feat: Add CCR architecture, TOIN telemetry, and DevEx improvements
## Core Features
### Compress-Cache-Retrieve (CCR) Architecture
- Implement reversible compression with automatic retrieval support
- Add CompressionStore for caching original content with TTL-based eviction
- Add CompressionFeedback for learning from retrieval patterns
- Implement tool injection for LLM retrieval capability
- Add MCP server support for CCR operations
- Track retrieval rates to dynamically adjust compression aggressiveness
### Tool Output Intelligence Network (TOIN)
- Implement cross-session pattern learning for tool compression
- Add ToolSignature for structural hashing of tool outputs
- Track compression success rates per strategy (top_n, sample, truncate, etc.)
- Implement privacy-preserving telemetry with SHA256 hashing
- Add persistent storage with JSON file backend
- Support network-effect learning across tool types
### SmartCrusher Enhancements
- Add crushability analysis with variance/uniqueness detection
- Implement statistical anomaly detection for outlier preservation
- Add relevance-based item prioritization using BM25 scoring
- Support multiple compression strategies with quality retention
- Add change point detection for time-series data
- Implement constant factoring for homogeneous datasets
## Developer Experience Improvements
### Exception Hierarchy
- Add HeadroomError base class for all custom exceptions
- Add specific exceptions: ConfigurationError, ProviderError,
StorageError, CompressionError, TokenizationError, CacheError,
ValidationError, TransformError
### Client Enhancements
- Add validate_setup() for configuration verification
- Add get_stats() for in-memory session metrics without DB query
- Track session statistics (requests, tokens saved, cache hits)
### Logging Infrastructure
- Add structured logging to TransformPipeline with token savings
- Add logging to RollingWindow for dropped message tracking
- Add logging to ToolCrusher for compression events
- Add logging to CacheAligner for cache hit/miss detection
- Add logging to SmartCrusher for strategy selection
## Bug Fixes (from deep analysis)
### Critical Fixes
- Fix eviction heap memory leak with stale entry tracking
- Fix hash collision detection in compression store
- Fix strategy truncation desync in TOIN
- Fix non-deterministic set truncation with sorted iteration
- Fix race conditions in lazy initialization with proper locking
- Fix user count double-counting in TOIN metrics
### High Priority Fixes
- Fix unbounded strategy_success_rates growth with LRU eviction
- Fix mutable pattern references with defensive copying
- Fix lock held during file I/O with copy-then-write pattern
- Fix state divergence on eviction with success event recording
- Fix TOIN skip check order for CPU efficiency
- Fix preserve_fields type mismatch (set vs list)
- Fix prioritize_indices exceeding max_items limit
- Fix instance ID collision risk (32-bit to 64-bit hash)
## Testing
- Add comprehensive test suites for CCR, TOIN, and telemetry
- Add crushability detection tests
- Add quality retention tests for compression
- Add integration tests for cross-component data flow
- All 902 tests passing
2026-01-10 10:12:13 -08:00
|
|
|
"""Tests for Compress-Cache-Retrieve (CCR) architecture.
|
|
|
|
|
|
|
|
|
|
These tests verify that:
|
|
|
|
|
1. CompressionStore correctly caches compressed content
|
|
|
|
|
2. SmartCrusher integrates with CompressionStore
|
|
|
|
|
3. Retrieval works correctly (full and search)
|
|
|
|
|
4. Feedback tracking works
|
|
|
|
|
5. TTL expiration works
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
import json
|
|
|
|
|
import time
|
2026-01-10 15:33:44 -08:00
|
|
|
|
feat: Add CCR architecture, TOIN telemetry, and DevEx improvements
## Core Features
### Compress-Cache-Retrieve (CCR) Architecture
- Implement reversible compression with automatic retrieval support
- Add CompressionStore for caching original content with TTL-based eviction
- Add CompressionFeedback for learning from retrieval patterns
- Implement tool injection for LLM retrieval capability
- Add MCP server support for CCR operations
- Track retrieval rates to dynamically adjust compression aggressiveness
### Tool Output Intelligence Network (TOIN)
- Implement cross-session pattern learning for tool compression
- Add ToolSignature for structural hashing of tool outputs
- Track compression success rates per strategy (top_n, sample, truncate, etc.)
- Implement privacy-preserving telemetry with SHA256 hashing
- Add persistent storage with JSON file backend
- Support network-effect learning across tool types
### SmartCrusher Enhancements
- Add crushability analysis with variance/uniqueness detection
- Implement statistical anomaly detection for outlier preservation
- Add relevance-based item prioritization using BM25 scoring
- Support multiple compression strategies with quality retention
- Add change point detection for time-series data
- Implement constant factoring for homogeneous datasets
## Developer Experience Improvements
### Exception Hierarchy
- Add HeadroomError base class for all custom exceptions
- Add specific exceptions: ConfigurationError, ProviderError,
StorageError, CompressionError, TokenizationError, CacheError,
ValidationError, TransformError
### Client Enhancements
- Add validate_setup() for configuration verification
- Add get_stats() for in-memory session metrics without DB query
- Track session statistics (requests, tokens saved, cache hits)
### Logging Infrastructure
- Add structured logging to TransformPipeline with token savings
- Add logging to RollingWindow for dropped message tracking
- Add logging to ToolCrusher for compression events
- Add logging to CacheAligner for cache hit/miss detection
- Add logging to SmartCrusher for strategy selection
## Bug Fixes (from deep analysis)
### Critical Fixes
- Fix eviction heap memory leak with stale entry tracking
- Fix hash collision detection in compression store
- Fix strategy truncation desync in TOIN
- Fix non-deterministic set truncation with sorted iteration
- Fix race conditions in lazy initialization with proper locking
- Fix user count double-counting in TOIN metrics
### High Priority Fixes
- Fix unbounded strategy_success_rates growth with LRU eviction
- Fix mutable pattern references with defensive copying
- Fix lock held during file I/O with copy-then-write pattern
- Fix state divergence on eviction with success event recording
- Fix TOIN skip check order for CPU efficiency
- Fix preserve_fields type mismatch (set vs list)
- Fix prioritize_indices exceeding max_items limit
- Fix instance ID collision risk (32-bit to 64-bit hash)
## Testing
- Add comprehensive test suites for CCR, TOIN, and telemetry
- Add crushability detection tests
- Add quality retention tests for compression
- Add integration tests for cross-component data flow
- All 902 tests passing
2026-01-10 10:12:13 -08:00
|
|
|
import pytest
|
2026-01-10 15:33:44 -08:00
|
|
|
|
feat: Add CCR architecture, TOIN telemetry, and DevEx improvements
## Core Features
### Compress-Cache-Retrieve (CCR) Architecture
- Implement reversible compression with automatic retrieval support
- Add CompressionStore for caching original content with TTL-based eviction
- Add CompressionFeedback for learning from retrieval patterns
- Implement tool injection for LLM retrieval capability
- Add MCP server support for CCR operations
- Track retrieval rates to dynamically adjust compression aggressiveness
### Tool Output Intelligence Network (TOIN)
- Implement cross-session pattern learning for tool compression
- Add ToolSignature for structural hashing of tool outputs
- Track compression success rates per strategy (top_n, sample, truncate, etc.)
