headroom/tests/test_system_compaction.py
Gen Li 3dd9660d91
feat: 3-layer context compression pipeline (L1+L2+L3) (#1405)
## Description

> **Default behavior is unchanged:** only L1 (annotation-key stripping)
is on by default. L2 (description truncation) and L3 (system-prompt
compression) are **opt-in** via `HEADROOM_TOOL_DESC_MAX_CHARS` and
`HEADROOM_SYSTEM_COMPACT=1` respectively — instruction-level compression
never runs unless an operator explicitly enables it. Verified in
`system_compact.py`: `system_compact_enabled()` returns `False` when the
env var is unset.

Reduces MCP-injected context overhead (~40K tokens / 20% of a 200K
window) through a progressive 3-layer compression pipeline. Each layer
is independently controlled, fail-safe, and additive — operators can
enable L1 only (default) or opt into L2/L3 for deeper savings.

### Layer 1: Tool Schema Annotation Key Stripping (default on)
- Strip JSON Schema annotation keys (`$schema`, `title`, `examples`,
`deprecated`, `default`, `readOnly`, `writeOnly`) from tool definitions
- Normalise whitespace in `description` fields
- Zero risk — removes only non-constraint metadata that models ignore
- ~8% savings on tool schema size

### Layer 2: Tool Description Truncation (opt-in:
`HEADROOM_TOOL_DESC_MAX_CHARS`)
- Truncate verbose tool/parameter descriptions to configurable length
- Preserves first complete sentence (critical for model tool selection)
- Optionally appends second sentence within 1.5× budget
- Hard-truncates with `...` if a single sentence exceeds limit
- Recursively processes nested `description` fields in
`input_schema`/`parameters`
- ~43% savings on description text (estimated ~17K tokens)

### Layer 3: System Prompt CCR Compression (opt-in:
`HEADROOM_SYSTEM_COMPACT`)
- Compress `system[]` content blocks using existing
`ContentRouter.compress()`
- Only compresses blocks exceeding `HEADROOM_SYSTEM_COMPACT_MIN_CHARS`
(default 500)
- Preserves `cache_control` markers and non-text blocks
- Fail-safe: leaves block unchanged if compression fails or doesn't save
size
- ~14.5% savings on system prompt (estimated ~3.5K tokens)

**Combined savings (all 3 layers enabled): ~40K → ~17K tokens (~58%
reduction)**

## 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)
- [ ] Documentation update
- [x] Performance improvement
- [ ] Code refactoring (no functional changes)

## Changes Made

- `headroom/proxy/tool_schema_compaction.py` — New shared module: L1
annotation stripping + L2 description truncation with
`strip_annotation_keys()` and `truncate_descriptions()`
- `headroom/proxy/system_compaction.py` — New module: L3 system prompt
CCR compression with `compact_system_blocks()`
- `headroom/proxy/handlers/anthropic.py` — Add L1+L2+L3 call sites
(after tool assembly, before PRE_SEND)
- `headroom/proxy/handlers/openai.py` — Add L1+L2+L3 call sites
(parallel to Anthropic handler)
- `tests/test_tool_schema_compaction.py` — 42 unit tests covering edge
cases, nested schemas, fail-safe behavior
- `tests/test_system_compaction.py` — Tests for L3 compression,
cache_control preservation, min-chars gating

## Testing

- [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 pytest tests/test_tool_schema_compaction.py tests/test_system_compaction.py tests/test_anthropic_compaction_transforms.py -v
===== 49 passed in 4.96s =====

$ uv run ruff check <changed files>
All checks passed!

