mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
Builds on PR #406 (HTTP /v1/responses PyO3) and PR #410 (WS first-frame PyO3) which landed the binding for `compress_openai_responses_live_zone`. This change closes the remaining gaps so every (provider × endpoint × auth-mode × streaming) combination compresses AND surfaces in the dashboard. Telemetry: extend the PyO3 binding return tuple from `(bytes, modified)` to `(bytes, modified, tokens_saved, transforms_applied)` by adding `CompressionManifest::tokens_saved()` and `transforms_applied()` accessors on the existing manifest. The Python proxy populates request-log telemetry from the binding output instead of recounting tokens. Updates the existing 2-tuple call sites in HTTP and WS first-frame, plus the unpacks in tests. WebSocket multi-frame compression: subscription Codex users keep a long-lived WS open and send multiple `response.create` events per session. PR #410 only compressed the first frame; subsequent frames went raw. Added `_maybe_compress_response_create_frame` closure inside `_client_to_upstream` that runs the same Rust dispatcher on every client→upstream `response.create` text frame, passes other event types (response.cancel, session.update, etc.) through unchanged, and accumulates `tokens_saved` / `transforms_applied` / `ws_frames_compressed` counters across the session. Pre-existing dashboard gap: `streaming.py` and `anthropic.py` write `RequestLog` entries; the non-streaming OpenAI HTTP and WS handlers did not. Result: /transformations/feed was invisible for every Codex turn and every Cline / OpenClaude / Aider turn. Added the same wiring in `handle_openai_chat` (non-streaming), `handle_openai_responses` (non-streaming HTTP), and `handle_openai_responses_ws` (session-end). All three populate `auth_mode` + `endpoint` tags so the dashboard can break compression activity down by client class (PAYG / OAuth / Subscription) and surface (`chat_completions` / `responses_http` / `responses_ws`). The WS metric record is now unconditional — was previously gated on `tokens_saved > 0`, so first-frame no-changes never registered. compute_frozen_count over-freeze for prose-format clients: `compute_frozen_count` walked until it found an unstable `tool_result` / `role: "tool"` block. Cline / OpenClaude / Aider — clients that embed tool calls as XML inside plain text — never produce such a boundary, so the function returned `len(messages)` and the pipeline froze 100% of messages including the brand-new user turn. Live zone empty → `Transform content_router: 16414 → 16414 tokens (saved 0)`. Reported on Discord 2026-05-07 with Cline+DeepSeek. Fix: cap at `max(0, len(messages) - 1)`. Updates 3 existing test assertions whose expected values encoded the old over-freeze. Adds 6 new prose-format invariant tests. CodeQL "clear-text logging of sensitive information" fix: `tests/e2e_real_compression.py` previously stored API keys in local variables in the same scope as diagnostic prints, which CodeQL flagged via data-flow analysis. Refactored to read keys from `os.environ` inside the request helper — the credentials never enter the runner's main scope, so the taint flow never reaches the print. End-to-end verification with real keys (.env): /v1/messages (PAYG, non-stream) tok 14109 → 969 saved 13140 /v1/messages (PAYG, stream) tok 14109 → 969 saved 13140 /v1/chat/completions (PAYG, non-stream) tok 18460 → 1374 saved 17086 /v1/chat/completions (PAYG, stream) tok 18460 → 1374 saved 17086 (cache_hit=100%) /v1/responses HTTP (PAYG, non-stream) bytes 50138 → 597 saved 18391 /v1/responses WS (frame 1) bytes 46429 → 488 saved 16791 /v1/responses WS (frame 2 multi) bytes 46429 → 488 saved 16791 /v1/responses WS (response.cancel) passthrough untouched Tests: cargo workspace + pytest (4846 pass, 0 fail), make ci-precheck passed, two E2E scripts (multi-turn HTTP, WS fake-upstream) all green.