- Implement privacy-preserving telemetry with SHA256 hashing
- Add persistent storage with JSON file backend
- Support network-effect learning across tool types
### SmartCrusher Enhancements
- Add crushability analysis with variance/uniqueness detection
- Implement statistical anomaly detection for outlier preservation
- Add relevance-based item prioritization using BM25 scoring
- Support multiple compression strategies with quality retention
- Add change point detection for time-series data
- Implement constant factoring for homogeneous datasets
## Developer Experience Improvements
### Exception Hierarchy
- Add HeadroomError base class for all custom exceptions
- Add specific exceptions: ConfigurationError, ProviderError,
StorageError, CompressionError, TokenizationError, CacheError,
ValidationError, TransformError
### Client Enhancements
- Add validate_setup() for configuration verification
- Add get_stats() for in-memory session metrics without DB query
- Track session statistics (requests, tokens saved, cache hits)
### Logging Infrastructure
- Add structured logging to TransformPipeline with token savings
- Add logging to RollingWindow for dropped message tracking
- Add logging to ToolCrusher for compression events
- Add logging to CacheAligner for cache hit/miss detection
- Add logging to SmartCrusher for strategy selection
## Bug Fixes (from deep analysis)
### Critical Fixes
- Fix eviction heap memory leak with stale entry tracking
- Fix hash collision detection in compression store
- Fix strategy truncation desync in TOIN
- Fix non-deterministic set truncation with sorted iteration
- Fix race conditions in lazy initialization with proper locking
- Fix user count double-counting in TOIN metrics
### High Priority Fixes
- Fix unbounded strategy_success_rates growth with LRU eviction
- Fix mutable pattern references with defensive copying
- Fix lock held during file I/O with copy-then-write pattern
- Fix state divergence on eviction with success event recording
- Fix TOIN skip check order for CPU efficiency
- Fix preserve_fields type mismatch (set vs list)
- Fix prioritize_indices exceeding max_items limit
- Fix instance ID collision risk (32-bit to 64-bit hash)
## Testing
- Add comprehensive test suites for CCR, TOIN, and telemetry
- Add crushability detection tests
- Add quality retention tests for compression
- Add integration tests for cross-component data flow
- All 902 tests passing
2026-01-10 10:12:13 -08:00
|
|
|
from headroom.cache.compression_store import (
|
|
|
|
|
CompressionStore,
|
|
|
|
|
get_compression_store,
|
|
|
|
|
reset_compression_store,
|
|
|
|
|
)
|
2026-01-10 15:33:44 -08:00
|
|
|
from headroom.config import CCRConfig
|
feat: Add CCR architecture, TOIN telemetry, and DevEx improvements
## Core Features
### Compress-Cache-Retrieve (CCR) Architecture
- Implement reversible compression with automatic retrieval support
- Add CompressionStore for caching original content with TTL-based eviction
- Add CompressionFeedback for learning from retrieval patterns
- Implement tool injection for LLM retrieval capability
- Add MCP server support for CCR operations
- Track retrieval rates to dynamically adjust compression aggressiveness
### Tool Output Intelligence Network (TOIN)
- Implement cross-session pattern learning for tool compression
- Add ToolSignature for structural hashing of tool outputs
- Track compression success rates per strategy (top_n, sample, truncate, etc.)
- Implement privacy-preserving telemetry with SHA256 hashing
- Add persistent storage with JSON file backend
- Support network-effect learning across tool types
### SmartCrusher Enhancements
- Add crushability analysis with variance/uniqueness detection
- Implement statistical anomaly detection for outlier preservation
- Add relevance-based item prioritization using BM25 scoring
- Support multiple compression strategies with quality retention
- Add change point detection for time-series data
- Implement constant factoring for homogeneous datasets
## Developer Experience Improvements
### Exception Hierarchy
- Add HeadroomError base class for all custom exceptions
- Add specific exceptions: ConfigurationError, ProviderError,
StorageError, CompressionError, TokenizationError, CacheError,
ValidationError, TransformError
### Client Enhancements
- Add validate_setup() for configuration verification
- Add get_stats() for in-memory session metrics without DB query
- Track session statistics (requests, tokens saved, cache hits)
### Logging Infrastructure
- Add structured logging to TransformPipeline with token savings
- Add logging to RollingWindow for dropped message tracking
- Add logging to ToolCrusher for compression events
- Add logging to CacheAligner for cache hit/miss detection
- Add logging to SmartCrusher for strategy selection
## Bug Fixes (from deep analysis)
### Critical Fixes
- Fix eviction heap memory leak with stale entry tracking
- Fix hash collision detection in compression store
- Fix strategy truncation desync in TOIN
- Fix non-deterministic set truncation with sorted iteration
- Fix race conditions in lazy initialization with proper locking
- Fix user count double-counting in TOIN metrics
### High Priority Fixes
- Fix unbounded strategy_success_rates growth with LRU eviction
- Fix mutable pattern references with defensive copying
- Fix lock held during file I/O with copy-then-write pattern
- Fix state divergence on eviction with success event recording
- Fix TOIN skip check order for CPU efficiency
- Fix preserve_fields type mismatch (set vs list)
- Fix prioritize_indices exceeding max_items limit
- Fix instance ID collision risk (32-bit to 64-bit hash)
## Testing
- Add comprehensive test suites for CCR, TOIN, and telemetry
- Add crushability detection tests
- Add quality retention tests for compression
- Add integration tests for cross-component data flow
- All 902 tests passing
2026-01-10 10:12:13 -08:00
|
|
|
from headroom.transforms.smart_crusher import (
|
|
|
|
|
SmartCrusherConfig,
|
|
|
|
|
smart_crush_tool_output,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestCompressionStore:
|
|
|
|
|
"""Test CompressionStore functionality."""
|
|
|
|
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
|
|
|
def reset_store(self):
|
|
|
|
|
"""Reset global store before each test."""
|
|
|
|
|
reset_compression_store()
|
|
|
|
|
yield
|
|
|
|
|
reset_compression_store()
|
|
|
|
|
|
|
|
|
|
def test_store_and_retrieve(self):
|
|
|
|
|
"""Basic store and retrieve flow."""
|
|
|
|
|
store = CompressionStore()
|
|
|
|
|
|
|
|
|
|
original = json.dumps([{"id": i} for i in range(100)])
|
|
|
|
|
compressed = json.dumps([{"id": i} for i in range(10)])
|
|
|
|
|
|
|
|
|
|
hash_key = store.store(
|
|
|
|
|
original=original,
|
|
|
|
|
compressed=compressed,
|
|
|
|
|
original_tokens=1000,
|
|
|
|
|
compressed_tokens=100,
|
|
|
|
|
original_item_count=100,
|
|
|
|
|
compressed_item_count=10,
|
|
|
|
|
)
|
|
|
|
|
|
2026-01-10 15:33:44 -08:00
|
|
|
assert (
|
|
|
|
|
len(hash_key) == 24
|
|
|
|
|
) # SHA256 truncated to 24 chars (96 bits for collision resistance)
|
feat: Add CCR architecture, TOIN telemetry, and DevEx improvements
## Core Features
### Compress-Cache-Retrieve (CCR) Architecture
- Implement reversible compression with automatic retrieval support
- Add CompressionStore for caching original content with TTL-based eviction
- Add CompressionFeedback for learning from retrieval patterns
- Implement tool injection for LLM retrieval capability
- Add MCP server support for CCR operations
- Track retrieval rates to dynamically adjust compression aggressiveness
### Tool Output Intelligence Network (TOIN)
- Implement cross-session pattern learning for tool compression
- Add ToolSignature for structural hashing of tool outputs
- Track compression success rates per strategy (top_n, sample, truncate, etc.)
- Implement privacy-preserving telemetry with SHA256 hashing
- Add persistent storage with JSON file backend
- Support network-effect learning across tool types
### SmartCrusher Enhancements
- Add crushability analysis with variance/uniqueness detection
- Implement statistical anomaly detection for outlier preservation
- Add relevance-based item prioritization using BM25 scoring
- Support multiple compression strategies with quality retention
- Add change point detection for time-series data
- Implement constant factoring for homogeneous datasets
## Developer Experience Improvements
### Exception Hierarchy
- Add HeadroomError base class for all custom exceptions
- Add specific exceptions: ConfigurationError, ProviderError,
StorageError, CompressionError, TokenizationError, CacheError,
ValidationError, TransformError
### Client Enhancements
- Add validate_setup() for configuration verification
- Add get_stats() for in-memory session metrics without DB query
- Track session statistics (requests, tokens saved, cache hits)
### Logging Infrastructure
- Add structured logging to TransformPipeline with token savings
- Add logging to RollingWindow for dropped message tracking
- Add logging to ToolCrusher for compression events
- Add logging to CacheAligner for cache hit/miss detection
- Add logging to SmartCrusher for strategy selection
## Bug Fixes (from deep analysis)
### Critical Fixes
- Fix eviction heap memory leak with stale entry tracking
- Fix hash collision detection in compression store
- Fix strategy truncation desync in TOIN
- Fix non-deterministic set truncation with sorted iteration
- Fix race conditions in lazy initialization with proper locking
- Fix user count double-counting in TOIN metrics
### High Priority Fixes
- Fix unbounded strategy_success_rates growth with LRU eviction
- Fix mutable pattern references with defensive copying
- Fix lock held during file I/O with copy-then-write pattern
- Fix state divergence on eviction with success event recording
- Fix TOIN skip check order for CPU efficiency
- Fix preserve_fields type mismatch (set vs list)
- Fix prioritize_indices exceeding max_items limit
- Fix instance ID collision risk (32-bit to 64-bit hash)
## Testing
- Add comprehensive test suites for CCR, TOIN, and telemetry
- Add crushability detection tests
- Add quality retention tests for compression
- Add integration tests for cross-component data flow
- All 902 tests passing
2026-01-10 10:12:13 -08:00
|
|
|
|
|
|
|
|
entry = store.retrieve(hash_key)
|
|
|
|
|
assert entry is not None
|
|
|
|
|
assert entry.original_content == original
|
|
|
|
|
assert entry.compressed_content == compressed
|
|
|
|
|
assert entry.original_tokens == 1000
|
|
|
|
|
assert entry.compressed_tokens == 100
|
|
|
|
|
|
|
|
|
|
def test_retrieve_nonexistent(self):
|
|
|
|
|
"""Retrieve returns None for nonexistent hash."""