$ uv run mypy headroom/proxy/tool_schema_compaction.py headroom/proxy/system_compaction.py headroom/proxy/handlers/anthropic.py headroom/proxy/handlers/openai.py
Success: no issues found in 4 source files

# Manual verification with HEADROOM_TOOL_DESC_MAX_CHARS=120
# Single tool schema: 548→434 bytes (L1, 20.8% saved) → 315 bytes (L2, 27.4% saved)
# Combined: 548→315, 42.5% saved
# Full request with proxy: orig=39179 opt=31988 saved=7191 (18.4% compression)
```

## Real Behavior Proof

- Environment: macOS, Python 3.13, headroom proxy v0.28.0, Claude Code
CLI
- Exact command / steps:
1. Start proxy with `HEADROOM_TOOL_DESC_MAX_CHARS=120
HEADROOM_SYSTEM_COMPACT=1 headroom proxy`
  2. Route Claude Code traffic through proxy
  3. Check `/stats` endpoint for `transforms_applied` and byte savings
- Observed result: L1/L2/L3 transforms applied correctly, ~58% token
reduction on MCP-heavy context
- Not tested: Windows, production deployment

## 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
- [ ] 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
- [ ] I have updated the CHANGELOG.md if applicable

## Screenshots (if applicable)

N/A

## Additional Notes

- L2 and L3 are **opt-in** via env vars. Default behavior is unchanged
(only L1 active).
- All layers have fail-safe fallbacks — if compaction fails or doesn't
reduce size, the original payload passes through unchanged.
- The Anthropic handler now appends `anthropic:tool_schema_compaction`
(L1), `anthropic:tool_desc_compaction` (L2), and
`anthropic:system_compact` (L3) to `transforms_applied`, so `/stats` and
transformation accounting are no longer blind to compression that
changed the request. Covered by handler-level e2e regression in
`tests/test_anthropic_compaction_transforms.py` (positive + negative
cases). The earlier follow-up #1423 is superseded — no longer needed.

---------

Signed-off-by: lg320531124 <lg320531124@users.noreply.github.com>
Co-authored-by: lg320531124 <lg320531124@users.noreply.github.com>
Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
2026-07-15 19:58:51 +00:00

249 lines
7.8 KiB
Python

"""Tests for headroom.proxy.system_compaction — Layer 3 system-prompt compression.
Verifies that system-prompt compaction:
- compresses eligible (long) text blocks via a mock ContentRouter
- preserves short blocks, cache_control, and non-text blocks
- handles both string and content-blocks system field formats
- returns payload unchanged when compaction doesn't help
"""
from __future__ import annotations
from headroom.proxy.system_compaction import (
compact_system_prompt,
system_compact_enabled,
system_compact_min_chars,
)
class _MockCompressResult:
def __init__(self, compressed: str):
self.compressed = compressed
class _MockRouter:
"""Minimal mock of ContentRouter that shortens text by 50%."""
def compress(self, text: str, context: str = "", model: str = "") -> _MockCompressResult:
# Simple "compression": keep first half
half = len(text) // 2
return _MockCompressResult(text[:half])
class _NoopRouter:
"""Mock router whose compression never reduces size."""
def compress(self, text: str, context: str = "", model: str = "") -> _MockCompressResult:
# Return something longer than input
return _MockCompressResult(text + " expanded")
class _FailRouter:
"""Mock router that always raises."""
def compress(self, text: str, context: str = "", model: str = "") -> None:
raise RuntimeError("CCR unavailable")
class TestCompactSystemPromptContentBlocks:
"""Tests for content-blocks format (Anthropic standard)."""
def test_compresses_long_blocks(self) -> None:
payload = {
"model": "claude-sonnet-4-20250514",
"system": [
{"type": "text", "text": "A" * 1000},
{"type": "text", "text": "B" * 600},
],
"messages": [],
}
result, modified, before, after = compact_system_prompt(
payload,
router=_MockRouter(),
model="claude-sonnet-4-20250514",
request_id="test1",
)
assert modified is True
assert after < before
# Each block should be compressed
for block in result["system"]:
if block.get("type") == "text":
assert len(block["text"]) < 1000
def test_preserves_short_blocks(self) -> None:
