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. -->
68 lines
1.9 KiB
TypeScript
68 lines
1.9 KiB
TypeScript
import type { Plugin } from "@opencode-ai/plugin";
|
|
import { tool } from "@opencode-ai/plugin";
|
|
import { z } from "zod";
|
|
|
|
import { createHeadroomRetrieveTool, getDefaultProxyUrl } from "./retrieve.js";
|
|
import { installHeadroomTransport } from "./transport.js";
|
|
|
|
export interface HeadroomOpenCodePluginOptions {
|
|
proxyUrl?: string;
|
|
project?: string;
|
|
backend?: string;
|
|
debug?: boolean;
|
|
}
|
|
|
|
function normalizeProxyUrl(url: string): string {
|
|
return url.replace(/\/+$/, "");
|
|
}
|
|
|
|
function resolveProxyUrl(options?: HeadroomOpenCodePluginOptions): string {
|
|
return normalizeProxyUrl(
|
|
options?.proxyUrl ??
|
|
process.env.HEADROOM_PROXY_URL ??
|
|
process.env.HEADROOM_BASE_URL ??
|
|
getDefaultProxyUrl(),
|
|
);
|
|
}
|
|
|
|
export const HeadroomPlugin: Plugin = async (input, options = {}) => {
|
|
const pluginOptions = options as HeadroomOpenCodePluginOptions;
|
|
const proxyUrl = resolveProxyUrl(pluginOptions);
|
|
const retrieveTool = createHeadroomRetrieveTool({ proxyBaseUrl: proxyUrl });
|
|
const uninstallTransport = installHeadroomTransport({
|
|
proxyUrl,
|
|
debug: pluginOptions.debug,
|
|
});
|
|
|
|
return {
|
|
dispose: async () => {
|
|
uninstallTransport();
|
|
},
|
|
tool: {
|
|
headroom_retrieve: tool({
|
|
description: retrieveTool.description,
|
|
args: {
|
|
hash: z
|
|
.string()
|
|
.regex(/^[a-f0-9]{24}$/i, "Expected 24-character hex hash"),
|
|
},
|
|
async execute(args) {
|
|
return retrieveTool.execute(args);
|
|
},
|
|
}),
|
|
},
|
|
"shell.env": async (_input, output) => {
|
|
output.env.HEADROOM_ACTIVE = "1";
|
|
output.env.HEADROOM_PROXY_URL = proxyUrl;
|
|
output.env.HEADROOM_PROJECT =
|
|
pluginOptions.project ??
|
|
(input.project as { id?: string }).id ??
|
|
input.directory;
|
|
if (pluginOptions.backend) {
|
|
output.env.HEADROOM_BACKEND = pluginOptions.backend;
|
|
}
|
|
},
|
|
};
|
|
};
|
|
|
|
export default HeadroomPlugin;
|