|
|
|
|
|
store = CompressionStore()
|
|
|
|
|
entry = store.retrieve("nonexistent1234")
|
|
|
|
|
assert entry is None
|
|
|
|
|
|
|
|
|
|
def test_ttl_expiration(self):
|
|
|
|
|
"""Entries expire after TTL."""
|
|
|
|
|
store = CompressionStore(default_ttl=1) # 1 second TTL
|
|
|
|
|
|
|
|
|
|
hash_key = store.store(
|
|
|
|
|
original="[1,2,3]",
|
|
|
|
|
compressed="[1]",
|
|
|
|
|
ttl=1,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Should exist immediately
|
|
|
|
|
assert store.exists(hash_key)
|
|
|
|
|
|
|
|
|
|
# Wait for expiration
|
|
|
|
|
time.sleep(1.1)
|
|
|
|
|
|
|
|
|
|
# Should be expired
|
|
|
|
|
assert not store.exists(hash_key)
|
|
|
|
|
entry = store.retrieve(hash_key)
|
|
|
|
|
assert entry is None
|
|
|
|
|
|
|
|
|
|
def test_eviction_at_capacity(self):
|
|
|
|
|
"""Oldest entries evicted when at capacity."""
|
|
|
|
|
store = CompressionStore(max_entries=3)
|
|
|
|
|
|
|
|
|
|
hashes = []
|
|
|
|
|
for i in range(5):
|
|
|
|
|
h = store.store(
|
|
|
|
|
original=f"original_{i}",
|
|
|
|
|
compressed=f"compressed_{i}",
|
|
|
|
|
)
|
|
|
|
|
hashes.append(h)
|
|
|
|
|
time.sleep(0.01) # Ensure different timestamps
|
|
|
|
|
|
|
|
|
|
# Only last 3 should exist
|
|
|
|
|
assert not store.exists(hashes[0])
|
|
|
|
|
assert not store.exists(hashes[1])
|
|
|
|
|
assert store.exists(hashes[2])
|
|
|
|
|
assert store.exists(hashes[3])
|
|
|
|
|
assert store.exists(hashes[4])
|
|
|
|
|
|
|
|
|
|
def test_retrieval_tracking(self):
|
|
|
|
|
"""Retrieval events are tracked for feedback."""
|
|
|
|
|
store = CompressionStore(enable_feedback=True)
|
|
|
|
|
|
|
|
|
|
hash_key = store.store(
|
|
|
|
|
original="[1,2,3]",
|
|
|
|
|
compressed="[1]",
|
|
|
|
|
tool_name="test_tool",
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Retrieve multiple times
|
|
|
|
|
store.retrieve(hash_key)
|
|
|
|
|
store.retrieve(hash_key, query="test query")
|
|
|
|
|
|
|
|
|
|
events = store.get_retrieval_events(limit=10)
|
|
|
|
|
assert len(events) >= 2
|
|
|
|
|
|
fix(ccr): make headroom_retrieve a hash-only full-content lookup (#1532)
The optional `query` parameter on headroom_retrieve routed retrieval
through CompressionStore.search(), which BM25-scored the items inside a
single cached blob and dropped everything below a 0.3 relevance floor.
On small per-blob corpora with conversational queries this returned an
empty result the large majority of the time, so the LLM saw "nothing
found" for content that was actually present — pushing users to turn
compression off entirely.
Retrieval is fundamentally a hash lookup (this already matches the Rust
proxy's CCR store, which is put/get only — "no BM25 search"). Remove the
query/search path end to end and always return the full original
content:
Core (Python proxy):
- tool schemas (anthropic/openai/google) drop the `query` property
- parse_tool_call returns the hash (str | None) instead of (hash, query)
- response handler, proxy POST/GET/tool-call handlers, the MCP retrieve
tool, and the streaming feedback recorders retrieve by hash only
- proactive context-tracker expansion always restores full content
- delete CompressionStore.search() and its BM25 machinery (the bm25
module stays — it is still used by relevance/)
- CCRToolCall.query, CCRToolResult.was_search, and
ExpansionRecommendation.expand_full/search_query are removed
Plugins (advertised a now-defunct query param to the LLM):
- hermes (Python), openclaw + opencode (TypeScript) retrieve tools drop
`query` from their schemas, signatures, request URLs, and tests
Benchmarks/docs:
- ccr_regression + adversarial benchmarks switch from store.search() to
full hash retrieval (search input-injection tests repurposed to the
hash, the only remaining input surface)
- wiki/ARCHITECTURE.md, wiki/ccr.md, docs/content/docs/ccr.mdx,
config.py and store docstrings updated to describe hash-only retrieval
Tests updated to assert full-content retrieval and guard the removed
surface; the full CCR/proxy/store/TOIN suite passes. ruff + mypy clean.
## Description
<!-- Briefly explain the change and why it is needed. -->
Closes #
## Type of Change
- [ ] 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
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
-
## Testing
<!-- Check what you actually ran, then paste the real command output
below. -->
- [ ] Unit tests pass (`pytest`)
- [ ] Linting passes (`ruff check .`)
- [ ] Type checking passes (`mypy headroom`)
- [ ] New tests added for new functionality
- [ ] Manual testing performed
### Test Output
```text
# Paste relevant command output or artifact links here
```
## Real Behavior Proof
- Environment:
- Exact command / steps:
- Observed result:
- Not tested:
## Review Readiness
- [ ] I have performed a self-review
- [ ] This PR is ready for human review
## Checklist
- [ ] My code follows the project's style guidelines
- [ ] I have performed a self-review of my code
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] I have updated the CHANGELOG.md if applicable
## Screenshots (if applicable)
Add screenshots to help explain your changes.
## Additional Notes
<!-- Mention any N/A checklist items, tradeoffs, follow-ups, or
maintainer context. -->
2026-06-28 10:32:43 -07:00
|
|
|
# Check event details — retrieval is always full
|
feat: Add CCR architecture, TOIN telemetry, and DevEx improvements
## Core Features
### Compress-Cache-Retrieve (CCR) Architecture
- Implement reversible compression with automatic retrieval support
- Add CompressionStore for caching original content with TTL-based eviction
- Add CompressionFeedback for learning from retrieval patterns
- Implement tool injection for LLM retrieval capability
- Add MCP server support for CCR operations
- Track retrieval rates to dynamically adjust compression aggressiveness
### Tool Output Intelligence Network (TOIN)
- Implement cross-session pattern learning for tool compression
- Add ToolSignature for structural hashing of tool outputs
- Track compression success rates per strategy (top_n, sample, truncate, etc.)
- Implement privacy-preserving telemetry with SHA256 hashing
- Add persistent storage with JSON file backend
- Support network-effect learning across tool types
### SmartCrusher Enhancements
- Add crushability analysis with variance/uniqueness detection
- Implement statistical anomaly detection for outlier preservation
- Add relevance-based item prioritization using BM25 scoring
- Support multiple compression strategies with quality retention
- Add change point detection for time-series data
- Implement constant factoring for homogeneous datasets
## Developer Experience Improvements
### Exception Hierarchy
- Add HeadroomError base class for all custom exceptions
- Add specific exceptions: ConfigurationError, ProviderError,
StorageError, CompressionError, TokenizationError, CacheError,
ValidationError, TransformError
### Client Enhancements
- Add validate_setup() for configuration verification
- Add get_stats() for in-memory session metrics without DB query
- Track session statistics (requests, tokens saved, cache hits)
### Logging Infrastructure
- Add structured logging to TransformPipeline with token savings
- Add logging to RollingWindow for dropped message tracking
- Add logging to ToolCrusher for compression events
- Add logging to CacheAligner for cache hit/miss detection
- Add logging to SmartCrusher for strategy selection
## Bug Fixes (from deep analysis)
### Critical Fixes
- Fix eviction heap memory leak with stale entry tracking
- Fix hash collision detection in compression store
- Fix strategy truncation desync in TOIN
- Fix non-deterministic set truncation with sorted iteration
- Fix race conditions in lazy initialization with proper locking
- Fix user count double-counting in TOIN metrics
### High Priority Fixes
- Fix unbounded strategy_success_rates growth with LRU eviction
- Fix mutable pattern references with defensive copying
- Fix lock held during file I/O with copy-then-write pattern
- Fix state divergence on eviction with success event recording
- Fix TOIN skip check order for CPU efficiency
- Fix preserve_fields type mismatch (set vs list)
- Fix prioritize_indices exceeding max_items limit
- Fix instance ID collision risk (32-bit to 64-bit hash)
## Testing
- Add comprehensive test suites for CCR, TOIN, and telemetry
- Add crushability detection tests
- Add quality retention tests for compression
- Add integration tests for cross-component data flow
- All 902 tests passing
2026-01-10 10:12:13 -08:00
|
|
|
assert any(e.retrieval_type == "full" for e in events)
|
|
|
|
|
|
|
|
|
|
def test_access_tracking_on_entry(self):
|
|
|
|
|
"""Entry tracks access count and queries."""
