mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
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. -->
94 lines
3.5 KiB
Python
94 lines
3.5 KiB
Python
"""Headroom CCR retrieve plugin.
|
|
|
|
The headroom proxy (127.0.0.1:8787) compresses large tool outputs in LLM
|
|
requests, replacing them with markers like ``[N items compressed ...
|
|
hash=abc123]`` or ``<<ccr:abc123>>``. This plugin gives Hermes a tool to fetch the original
|
|
uncompressed content back from the proxy's compression store, so compressed
|
|
markers are no longer a black box.
|
|
|
|
Storage is in-memory on the proxy side with a TTL — expired or
|
|
post-proxy-restart hashes return 404 and the tool reports that clearly.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import httpx
|
|
from tools.registry import tool_error, tool_result
|
|
|
|
_PROXY_URL = "http://127.0.0.1:8787"
|
|
|
|
HEADROOM_RETRIEVE_SCHEMA = {
|
|
"name": "headroom_retrieve",
|
|
"description": (
|
|
"Retrieve the original uncompressed content behind a headroom "
|
|
"compression marker. Markers look like "
|
|
"'[N items compressed ... hash=abc123]' OR '<<ccr:abc123>>' OR "
|
|
"'<<ccr:abc123,base64,4.5KB>>'. They are NOT file paths — never try "
|
|
"to cat/read them. When you see one in a tool result or in "
|
|
"conversation history, call this tool with the hash (the hex string "
|
|
"after 'hash=' or 'ccr:') to read the full original content instead "
|
|
"of guessing or re-running the command. Retrieval is by hash and "
|
|
"always returns the complete original content. Content expires after "
|
|
"a TTL — if expired, re-run the original command instead."
|
|
),
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"hash": {
|
|
"type": "string",
|
|
"description": "Hash from the compression marker, e.g. 'abc123' from '[... hash=abc123]' or '<<ccr:abc123>>'",
|
|
},
|
|
},
|
|
"required": ["hash"],
|
|
},
|
|
}
|
|
|
|
|
|
def _handle_headroom_retrieve(args: dict, **kw) -> str:
|
|
hash_key = str(args.get("hash") or "").strip()
|
|
# Tolerate the model passing the whole marker instead of the bare hash:
|
|
# '<<ccr:abc123,base64,4.5KB>>' / 'ccr:abc123' / 'hash=abc123' -> 'abc123'
|
|
hash_key = hash_key.strip("<>").removeprefix("ccr:").removeprefix("hash=")
|
|
hash_key = hash_key.split(",")[0].strip()
|
|
if not hash_key:
|
|
return tool_error(
|
|
"hash is required (from a '[... hash=abc123]' or '<<ccr:abc123>>' marker)"
|
|
)
|
|
|
|
payload: dict = {"hash": hash_key}
|
|
|
|
try:
|
|
resp = httpx.post(f"{_PROXY_URL}/v1/retrieve", json=payload, timeout=15)
|
|
except httpx.HTTPError as exc:
|
|
return tool_error(
|
|
f"headroom proxy unreachable at {_PROXY_URL} ({type(exc).__name__}). "
|
|
"The proxy may be down; re-run the original command to get the data."
|
|
)
|
|
|
|
if resp.status_code == 404:
|
|
return tool_error(
|
|
"Content not found: expired (TTL passed) or proxy restarted. "
|
|
"Re-run the original command to regenerate the data."
|
|
)
|
|
if resp.status_code != 200:
|
|
return tool_error(f"headroom proxy returned HTTP {resp.status_code}: {resp.text[:200]}")
|
|
|
|
data = resp.json()
|
|
return tool_result(
|
|
{
|
|
"original_content": data.get("original_content", ""),
|
|
"original_tokens": data.get("original_tokens"),
|
|
"tool_name": data.get("tool_name"),
|
|
}
|
|
)
|
|
|
|
|
|
def register(ctx) -> None:
|
|
"""Register the headroom_retrieve tool. Called by the plugin loader."""
|
|
ctx.register_tool(
|
|
name="headroom_retrieve",
|
|
toolset="headroom",
|
|
schema=HEADROOM_RETRIEVE_SCHEMA,
|
|
handler=_handle_headroom_retrieve,
|
|
emoji="🗜️",
|
|
)
|