRunner, mock_run_server: dict
|
|
|
|
|
) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--anthropic-buffered-request-timeout-seconds", "901"],
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].anthropic_buffered_request_timeout_seconds == 901
|
|
|
|
|
|
|
|
|
|
def test_direct_server_env_timeout_zero_falls_back_to_default(
|
|
|
|
|
self, monkeypatch: pytest.MonkeyPatch
|
|
|
|
|
) -> None:
|
|
|
|
|
import headroom.proxy.server as server_mod
|
|
|
|
|
|
|
|
|
|
monkeypatch.delenv(server_mod._MULTI_WORKER_CONFIG_ENV, raising=False)
|
|
|
|
|
monkeypatch.setenv("HEADROOM_ANTHROPIC_BUFFERED_REQUEST_TIMEOUT_SECONDS", "0")
|
|
|
|
|
|
|
|
|
|
config = server_mod._proxy_config_from_env()
|
|
|
|
|
assert config.anthropic_buffered_request_timeout_seconds == 600
|
|
|
|
|
|
|
|
|
|
def test_direct_server_timeout_parser_rejects_zero(
|
|
|
|
|
self, monkeypatch: pytest.MonkeyPatch
|
|
|
|
|
) -> None:
|
|
|
|
|
import headroom.proxy.server as server_mod
|
|
|
|
|
|
|
|
|
|
with pytest.raises(argparse.ArgumentTypeError):
|
|
|
|
|
server_mod._positive_int_arg("0")
|
|
|
|
|
|
2026-06-10 21:53:18 -04:00
|
|
|
def test_headroom_backend_from_env(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy"],
|
|
|
|
|
env={"HEADROOM_BACKEND": "bedrock"},
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].backend == "bedrock"
|
|
|
|
|
|
|
|
|
|
def test_headroom_region_from_env(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy"],
|
|
|
|
|
env={"HEADROOM_REGION": "eu-west-1"},
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
# bedrock_region falls back to region
|
|
|
|
|
assert mock_run_server["config"].bedrock_region == "eu-west-1"
|
|
|
|
|
|
|
|
|
|
def test_headroom_memory_top_k_from_env(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy", "--memory"],
|
|
|
|
|
env={"HEADROOM_MEMORY_TOP_K": "20"},
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].memory_top_k == 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestHelpTextCompleteness:
|
|
|
|
|
"""Verify key flags appear in --help output with non-trivial descriptions."""
|
|
|
|
|
|
|
|
|
|
def _help(self, runner: CliRunner) -> str:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--help"])
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
return result.output
|
|
|
|
|
|
|
|
|
|
def test_help_contains_mode_option(self, runner: CliRunner) -> None:
|
|
|
|
|
assert "--mode" in self._help(runner)
|
|
|
|
|
|
|
|
|
|
def test_help_contains_workers_option(self, runner: CliRunner) -> None:
|
|
|
|
|
assert "--workers" in self._help(runner)
|
|
|
|
|
|
|
|
|
|
def test_help_contains_memory_option(self, runner: CliRunner) -> None:
|
|
|
|
|
assert "--memory" in self._help(runner)
|
|
|
|
|
|
|
|
|
|
def test_help_contains_backend_option(self, runner: CliRunner) -> None:
|
|
|
|
|
assert "--backend" in self._help(runner)
|
|
|
|
|
|
|
|
|
|
def test_help_contains_budget_option(self, runner: CliRunner) -> None:
|
|
|
|
|
assert "--budget" in self._help(runner)
|
|
|
|
|
|
|
|
|
|
def test_help_contains_log_file_option(self, runner: CliRunner) -> None:
|
|
|
|
|
assert "--log-file" in self._help(runner)
|
|
|
|
|
|
|
|
|
|
def test_help_contains_stateless_option(self, runner: CliRunner) -> None:
|
|
|
|
|
assert "--stateless" in self._help(runner)
|
|
|
|
|
|
|
|
|
|
def test_help_contains_usage_examples(self, runner: CliRunner) -> None:
|
|
|
|
|
"""Docstring examples should appear in --help output."""
|
|
|
|
|
out = self._help(runner)
|
|
|
|
|
assert "ANTHROPIC_BASE_URL" in out
|
|
|
|
|
|
|
|
|
|
def test_proxy_short_help_alias(self, runner: CliRunner) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy", "-?"])