|
|
|
|
|
store = CompressionStore()
|
|
|
|
|
|
|
|
|
|
hash_key = store.store(
|
|
|
|
|
original=json.dumps([{"id": i} for i in range(10)]),
|
|
|
|
|
compressed="[]",
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Access multiple times with queries
|
|
|
|
|
store.retrieve(hash_key, query="first query")
|
|
|
|
|
store.retrieve(hash_key, query="second query")
|
|
|
|
|
store.retrieve(hash_key, query="first query") # Duplicate
|
|
|
|
|
|
|
|
|
|
entry = store.retrieve(hash_key)
|
|
|
|
|
assert entry.retrieval_count >= 3
|
|
|
|
|
assert "first query" in entry.search_queries
|
|
|
|
|
assert "second query" in entry.search_queries
|
|
|
|
|
|
|
|
|
|
def test_stats(self):
|
|
|
|
|
"""Store statistics are accurate."""
|
|
|
|
|
store = CompressionStore()
|
|
|
|
|
|
|
|
|
|
store.store(
|
|
|
|
|
original="x" * 100,
|
|
|
|
|
compressed="x" * 10,
|
|
|
|
|
original_tokens=100,
|
|
|
|
|
compressed_tokens=10,
|
|
|
|
|
)
|
|
|
|
|
store.store(
|
|
|
|
|
original="y" * 200,
|
|
|
|
|
compressed="y" * 20,
|
|
|
|
|
original_tokens=200,
|
|
|
|
|
compressed_tokens=20,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
stats = store.get_stats()
|
|
|
|
|
assert stats["entry_count"] == 2
|
|
|
|
|
assert stats["total_original_tokens"] == 300
|
|
|
|
|
assert stats["total_compressed_tokens"] == 30
|
|
|
|
|
|
|
|
|
|
def test_global_store_singleton(self):
|
|
|
|
|
"""Global store uses singleton pattern."""
|
|
|
|
|
reset_compression_store()
|
|
|
|
|
|
|
|
|
|
store1 = get_compression_store()
|
|
|
|
|
store2 = get_compression_store()
|
|
|
|
|
|
|
|
|
|
assert store1 is store2
|
|
|
|
|
|
|
|
|
|
def test_thread_safety(self):
|
|
|
|
|
"""Store is thread-safe."""
|
|
|
|
|
import threading
|
|
|
|
|
|
|
|
|
|
store = CompressionStore()
|
|
|
|
|
hashes = []
|
|
|
|
|
lock = threading.Lock()
|
|
|
|
|
|
|
|
|
|
def store_item(i):
|
|
|
|
|
h = store.store(
|
|
|
|
|
original=f"original_{i}",
|
|
|
|
|
compressed=f"compressed_{i}",
|
|
|
|
|
)
|
|
|
|
|
with lock:
|
|
|
|
|
hashes.append(h)
|
|
|
|
|
|
|
|
|
|
threads = [threading.Thread(target=store_item, args=(i,)) for i in range(10)]
|
|
|
|
|
for t in threads:
|
|
|
|
|
t.start()
|
|
|
|
|
for t in threads:
|
|
|
|
|
t.join()
|
|
|
|
|
|
|
|
|
|
assert len(hashes) == 10
|
|
|
|
|
for h in hashes:
|
|
|
|
|
assert store.exists(h)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestCCRConfig:
|
|
|
|
|
"""Test CCR configuration options."""
|
|
|
|
|
|
|
|
|
|
def test_default_config(self):
|
|
|
|
|
"""Default CCR config values."""
|
|
|
|
|
config = CCRConfig()
|
|
|
|
|
assert config.enabled is True
|
|
|
|
|
assert config.store_max_entries == 1000
|
feat: compression extraction — Rust knob exposure, CCR hardening, traffic audits (#818)
## Description
A data-driven push for better compression savings without accuracy loss,
in four parts: expose and tune the Rust compressor knobs, harden the CCR
retrieval store, add traffic-audit tooling that sizes opportunities from
real transcripts, and introduce **read maturation** — a new,
live-validated mechanism that compresses Read outputs *before* they ever
enter the provider prefix cache.
## Type of Change
- [x] 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
### 1. Rust compressor extraction
- Expose `lossless_min_savings_ratio` end-to-end and lower the default
0.30 → 0.15 (lockstep across Rust, PyO3, and both Python config classes)
so the lossless Table/CSV compaction path wins more often.
- Expose the `CompactConfig` heuristics (core-field fraction,
heterogeneity ratio, flatten cap, bucket bounds) through PyO3 + Python.
- `SearchCompressor` grouped-by-file output (`rg --heading` style — path
once per file instead of per match). Library default off; the proxy
enables it in token mode.
- Complete `factor_out_constants`: constant fields now emit once in a
`_constant_fields` sentinel with slim rows (defensive per-item value
match; default off).
- `ContentRouter` accepts a SmartCrusher config override and the
search-grouping knob.
### 2. CCR store hardening
- Session-scale TTL: 300s → 1800s (CCRConfig, CompressionEntry,
CompressionStore, Rust `DEFAULT_TTL` — lockstep).
- **SQLite is the default CCR backend** (`~/.headroom/ccr_store.db`,
WAL): survives proxy restarts and is shared across workers.
`HEADROOM_CCR_BACKEND=memory` opts out.
- Multi-worker safety: `busy_timeout`, and corruption detection narrowed
so transient `SQLITE_BUSY` errors can never trigger database deletion.
- Data-at-rest hygiene: `chmod 600` on db + sidecars, expired rows swept
at open.
- Retrieval-miss messages are actionable (re-read the file / re-run the
command).
### 3. Traffic audit tooling (measure before tuning)
- `headroom audit-reads`: sizes Read opportunities from local Claude
Code transcripts (read share, stale %, line-number overhead, context
residency, cache-death windows).
- `--simulate-maturation`: Mechanism B risk sizing (re-read rates,
never-touched-again share, quiesce coverage, at-risk edits).
- `--codex`: shell-read classifier for Codex transcripts (rtk-wrapper
aware, workdir resolution).
- Findings that shaped this PR (81 sessions): Reads are 67% of tool
bytes; median Read lingers 118 turns (~13x lifetime cost); a prototyped
repeat-Read dedup measured 0.1% and was **removed** rather than shipped
as dead code.
### 4. Read maturation (Mechanism B) — experimental, default OFF
- Activity-based: a fresh large Read is held **out** of the provider
cache (trailing breakpoint relocated before it), stays verbatim while
its file is active, and matures into a CCR-backed marker once the file
is quiet for `quiesce_turns` (default 5; `max_hold_turns` bounds busy
files).
- Only the final compressed form ever enters the cache — **no cached
byte is ever mutated**; matured markers replay byte-identically.
- Wired into the Anthropic handler behind `--read-maturation` /
`HEADROOM_READ_MATURATION=1`; session state rides on the prefix tracker;
advisory (can never fail a request).
- Live-validated against the Anthropic API: held content excluded from
cache_creation; after maturation the prior cached prefix still served —
the no-bust invariant holds end-to-end.
### 5. Rebase / CI fixups (this update)
- Rebased onto latest `main` (was 28 commits behind): picks up `ci: pass
CODECOV_TOKEN to coverage uploads (#968)`, which is what was turning the
4 test shards red — the tests themselves passed (1528) but the post-test
codecov upload exited non-zero on a protected branch.
- Resolved the duplicate `lossless_min_savings_ratio` that two
independent main/branch additions left in `SmartCrusherConfig` and the
Rust-config kwarg (import-time `SyntaxError` + mypy `no-redef`).
- Aligned CCR tests with the new defaults (SQLite backend, 1800s TTL)
across `test_ccr`, `test_adapter_hooks`, `test_compression_store`,
`test_proxy_ccr`, and the lossy row-drop bridge test.