"""Blocks shorter than min_chars should not be touched."""
payload = {
"system": [
{"type": "text", "text": "Short instruction."},
],
}
result, modified, _, _ = compact_system_prompt(
payload,
router=_MockRouter(),
model="m",
request_id="test2",
)
assert modified is False
assert result["system"][0]["text"] == "Short instruction."
def test_preserves_cache_control(self) -> None:
"""cache_control must survive compaction."""
payload = {
"system": [
{
"type": "text",
"text": "A" * 1000,
"cache_control": {"type": "ephemeral"},
},
],
}
result, modified, _, _ = compact_system_prompt(
payload,
router=_MockRouter(),
model="m",
request_id="test3",
)
assert modified is True
block = result["system"][0]
assert block["cache_control"] == {"type": "ephemeral"}
def test_preserves_non_text_blocks(self) -> None:
payload = {
"system": [
{"type": "text", "text": "A" * 1000},
{"type": "image", "source": {"type": "base64", "data": "..."}},
],
}
result, modified, _, _ = compact_system_prompt(
payload,
router=_MockRouter(),
model="m",
request_id="test4",
)
assert modified is True
# Image block preserved unchanged
image_block = result["system"][1]
assert image_block["type"] == "image"
def test_noop_router_returns_unchanged(self) -> None:
payload = {
"system": [
{"type": "text", "text": "A" * 1000},
],
}
result, modified, _, _ = compact_system_prompt(
payload,
router=_NoopRouter(),
model="m",
request_id="test5",
)
assert modified is False
assert result is payload
def test_failing_router_returns_unchanged(self) -> None:
payload = {
"system": [
{"type": "text", "text": "A" * 1000},
],
}
result, modified, _, _ = compact_system_prompt(
payload,
router=_FailRouter(),
model="m",
request_id="test6",
)
assert modified is False
def test_no_system_field_returns_unchanged(self) -> None:
payload = {"model": "claude-sonnet-4-20250514", "messages": []}
result, modified, _, _ = compact_system_prompt(
payload,
router=_MockRouter(),
model="m",
request_id="test7",
)
assert modified is False
assert result is payload
def test_empty_system_list(self) -> None:
payload = {"system": []}
result, modified, _, _ = compact_system_prompt(
payload,
router=_MockRouter(),
model="m",
request_id="test8",
)
assert modified is False
def test_preserves_non_system_fields(self) -> None:
payload = {
"model": "claude-sonnet-4-20250514",
"max_tokens": 8192,
"system": [
{"type": "text", "text": "A" * 1000},
],
"messages": [{"role": "user", "content": "hi"}],
}
result, _, _, _ = compact_system_prompt(
payload,
router=_MockRouter(),
model="m",
request_id="test9",
)
assert result["model"] == "claude-sonnet-4-20250514"
assert result["max_tokens"] == 8192
assert len(result["messages"]) == 1
class TestCompactSystemPromptString:
"""Tests for string-format system field."""
def test_compresses_long_string(self) -> None:
payload = {
"system": "A" * 1000,
}
result, modified, before, after = compact_system_prompt(
payload,
router=_MockRouter(),
model="m",
request_id="test_s1",
)
assert modified is True
assert after < before
assert len(result["system"]) < 1000
def test_short_string_unchanged(self) -> None:
payload = {
"system": "Short instruction.",
}
result, modified, _, _ = compact_system_prompt(
payload,
router=_MockRouter(),
model="m",
request_id="test_s2",
)
assert modified is False
class TestEnvVarHelpers:
"""Tests for env-var configuration helpers."""
def test_system_compact_enabled_default(self, monkeypatch) -> None:
monkeypatch.delenv("HEADROOM_SYSTEM_COMPACT", raising=False)
# Force re-read
import headroom.proxy.system_compaction as sc
# The function reads env directly, so this should work
assert not sc.system_compact_enabled()
def test_system_compact_enabled_true(self, monkeypatch) -> None:
monkeypatch.setenv("HEADROOM_SYSTEM_COMPACT", "1")
assert system_compact_enabled()
def test_system_compact_min_chars_default(self, monkeypatch) -> None:
monkeypatch.delenv("HEADROOM_SYSTEM_COMPACT_MIN_CHARS", raising=False)
assert system_compact_min_chars() == 500
def test_system_compact_min_chars_custom(self, monkeypatch) -> None:
monkeypatch.setenv("HEADROOM_SYSTEM_COMPACT_MIN_CHARS", "200")
assert system_compact_min_chars() == 200