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert "--mode" in result.output
|
|
|
|
|
|
|
|
|
|
def test_mode_invalid_value_error(self, runner: CliRunner) -> None:
|
|
|
|
|
"""An invalid --mode value should fail with a clear error, not a traceback."""
|
|
|
|
|
result = runner.invoke(main, ["proxy", "--mode", "bogus_mode_xyz"])
|
|
|
|
|
assert result.exit_code != 0
|
|
|
|
|
assert "invalid" in result.output.lower() or "choice" in result.output.lower()
|
2026-07-02 06:19:48 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestCompressionMaxWorkers:
|
|
|
|
|
"""--compression-max-workers / HEADROOM_COMPRESSION_MAX_WORKERS must reach ProxyConfig.
|
|
|
|
|
|
|
|
|
|
Regression: the field was documented in ProxyConfig and consumed by the
|
|
|
|
|
server, but the CLI never defined the option or passed it through, so it
|
perf(proxy): cap compression workers to CPU count (#1803)
## Description
The request-path compression executor currently uses asyncio-style I/O
sizing for CPU-bound Kompress work. When `compression_max_workers` is
unset, `HeadroomProxy.__init__` resolves the pool to `min(32, cpu * 4)`,
so an eight-core host can run 32 simultaneous compression workers that
all contend for real CPU.
This changes only the automatic request-path default to one worker per
reported CPU while preserving the existing explicit override path from
`--compression-max-workers` and `HEADROOM_COMPRESSION_MAX_WORKERS`.
Closes #1635
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [x] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
- Cap the automatic request-path compression executor default at `max(1,
os.cpu_count() or 1)`.
- Preserve explicit `compression_max_workers` values, including the
existing clamp to at least one worker.
- Keep CLI help, `ProxyConfig` comments, and nearby test documentation
aligned with the CPU-bound default.
- Update the focused compression executor regression so the default
contract documents CPU-bound sizing, and keep the existing Codex
compression stress guard stable when p50 rounds to zero.
## Testing
- [x] Unit tests pass (`uv run pytest
tests/test_codex_ws_compression_scheduler.py
tests/test_proxy_compression_executor.py
tests/test_cli_proxy_improvements.py::TestCompressionMaxWorkers -q`)
- [x] Linting passes (`uv run ruff check headroom/cli/proxy.py
headroom/proxy/models.py headroom/proxy/server.py
tests/test_cli_proxy_improvements.py
tests/test_proxy_compression_executor.py
tests/test_codex_ws_compression_scheduler.py`)
- [ ] Type checking passes (`uv run mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ uv run pytest tests/test_codex_ws_compression_scheduler.py tests/test_proxy_compression_executor.py tests/test_cli_proxy_improvements.py::TestCompressionMaxWorkers -q
16 passed, 1 skipped, 1 warning in 6.13s
$ uv run ruff check headroom/cli/proxy.py headroom/proxy/models.py headroom/proxy/server.py tests/test_cli_proxy_improvements.py tests/test_proxy_compression_executor.py tests/test_codex_ws_compression_scheduler.py
All checks passed!
```
## Real Behavior Proof
- Environment: Windows, Python environment from `uv sync --extra dev`,
no provider credentials needed.
- Exact command / steps: construct `HeadroomProxy` with
`compression_max_workers=None`, inspect `proxy.compression_max_workers`
and `/health` `runtime.compression_executor`.
- Observed result: the automatic request-path pool resolves to reported
CPU count, while explicit overrides still resolve to the configured
value and report `source: explicit`.
- Not tested: multi-session wall-clock benchmark under live Kompress
load.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] I have updated the CHANGELOG.md if applicable
## Additional Notes
No `CHANGELOG.md` edit: this repo generates changelog entries from
conventional commits. This intentionally does not touch the background
compression executor surface covered by #1633.
2026-07-05 17:01:23 -04:00
|
|
|
was permanently None (always resolving to the automatic server default).
|
2026-07-02 06:19:48 +02:00
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
def test_flag_reaches_config(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main, ["proxy", "--compression-max-workers", "3"], catch_exceptions=False
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].compression_max_workers == 3
|
|
|
|
|
|
|
|
|
|
def test_env_reaches_config(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(
|
|
|
|
|
main,
|
|
|
|
|
["proxy"],
|
|
|
|
|
env={"HEADROOM_COMPRESSION_MAX_WORKERS": "5"},
|
|
|
|
|
catch_exceptions=False,
|
|
|
|
|
)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].compression_max_workers == 5
|
|
|
|
|
|
|
|
|
|
def test_default_is_none(self, runner: CliRunner, mock_run_server: dict) -> None:
|
|
|
|
|
result = runner.invoke(main, ["proxy"], catch_exceptions=False)
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert mock_run_server["config"].compression_max_workers is None
|