## 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
- [ ] Manual testing performed
### Test Output
```text
$ python -m pytest tests/test_proxy_ccr.py tests/test_ccr.py tests/test_compression_store.py tests/test_adapter_hooks.py tests/test_ccr_row_drop_store_bridge.py -q
170 passed, 4 warnings in 42.49s
$ python -m pytest tests/test_audit_reads.py tests/test_audit_codex.py tests/test_read_maturation.py tests/test_transforms_content_router.py tests/test_smart_crusher_toin_attachment.py -q
83 passed
$ mypy headroom/
Success: no issues found in 365 source files
$ python -m compileall headroom/ -q
COMPILE-OK
# CI (run 27488990477, pre-rebase head): all 4 shards ran to completion —
# "1528 passed, 120 skipped, 4922 deselected"
# The red shards were the codecov upload step, not test failures; fixed by
# the #968 rebase above.
```
## Real Behavior Proof
- Environment: macOS (darwin), Python 3.12 venv; branch
`feat/compression-extraction` rebased onto `origin/main` (head
7cb0f43b); GitHub Actions CI run 27488990477 for the test shards
- Exact command / steps: rebased onto latest main (clean, 13 commits
replayed, 0 conflicts); ran the pytest suites and mypy above locally;
inspected CI shard logs to confirm the failure was the codecov upload,
not the test phase
- Observed result: 253 targeted tests pass locally; mypy clean on 365
files; CI test phase reports `1528 passed, 120 skipped`; the only red
step (codecov `upload-coverage` → "Token required because branch is
protected") is resolved by the rebased-in #968 CODECOV_TOKEN fix
- Not tested: the read-maturation live-API no-bust validation
(`tests/test_live/`) was not re-run in this rebase pass (requires
provider keys); it was validated when the feature first landed, and no
maturation code changed in the rebase — only CCR-default test assertions
and the duplicate-field resolution
## 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
## Additional Notes
CHANGELOG is generated by release-please from the conventional commits,
so the CHANGELOG box is intentionally left unchecked. "Manual testing
performed" is unchecked deliberately — see `Real Behavior Proof` → `Not
tested` for the exact boundary (the live-API maturation validation was
not re-run in this rebase pass).
### Follow-ups (tracked, not in this PR)
- Mechanism B provider extensions: OpenAI-family wiring (no breakpoint
hold — bounded near-tail bust) and the Codex runtime read-detector (the
audit classifier is the prototype).
- Pilot enablement playbook: run `audit-reads --simulate-maturation` on
target traffic → pick `quiesce_turns` → enable via env → watch cache hit
rate + `read_maturation:N` transform tags.
2026-06-16 20:21:13 -07:00
|
|
|
assert config.store_ttl_seconds == 1800 # session-scale (was 300)
|
feat: Add CCR architecture, TOIN telemetry, and DevEx improvements
## Core Features
### Compress-Cache-Retrieve (CCR) Architecture
- Implement reversible compression with automatic retrieval support
- Add CompressionStore for caching original content with TTL-based eviction
- Add CompressionFeedback for learning from retrieval patterns
- Implement tool injection for LLM retrieval capability
- Add MCP server support for CCR operations
- Track retrieval rates to dynamically adjust compression aggressiveness
### Tool Output Intelligence Network (TOIN)
- Implement cross-session pattern learning for tool compression
- Add ToolSignature for structural hashing of tool outputs
- Track compression success rates per strategy (top_n, sample, truncate, etc.)
- Implement privacy-preserving telemetry with SHA256 hashing
- Add persistent storage with JSON file backend
- Support network-effect learning across tool types
### SmartCrusher Enhancements
- Add crushability analysis with variance/uniqueness detection
- Implement statistical anomaly detection for outlier preservation
- Add relevance-based item prioritization using BM25 scoring
- Support multiple compression strategies with quality retention
- Add change point detection for time-series data
- Implement constant factoring for homogeneous datasets
## Developer Experience Improvements
### Exception Hierarchy
- Add HeadroomError base class for all custom exceptions
- Add specific exceptions: ConfigurationError, ProviderError,
StorageError, CompressionError, TokenizationError, CacheError,
ValidationError, TransformError
### Client Enhancements
- Add validate_setup() for configuration verification
- Add get_stats() for in-memory session metrics without DB query
- Track session statistics (requests, tokens saved, cache hits)
### Logging Infrastructure
- Add structured logging to TransformPipeline with token savings
- Add logging to RollingWindow for dropped message tracking
- Add logging to ToolCrusher for compression events
- Add logging to CacheAligner for cache hit/miss detection
- Add logging to SmartCrusher for strategy selection
## Bug Fixes (from deep analysis)
### Critical Fixes
- Fix eviction heap memory leak with stale entry tracking
- Fix hash collision detection in compression store
- Fix strategy truncation desync in TOIN
- Fix non-deterministic set truncation with sorted iteration
- Fix race conditions in lazy initialization with proper locking
- Fix user count double-counting in TOIN metrics
### High Priority Fixes
- Fix unbounded strategy_success_rates growth with LRU eviction
- Fix mutable pattern references with defensive copying
- Fix lock held during file I/O with copy-then-write pattern
- Fix state divergence on eviction with success event recording
- Fix TOIN skip check order for CPU efficiency
- Fix preserve_fields type mismatch (set vs list)
- Fix prioritize_indices exceeding max_items limit
- Fix instance ID collision risk (32-bit to 64-bit hash)
## Testing
- Add comprehensive test suites for CCR, TOIN, and telemetry
- Add crushability detection tests
- Add quality retention tests for compression
- Add integration tests for cross-component data flow
- All 902 tests passing
2026-01-10 10:12:13 -08:00
|
|
|
assert config.inject_retrieval_marker is True
|
|
|
|
|
assert config.feedback_enabled is True
|
|
|
|
|
assert config.min_items_to_cache == 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestCCRFeedbackLoop:
|
|
|
|
|
"""Test CCR feedback tracking for learning."""
|
|
|
|
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
|
|
|
def reset_store(self):
|
|
|
|
|
"""Reset global store before each test."""
|
|
|
|
|
reset_compression_store()
|
|
|
|
|
yield
|
|
|
|
|
reset_compression_store()
|
|
|
|
|
|
|
|
|
|
def test_retrieval_events_logged(self):
|
|
|
|
|
"""Retrieval events are logged for feedback."""
|
|
|
|
|
store = CompressionStore(enable_feedback=True)
|
|
|
|
|
|
|
|
|
|
items = [{"id": i, "data": f"item_{i}"} for i in range(50)]
|
|
|
|
|
hash_key = store.store(
|
|
|
|
|
original=json.dumps(items),
|
|
|
|
|
compressed=json.dumps(items[:10]),
|
|
|
|
|
original_item_count=50,
|
|
|
|
|
compressed_item_count=10,
|
|
|
|
|
tool_name="search_api",
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Simulate retrievals
|
|
|
|
|
store.retrieve(hash_key)
|
fix(ccr): make headroom_retrieve a hash-only full-content lookup (#1532)
The optional `query` parameter on headroom_retrieve routed retrieval
through CompressionStore.search(), which BM25-scored the items inside a
single cached blob and dropped everything below a 0.3 relevance floor.
On small per-blob corpora with conversational queries this returned an
empty result the large majority of the time, so the LLM saw "nothing
found" for content that was actually present — pushing users to turn
compression off entirely.
Retrieval is fundamentally a hash lookup (this already matches the Rust
proxy's CCR store, which is put/get only — "no BM25 search"). Remove the
query/search path end to end and always return the full original
content:
Core (Python proxy):
- tool schemas (anthropic/openai/google) drop the `query` property
- parse_tool_call returns the hash (str | None) instead of (hash, query)
- response handler, proxy POST/GET/tool-call handlers, the MCP retrieve
tool, and the streaming feedback recorders retrieve by hash only
- proactive context-tracker expansion always restores full content
- delete CompressionStore.search() and its BM25 machinery (the bm25
module stays — it is still used by relevance/)
- CCRToolCall.query, CCRToolResult.was_search, and
ExpansionRecommendation.expand_full/search_query are removed
Plugins (advertised a now-defunct query param to the LLM):
- hermes (Python), openclaw + opencode (TypeScript) retrieve tools drop
`query` from their schemas, signatures, request URLs, and tests
Benchmarks/docs:
- ccr_regression + adversarial benchmarks switch from store.search() to
full hash retrieval (search input-injection tests repurposed to the
hash, the only remaining input surface)
- wiki/ARCHITECTURE.md, wiki/ccr.md, docs/content/docs/ccr.mdx,
config.py and store docstrings updated to describe hash-only retrieval
Tests updated to assert full-content retrieval and guard the removed
surface; the full CCR/proxy/store/TOIN suite passes. ruff + mypy clean.
## Description
<!-- Briefly explain the change and why it is needed. -->
Closes #
## Type of Change
- [ ] 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
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
-
## Testing
<!-- Check what you actually ran, then paste the real command output
below. -->
- [ ] Unit tests pass (`pytest`)
- [ ] Linting passes (`ruff check .`)
- [ ] Type checking passes (`mypy headroom`)
- [ ] New tests added for new functionality
- [ ] Manual testing performed
### Test Output
```text
# Paste relevant command output or artifact links here
```
## Real Behavior Proof
- Environment:
- Exact command / steps:
- Observed result:
- Not tested:
## Review Readiness
- [ ] I have performed a self-review
- [ ] This PR is ready for human review
## Checklist
- [ ] My code follows the project's style guidelines
- [ ] I have performed a self-review of my code
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] I have updated the CHANGELOG.md if applicable
## Screenshots (if applicable)
Add screenshots to help explain your changes.