205 lines
7.2 KiB
Python
205 lines
7.2 KiB
Python
"""WebSocket /v1/responses compression integration tests.
|
|
|
|
PR-C5 retired Python compression on the WS path expecting the standalone
|
|
Rust proxy binary to take over (it isn't deployed by the CLI). PR #406
|
|
re-enabled compression on the HTTP path via the inline PyO3 binding.
|
|
This module pins the WS-side equivalent: the first frame from the client
|
|
must be compressed via the same PyO3 dispatcher before forwarding to
|
|
the upstream WebSocket.
|
|
|
|
The tests exercise the compression *transformation logic* in isolation —
|
|
they replicate the body-shape handling the WS handler does (envelope
|
|
detect, compress inner, re-wrap) without spinning up a full WebSocket
|
|
session. Full session-lifecycle coverage already exists in
|
|
`test_openai_codex_ws_lifecycle.py`.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
|
|
def _ensure_binding():
|
|
"""Skip if the Rust extension hasn't been built (mirrors the pattern
|
|
in `test_responses_pyo3_compression.py`)."""
|
|
try:
|
|
from headroom._core import compress_openai_responses_live_zone
|
|
|
|
return compress_openai_responses_live_zone
|
|
except ImportError:
|
|
pytest.skip("headroom._core not built — run scripts/build_rust_extension.sh")
|
|
|
|
|
|
def _ws_compress_first_frame(
|
|
first_msg_raw: str,
|
|
auth_mode_value: str = "payg",
|
|
) -> tuple[str, bool]:
|
|
"""Replicates the WS-handler compression block as a pure function.
|
|
|
|
Returns ``(new_first_msg_raw, modified)``. The real handler embeds
|
|
this logic inline in `handle_openai_responses_ws`; pulling it out
|
|
here lets us pin the exact byte-shape contract without standing
|
|
up a full WebSocket fixture. If you change the handler's
|
|
compression block, mirror it here so the tests catch the drift.
|
|
"""
|
|
compress = _ensure_binding()
|
|
|
|
try:
|
|
send_body: Any = json.loads(first_msg_raw)
|
|
except json.JSONDecodeError:
|
|
return first_msg_raw, False
|
|
|
|
if not isinstance(send_body, dict):
|
|
return first_msg_raw, False
|
|
|
|
wrapped = "response" in send_body and isinstance(send_body["response"], dict)
|
|
inner = send_body["response"] if wrapped else send_body
|
|
model = (inner.get("model") if isinstance(inner, dict) else None) or ""
|
|
|
|
inner_bytes = json.dumps(inner).encode("utf-8")
|
|
new_bytes, modified, _saved, _transforms = compress(inner_bytes, auth_mode_value, model)
|
|
if not modified:
|
|
return first_msg_raw, False
|
|
|
|
try:
|
|
new_inner = json.loads(new_bytes)
|
|
except json.JSONDecodeError:
|
|
return first_msg_raw, False
|
|
|
|
if not isinstance(new_inner, dict):
|
|
return first_msg_raw, False
|
|
|
|
if wrapped:
|
|
send_body["response"] = new_inner
|
|
else:
|
|
send_body = new_inner
|
|
return json.dumps(send_body), True
|
|
|
|
|
|
class TestWrappedEnvelopeShape:
|
|
"""Codex's WebSocket protocol wraps the Responses payload in a
|
|
``response.create`` envelope. The WS handler must unwrap to compress
|
|
and re-wrap to forward."""
|
|
|
|
def test_passthrough_when_inner_has_no_input_array(self):
|
|
# No `input` array → dispatcher's NoMessagesArray path → passthrough.
|
|
first_msg = json.dumps(
|
|
{
|
|
"type": "response.create",
|
|
"response": {"model": "gpt-5"},
|
|
}
|
|
)
|
|
out, modified = _ws_compress_first_frame(first_msg)
|
|
assert modified is False
|
|
assert out == first_msg
|
|
|
|
def test_envelope_preserved_on_passthrough(self):
|
|
first_msg = json.dumps(
|
|
{
|
|
"type": "response.create",
|
|
"response": {
|
|
"model": "gpt-5",
|
|
"input": [{"type": "message", "role": "user", "content": "hi"}],
|
|
},
|
|
}
|
|
)
|
|
out, modified = _ws_compress_first_frame(first_msg)
|
|
# Single small user message → no compression applies.
|
|
assert modified is False
|
|
assert json.loads(out) == json.loads(first_msg)
|
|
|
|
|
|
class TestUnwrappedShape:
|
|
"""Older Codex versions (and some test fixtures) send the Responses
|
|
payload directly as the first frame, without a `response.create`
|
|
envelope. The handler must work for both shapes."""