## Additional Notes
<!-- Mention any N/A checklist items, tradeoffs, follow-ups, or
maintainer context. -->
2026-06-28 10:32:43 -07:00
|
|
|
store.retrieve(hash_key)
|
|
|
|
|
store.retrieve(hash_key)
|
feat: Add CCR architecture, TOIN telemetry, and DevEx improvements
## Core Features
### Compress-Cache-Retrieve (CCR) Architecture
- Implement reversible compression with automatic retrieval support
- Add CompressionStore for caching original content with TTL-based eviction
- Add CompressionFeedback for learning from retrieval patterns
- Implement tool injection for LLM retrieval capability
- Add MCP server support for CCR operations
- Track retrieval rates to dynamically adjust compression aggressiveness
### Tool Output Intelligence Network (TOIN)
- Implement cross-session pattern learning for tool compression
- Add ToolSignature for structural hashing of tool outputs
- Track compression success rates per strategy (top_n, sample, truncate, etc.)
- Implement privacy-preserving telemetry with SHA256 hashing
- Add persistent storage with JSON file backend
- Support network-effect learning across tool types
### SmartCrusher Enhancements
- Add crushability analysis with variance/uniqueness detection
- Implement statistical anomaly detection for outlier preservation
- Add relevance-based item prioritization using BM25 scoring
- Support multiple compression strategies with quality retention
- Add change point detection for time-series data
- Implement constant factoring for homogeneous datasets
## Developer Experience Improvements
### Exception Hierarchy
- Add HeadroomError base class for all custom exceptions
- Add specific exceptions: ConfigurationError, ProviderError,
StorageError, CompressionError, TokenizationError, CacheError,
ValidationError, TransformError
### Client Enhancements
- Add validate_setup() for configuration verification
- Add get_stats() for in-memory session metrics without DB query
- Track session statistics (requests, tokens saved, cache hits)
### Logging Infrastructure
- Add structured logging to TransformPipeline with token savings
- Add logging to RollingWindow for dropped message tracking
- Add logging to ToolCrusher for compression events
- Add logging to CacheAligner for cache hit/miss detection
- Add logging to SmartCrusher for strategy selection
## Bug Fixes (from deep analysis)
### Critical Fixes
- Fix eviction heap memory leak with stale entry tracking
- Fix hash collision detection in compression store
- Fix strategy truncation desync in TOIN
- Fix non-deterministic set truncation with sorted iteration
- Fix race conditions in lazy initialization with proper locking
- Fix user count double-counting in TOIN metrics
### High Priority Fixes
- Fix unbounded strategy_success_rates growth with LRU eviction
- Fix mutable pattern references with defensive copying
- Fix lock held during file I/O with copy-then-write pattern
- Fix state divergence on eviction with success event recording
- Fix TOIN skip check order for CPU efficiency
- Fix preserve_fields type mismatch (set vs list)
- Fix prioritize_indices exceeding max_items limit
- Fix instance ID collision risk (32-bit to 64-bit hash)
## Testing
- Add comprehensive test suites for CCR, TOIN, and telemetry
- Add crushability detection tests
- Add quality retention tests for compression
- Add integration tests for cross-component data flow
- All 902 tests passing
2026-01-10 10:12:13 -08:00
|
|
|
|
|
|
|
|
events = store.get_retrieval_events(limit=10)
|
|
|
|
|
|
|
|
|
|
# Should have logged all retrievals
|
|
|
|
|
assert len(events) >= 3
|
|
|
|
|
|
fix(ccr): make headroom_retrieve a hash-only full-content lookup (#1532)
The optional `query` parameter on headroom_retrieve routed retrieval
through CompressionStore.search(), which BM25-scored the items inside a
single cached blob and dropped everything below a 0.3 relevance floor.
On small per-blob corpora with conversational queries this returned an
empty result the large majority of the time, so the LLM saw "nothing
found" for content that was actually present — pushing users to turn
compression off entirely.
Retrieval is fundamentally a hash lookup (this already matches the Rust
proxy's CCR store, which is put/get only — "no BM25 search"). Remove the
query/search path end to end and always return the full original
content:
Core (Python proxy):
- tool schemas (anthropic/openai/google) drop the `query` property
- parse_tool_call returns the hash (str | None) instead of (hash, query)
- response handler, proxy POST/GET/tool-call handlers, the MCP retrieve
tool, and the streaming feedback recorders retrieve by hash only
- proactive context-tracker expansion always restores full content
- delete CompressionStore.search() and its BM25 machinery (the bm25
module stays — it is still used by relevance/)
- CCRToolCall.query, CCRToolResult.was_search, and
ExpansionRecommendation.expand_full/search_query are removed
Plugins (advertised a now-defunct query param to the LLM):
- hermes (Python), openclaw + opencode (TypeScript) retrieve tools drop
`query` from their schemas, signatures, request URLs, and tests
Benchmarks/docs:
- ccr_regression + adversarial benchmarks switch from store.search() to
full hash retrieval (search input-injection tests repurposed to the
hash, the only remaining input surface)
- wiki/ARCHITECTURE.md, wiki/ccr.md, docs/content/docs/ccr.mdx,
config.py and store docstrings updated to describe hash-only retrieval
Tests updated to assert full-content retrieval and guard the removed
surface; the full CCR/proxy/store/TOIN suite passes. ruff + mypy clean.
## Description
<!-- Briefly explain the change and why it is needed. -->
Closes #
## Type of Change
- [ ] 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
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
-
## Testing
<!-- Check what you actually ran, then paste the real command output
below. -->
- [ ] Unit tests pass (`pytest`)
- [ ] Linting passes (`ruff check .`)
- [ ] Type checking passes (`mypy headroom`)
- [ ] New tests added for new functionality
- [ ] Manual testing performed
### Test Output
```text
# Paste relevant command output or artifact links here
```
## Real Behavior Proof
- Environment:
- Exact command / steps:
- Observed result:
- Not tested:
## Review Readiness
- [ ] I have performed a self-review
- [ ] This PR is ready for human review
## Checklist
- [ ] My code follows the project's style guidelines
- [ ] I have performed a self-review of my code
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] I have updated the CHANGELOG.md if applicable
## Screenshots (if applicable)
Add screenshots to help explain your changes.
## Additional Notes
<!-- Mention any N/A checklist items, tradeoffs, follow-ups, or
maintainer context. -->
2026-06-28 10:32:43 -07:00
|
|
|
# Check event types — retrieval is always full
|
feat: Add CCR architecture, TOIN telemetry, and DevEx improvements
## Core Features
### Compress-Cache-Retrieve (CCR) Architecture
- Implement reversible compression with automatic retrieval support
- Add CompressionStore for caching original content with TTL-based eviction
- Add CompressionFeedback for learning from retrieval patterns
- Implement tool injection for LLM retrieval capability
- Add MCP server support for CCR operations
- Track retrieval rates to dynamically adjust compression aggressiveness
### Tool Output Intelligence Network (TOIN)
- Implement cross-session pattern learning for tool compression
- Add ToolSignature for structural hashing of tool outputs
- Track compression success rates per strategy (top_n, sample, truncate, etc.)
- Implement privacy-preserving telemetry with SHA256 hashing
- Add persistent storage with JSON file backend
- Support network-effect learning across tool types
### SmartCrusher Enhancements
- Add crushability analysis with variance/uniqueness detection
- Implement statistical anomaly detection for outlier preservation
- Add relevance-based item prioritization using BM25 scoring
- Support multiple compression strategies with quality retention
- Add change point detection for time-series data
- Implement constant factoring for homogeneous datasets
## Developer Experience Improvements
### Exception Hierarchy
- Add HeadroomError base class for all custom exceptions
- Add specific exceptions: ConfigurationError, ProviderError,
StorageError, CompressionError, TokenizationError, CacheError,
ValidationError, TransformError
### Client Enhancements
- Add validate_setup() for configuration verification
- Add get_stats() for in-memory session metrics without DB query
- Track session statistics (requests, tokens saved, cache hits)
### Logging Infrastructure
- Add structured logging to TransformPipeline with token savings
- Add logging to RollingWindow for dropped message tracking
- Add logging to ToolCrusher for compression events
- Add logging to CacheAligner for cache hit/miss detection
- Add logging to SmartCrusher for strategy selection
## Bug Fixes (from deep analysis)
### Critical Fixes
- Fix eviction heap memory leak with stale entry tracking
- Fix hash collision detection in compression store
- Fix strategy truncation desync in TOIN
- Fix non-deterministic set truncation with sorted iteration
- Fix race conditions in lazy initialization with proper locking
- Fix user count double-counting in TOIN metrics
### High Priority Fixes
- Fix unbounded strategy_success_rates growth with LRU eviction
- Fix mutable pattern references with defensive copying
- Fix lock held during file I/O with copy-then-write pattern
- Fix state divergence on eviction with success event recording
- Fix TOIN skip check order for CPU efficiency
- Fix preserve_fields type mismatch (set vs list)
- Fix prioritize_indices exceeding max_items limit
- Fix instance ID collision risk (32-bit to 64-bit hash)
## Testing
- Add comprehensive test suites for CCR, TOIN, and telemetry
- Add crushability detection tests
- Add quality retention tests for compression
- Add integration tests for cross-component data flow
- All 902 tests passing
2026-01-10 10:12:13 -08:00
|
|
|
full_events = [e for e in events if e.retrieval_type == "full"]
|
|
|
|
|
|
fix(ccr): make headroom_retrieve a hash-only full-content lookup (#1532)
The optional `query` parameter on headroom_retrieve routed retrieval
through CompressionStore.search(), which BM25-scored the items inside a
single cached blob and dropped everything below a 0.3 relevance floor.
On small per-blob corpora with conversational queries this returned an
empty result the large majority of the time, so the LLM saw "nothing
found" for content that was actually present — pushing users to turn
compression off entirely.
Retrieval is fundamentally a hash lookup (this already matches the Rust
proxy's CCR store, which is put/get only — "no BM25 search"). Remove the
query/search path end to end and always return the full original
content:
Core (Python proxy):
- tool schemas (anthropic/openai/google) drop the `query` property
- parse_tool_call returns the hash (str | None) instead of (hash, query)
- response handler, proxy POST/GET/tool-call handlers, the MCP retrieve
tool, and the streaming feedback recorders retrieve by hash only
- proactive context-tracker expansion always restores full content
- delete CompressionStore.search() and its BM25 machinery (the bm25
module stays — it is still used by relevance/)
- CCRToolCall.query, CCRToolResult.was_search, and
ExpansionRecommendation.expand_full/search_query are removed
Plugins (advertised a now-defunct query param to the LLM):
- hermes (Python), openclaw + opencode (TypeScript) retrieve tools drop
`query` from their schemas, signatures, request URLs, and tests
Benchmarks/docs:
- ccr_regression + adversarial benchmarks switch from store.search() to
full hash retrieval (search input-injection tests repurposed to the
hash, the only remaining input surface)
- wiki/ARCHITECTURE.md, wiki/ccr.md, docs/content/docs/ccr.mdx,
config.py and store docstrings updated to describe hash-only retrieval
Tests updated to assert full-content retrieval and guard the removed
surface; the full CCR/proxy/store/TOIN suite passes. ruff + mypy clean.
## Description
<!-- Briefly explain the change and why it is needed. -->
Closes #
## Type of Change
- [ ] 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
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
-
## Testing
<!-- Check what you actually ran, then paste the real command output
below. -->
- [ ] Unit tests pass (`pytest`)
- [ ] Linting passes (`ruff check .`)
- [ ] Type checking passes (`mypy headroom`)
- [ ] New tests added for new functionality
- [ ] Manual testing performed
### Test Output
```text
# Paste relevant command output or artifact links here
```
## Real Behavior Proof
- Environment:
- Exact command / steps:
- Observed result:
- Not tested:
## Review Readiness
- [ ] I have performed a self-review
- [ ] This PR is ready for human review
## Checklist
- [ ] My code follows the project's style guidelines
- [ ] I have performed a self-review of my code
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] I have updated the CHANGELOG.md if applicable
## Screenshots (if applicable)
Add screenshots to help explain your changes.
## Additional Notes
<!-- Mention any N/A checklist items, tradeoffs, follow-ups, or
maintainer context. -->
2026-06-28 10:32:43 -07:00
|
|
|
assert len(full_events) >= 3
|
feat: Add CCR architecture, TOIN telemetry, and DevEx improvements
## Core Features
### Compress-Cache-Retrieve (CCR) Architecture
- Implement reversible compression with automatic retrieval support
- Add CompressionStore for caching original content with TTL-based eviction
- Add CompressionFeedback for learning from retrieval patterns
- Implement tool injection for LLM retrieval capability
- Add MCP server support for CCR operations
- Track retrieval rates to dynamically adjust compression aggressiveness
### Tool Output Intelligence Network (TOIN)
- Implement cross-session pattern learning for tool compression
- Add ToolSignature for structural hashing of tool outputs
- Track compression success rates per strategy (top_n, sample, truncate, etc.)
- Implement privacy-preserving telemetry with SHA256 hashing
- Add persistent storage with JSON file backend
- Support network-effect learning across tool types
### SmartCrusher Enhancements
- Add crushability analysis with variance/uniqueness detection
- Implement statistical anomaly detection for outlier preservation
- Add relevance-based item prioritization using BM25 scoring
- Support multiple compression strategies with quality retention
- Add change point detection for time-series data
- Implement constant factoring for homogeneous datasets
## Developer Experience Improvements
### Exception Hierarchy
- Add HeadroomError base class for all custom exceptions
- Add specific exceptions: ConfigurationError, ProviderError,
StorageError, CompressionError, TokenizationError, CacheError,
ValidationError, TransformError
### Client Enhancements
- Add validate_setup() for configuration verification
- Add get_stats() for in-memory session metrics without DB query
- Track session statistics (requests, tokens saved, cache hits)
### Logging Infrastructure
- Add structured logging to TransformPipeline with token savings
- Add logging to RollingWindow for dropped message tracking
- Add logging to ToolCrusher for compression events
- Add logging to CacheAligner for cache hit/miss detection
- Add logging to SmartCrusher for strategy selection
## Bug Fixes (from deep analysis)
### Critical Fixes
- Fix eviction heap memory leak with stale entry tracking
- Fix hash collision detection in compression store
- Fix strategy truncation desync in TOIN
- Fix non-deterministic set truncation with sorted iteration
- Fix race conditions in lazy initialization with proper locking
- Fix user count double-counting in TOIN metrics
### High Priority Fixes
- Fix unbounded strategy_success_rates growth with LRU eviction
- Fix mutable pattern references with defensive copying
- Fix lock held during file I/O with copy-then-write pattern
- Fix state divergence on eviction with success event recording
- Fix TOIN skip check order for CPU efficiency
- Fix preserve_fields type mismatch (set vs list)
- Fix prioritize_indices exceeding max_items limit
- Fix instance ID collision risk (32-bit to 64-bit hash)
## Testing
- Add comprehensive test suites for CCR, TOIN, and telemetry
- Add crushability detection tests
- Add quality retention tests for compression
- Add integration tests for cross-component data flow
- All 902 tests passing
2026-01-10 10:12:13 -08:00
|
|
|
|
|
|
|
|
def test_tool_name_in_events(self):
|
|
|
|
|
"""Tool name is preserved in retrieval events."""
|
|
|
|
|
store = CompressionStore(enable_feedback=True)
|
|
|
|
|
|
|
|
|
|
hash_key = store.store(
|
|
|
|
|
original="[1,2,3]",
|
|
|
|
|
compressed="[1]",
|
|
|
|
|
tool_name="github_search",
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
store.retrieve(hash_key)
|
|
|
|
|
|
|
|
|
|
events = store.get_retrieval_events(tool_name="github_search")
|
|
|
|
|
assert len(events) >= 1
|
|
|
|
|
assert all(e.tool_name == "github_search" for e in events)
|
|
|
|
|
|
|
|
|
|
def test_event_filtering_by_tool(self):
|
|
|
|
|
"""Events can be filtered by tool name."""
|
|
|
|
|
store = CompressionStore(enable_feedback=True)
|
|
|
|
|
|
|
|
|
|
hash1 = store.store(
|
|
|
|
|
original="[1]",
|
|
|
|
|
compressed="[1]",
|
|
|
|
|
tool_name="tool_a",
|
|
|
|
|
)
|
|
|
|
|
hash2 = store.store(
|
|
|
|
|
original="[2]",
|
|
|
|
|
compressed="[2]",
|
|
|
|
|
tool_name="tool_b",
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
store.retrieve(hash1)
|
|
|
|
|
store.retrieve(hash1)
|
|
|
|
|
store.retrieve(hash2)
|
|
|
|
|
|
|
|
|
|
tool_a_events = store.get_retrieval_events(tool_name="tool_a")
|
|
|
|
|
tool_b_events = store.get_retrieval_events(tool_name="tool_b")
|
|
|
|
|
|
|
|
|
|
assert len(tool_a_events) == 2
|
|
|
|
|
assert len(tool_b_events) == 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestCCREdgeCases:
|
|
|
|
|
"""Test edge cases and error handling."""