|
|
|
|
def test_passthrough_when_no_input_array(self):
|
|
first_msg = json.dumps({"model": "gpt-5"})
|
|
out, modified = _ws_compress_first_frame(first_msg)
|
|
assert modified is False
|
|
assert out == first_msg
|
|
|
|
def test_passthrough_when_empty_input(self):
|
|
first_msg = json.dumps({"model": "gpt-5", "input": []})
|
|
out, modified = _ws_compress_first_frame(first_msg)
|
|
assert modified is False
|
|
assert out == first_msg
|
|
|
|
|
|
class TestNonJsonFirstFrame:
|
|
"""If the first frame isn't JSON, we forward it byte-for-byte rather
|
|
than crashing the WS session."""
|
|
|
|
def test_garbage_passthrough(self):
|
|
out, modified = _ws_compress_first_frame("not actually json")
|
|
assert modified is False
|
|
assert out == "not actually json"
|
|
|
|
def test_json_array_passthrough(self):
|
|
# Top-level array isn't a Responses envelope.
|
|
first_msg = json.dumps([1, 2, 3])
|
|
out, modified = _ws_compress_first_frame(first_msg)
|
|
assert modified is False
|
|
assert out == first_msg
|
|
|
|
def test_json_string_passthrough(self):
|
|
first_msg = json.dumps("a string at the top level")
|
|
out, modified = _ws_compress_first_frame(first_msg)
|
|
assert modified is False
|
|
assert out == first_msg
|
|
|
|
|
|
class TestAuthModeForwarded:
|
|
"""Every F1 AuthMode value reaches the dispatcher without raising.
|
|
The dispatcher itself currently treats all modes identically (per-mode
|
|
tuning is F2.2 follow-up), but the call must not fail on any value
|
|
the F1 classifier produces."""
|
|
|
|
@pytest.mark.parametrize(
|
|
"auth_mode_value",
|
|
["payg", "oauth", "subscription", "unknown"],
|
|
)
|
|
def test_all_auth_modes_accepted(self, auth_mode_value: str):
|
|
first_msg = json.dumps({"model": "gpt-5", "input": []})
|
|
out, modified = _ws_compress_first_frame(first_msg, auth_mode_value)
|
|
assert modified is False
|
|
assert out == first_msg
|
|
|
|
|
|
class TestNoExceptionLeak:
|
|
"""The WS handler wraps the compression block in try/except so a
|
|
JSON-shape edge case can never crash the WS session. This pins the
|
|
contract that no input shape produces an exception in the
|
|
transformation function."""
|
|
|
|
@pytest.mark.parametrize(
|
|
"first_msg",
|
|
[
|
|
"",
|
|
"{",
|
|
"{",
|
|
"}",
|
|
"[",
|
|
"null",
|
|
"true",
|
|
"0",
|
|
json.dumps({}),
|
|
json.dumps({"response": "not a dict"}),
|
|
json.dumps({"response": []}),
|
|
json.dumps({"response": None}),
|
|
json.dumps({"response": {"input": "not an array"}}),
|
|
json.dumps({"input": "string instead of array"}),
|
|
json.dumps({"input": None}),
|
|
],
|
|
)
|
|
def test_no_exception_for_garbage_shapes(self, first_msg: str):
|
|
# Should never raise — return passthrough on anything malformed.
|
|
out, modified = _ws_compress_first_frame(first_msg)
|
|
# Regardless of result, no exception leaked. modified might be
|
|
# False here (garbage input → no compression).
|
|
assert isinstance(out, str)
|
|
assert isinstance(modified, bool)
|