|
|
|
|
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
|
|
|
def reset_store(self):
|
|
|
|
|
"""Reset global store before each test."""
|
|
|
|
|
reset_compression_store()
|
|
|
|
|
yield
|
|
|
|
|
reset_compression_store()
|
|
|
|
|
|
|
|
|
|
def test_ccr_disabled_no_caching(self):
|
|
|
|
|
"""When CCR disabled, no caching occurs."""
|
|
|
|
|
reset_compression_store()
|
|
|
|
|
|
2026-01-10 15:33:44 -08:00
|
|
|
items = [{"id": i, "score": 100 - i} for i in range(100)]
|
feat: Add CCR architecture, TOIN telemetry, and DevEx improvements
## Core Features
### Compress-Cache-Retrieve (CCR) Architecture
- Implement reversible compression with automatic retrieval support
- Add CompressionStore for caching original content with TTL-based eviction
- Add CompressionFeedback for learning from retrieval patterns
- Implement tool injection for LLM retrieval capability
- Add MCP server support for CCR operations
- Track retrieval rates to dynamically adjust compression aggressiveness
### Tool Output Intelligence Network (TOIN)
- Implement cross-session pattern learning for tool compression
- Add ToolSignature for structural hashing of tool outputs
- Track compression success rates per strategy (top_n, sample, truncate, etc.)
- Implement privacy-preserving telemetry with SHA256 hashing
- Add persistent storage with JSON file backend
- Support network-effect learning across tool types
### SmartCrusher Enhancements
- Add crushability analysis with variance/uniqueness detection
- Implement statistical anomaly detection for outlier preservation
- Add relevance-based item prioritization using BM25 scoring
- Support multiple compression strategies with quality retention
- Add change point detection for time-series data
- Implement constant factoring for homogeneous datasets
## Developer Experience Improvements
### Exception Hierarchy
- Add HeadroomError base class for all custom exceptions
- Add specific exceptions: ConfigurationError, ProviderError,
StorageError, CompressionError, TokenizationError, CacheError,
ValidationError, TransformError
### Client Enhancements
- Add validate_setup() for configuration verification
- Add get_stats() for in-memory session metrics without DB query
- Track session statistics (requests, tokens saved, cache hits)
### Logging Infrastructure
- Add structured logging to TransformPipeline with token savings
- Add logging to RollingWindow for dropped message tracking
- Add logging to ToolCrusher for compression events
- Add logging to CacheAligner for cache hit/miss detection
- Add logging to SmartCrusher for strategy selection
## Bug Fixes (from deep analysis)
### Critical Fixes
- Fix eviction heap memory leak with stale entry tracking
- Fix hash collision detection in compression store
- Fix strategy truncation desync in TOIN
- Fix non-deterministic set truncation with sorted iteration
- Fix race conditions in lazy initialization with proper locking
- Fix user count double-counting in TOIN metrics
### High Priority Fixes
- Fix unbounded strategy_success_rates growth with LRU eviction
- Fix mutable pattern references with defensive copying
- Fix lock held during file I/O with copy-then-write pattern
- Fix state divergence on eviction with success event recording
- Fix TOIN skip check order for CPU efficiency
- Fix preserve_fields type mismatch (set vs list)
- Fix prioritize_indices exceeding max_items limit
- Fix instance ID collision risk (32-bit to 64-bit hash)
## Testing
- Add comprehensive test suites for CCR, TOIN, and telemetry
- Add crushability detection tests
- Add quality retention tests for compression
- Add integration tests for cross-component data flow
- All 902 tests passing
2026-01-10 10:12:13 -08:00
|
|
|
content = json.dumps(items)
|
|
|
|
|
|
|
|
|
|
config = SmartCrusherConfig(max_items_after_crush=15)
|
|
|
|
|
ccr_config = CCRConfig(enabled=False) # Disabled
|
|
|
|
|
|
|
|
|
|
smart_crush_tool_output(content, config, ccr_config)
|
|
|
|
|
|
|
|
|
|
store = get_compression_store()
|
|
|
|
|
stats = store.get_stats()
|
|
|
|
|
assert stats["entry_count"] == 0
|
|
|
|
|
|
|
|
|
|
def test_concurrent_store_and_retrieve(self):
|
|
|
|
|
"""Concurrent operations don't corrupt data."""
|
|
|
|
|
import threading
|
|
|
|
|
|
|
|
|
|
store = CompressionStore()
|
|
|
|
|
errors = []
|
|
|
|
|
|
|
|
|
|
def store_and_retrieve(i):
|
|
|
|
|
try:
|
|
|
|
|
items = [{"id": j, "batch": i} for j in range(10)]
|
|
|
|
|
hash_key = store.store(
|
|
|
|
|
original=json.dumps(items),
|
|
|
|
|
compressed="[]",
|
|
|
|
|
tool_name=f"tool_{i}",
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Immediately retrieve
|
|
|
|
|
entry = store.retrieve(hash_key)
|
|
|
|
|
if entry is None:
|
|
|
|
|
errors.append(f"Entry {i} not found after store")
|
|
|
|
|
elif f'"batch": {i}' not in entry.original_content:
|
|
|
|
|
errors.append(f"Entry {i} has wrong content")
|
|
|
|
|
except Exception as e:
|
|
|
|
|
errors.append(str(e))
|
|
|
|
|
|
2026-01-10 15:33:44 -08:00
|
|
|
threads = [threading.Thread(target=store_and_retrieve, args=(i,)) for i in range(20)]
|
feat: Add CCR architecture, TOIN telemetry, and DevEx improvements
## Core Features
### Compress-Cache-Retrieve (CCR) Architecture
- Implement reversible compression with automatic retrieval support
- Add CompressionStore for caching original content with TTL-based eviction
- Add CompressionFeedback for learning from retrieval patterns
- Implement tool injection for LLM retrieval capability
- Add MCP server support for CCR operations
- Track retrieval rates to dynamically adjust compression aggressiveness
### Tool Output Intelligence Network (TOIN)
- Implement cross-session pattern learning for tool compression
- Add ToolSignature for structural hashing of tool outputs
- Track compression success rates per strategy (top_n, sample, truncate, etc.)
- Implement privacy-preserving telemetry with SHA256 hashing
- Add persistent storage with JSON file backend
- Support network-effect learning across tool types
### SmartCrusher Enhancements
- Add crushability analysis with variance/uniqueness detection
- Implement statistical anomaly detection for outlier preservation
- Add relevance-based item prioritization using BM25 scoring
- Support multiple compression strategies with quality retention
- Add change point detection for time-series data
- Implement constant factoring for homogeneous datasets
## Developer Experience Improvements
### Exception Hierarchy
- Add HeadroomError base class for all custom exceptions
- Add specific exceptions: ConfigurationError, ProviderError,
StorageError, CompressionError, TokenizationError, CacheError,
ValidationError, TransformError
### Client Enhancements
- Add validate_setup() for configuration verification
- Add get_stats() for in-memory session metrics without DB query
- Track session statistics (requests, tokens saved, cache hits)
### Logging Infrastructure
- Add structured logging to TransformPipeline with token savings
- Add logging to RollingWindow for dropped message tracking
- Add logging to ToolCrusher for compression events
- Add logging to CacheAligner for cache hit/miss detection
- Add logging to SmartCrusher for strategy selection
## Bug Fixes (from deep analysis)
### Critical Fixes
- Fix eviction heap memory leak with stale entry tracking
- Fix hash collision detection in compression store
- Fix strategy truncation desync in TOIN
- Fix non-deterministic set truncation with sorted iteration
- Fix race conditions in lazy initialization with proper locking
- Fix user count double-counting in TOIN metrics
### High Priority Fixes
- Fix unbounded strategy_success_rates growth with LRU eviction
- Fix mutable pattern references with defensive copying
- Fix lock held during file I/O with copy-then-write pattern
- Fix state divergence on eviction with success event recording
- Fix TOIN skip check order for CPU efficiency
- Fix preserve_fields type mismatch (set vs list)
- Fix prioritize_indices exceeding max_items limit
- Fix instance ID collision risk (32-bit to 64-bit hash)
## Testing
- Add comprehensive test suites for CCR, TOIN, and telemetry
- Add crushability detection tests
- Add quality retention tests for compression
- Add integration tests for cross-component data flow
- All 902 tests passing
2026-01-10 10:12:13 -08:00
|
|
|
|
|
|
|
|
for t in threads:
|
|
|
|
|
t.start()
|
|
|
|
|
for t in threads:
|
|
|
|
|
t.join()
|
|
|
|
|
|
|
|
|
|
assert errors == [], f"Errors during concurrent operations: {errors}"
|