Files

Michal a869f77070 merge: AgentProject membership — the junction is now load-bearing

Merges feat/agent-project-membership (task 166/152). An agent can finally join
many projects: membership routes, per-membership role and optional brain
override, chat resolving context from the membership, and CLI attach-agent /
detach-agent / get memberships. The legacy Agent.projectId fallback is kept for
this release as the schema comment promises.

Conflict resolved in main.ts: that branch added its RBAC case to
mapUrlToPermission inline, while this branch had extracted the function to
middleware/url-permission.ts so it could be tested. Kept the extraction and
ported the case into it — joining a team is `edit:agents:<name>`, not
`create:agents`, which is the authority to mint a whole agent.

Also fixes something the extraction makes possible. security.test.ts contained a
hand-copied reproduction of mapUrlToPermission, because main.ts self-invokes
main() and nothing in it was importable. A security test asserting against a
copy stops testing the system the moment the real one changes, and this copy had
already drifted. It now imports the real function; all 18 assertions still pass,
against the code that actually runs.

Local: build clean, workspace 2550 passed, lint unchanged at 794 errors.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4wNHWf7xSwnZCWpJcyv9p

2026-08-09 23:34:18 +01:00

2.3 KiB

Raw Blame History

Task ID: 32

Title: Implement smart context optimization

Status: done

Dependencies: 29 ✓

Priority: medium

Description: Add token counting and decision logic to intelligently skip LLM filtering when responses are small enough, and cache filtering decisions for repeated queries.

Details:

Create src/mcplocal/src/llm/token-counter.ts:

export function estimateTokens(text: string): number {
  // Simple estimation: ~4 chars per token for English
  // More accurate: use tiktoken or similar library
  return Math.ceil(text.length / 4);
}

Create src/mcplocal/src/llm/filter-cache.ts:

export class FilterCache {
  private cache: LRUCache<string, FilterDecision>;

  shouldFilter(toolName: string, params: unknown, responseSize: number): boolean {
    const key = this.computeKey(toolName, params);
    const cached = this.cache.get(key);
    if (cached) return cached.shouldFilter;
    // No cache hit - use default threshold logic
    return responseSize > this.tokenThreshold;
  }

  recordDecision(toolName: string, params: unknown, decision: FilterDecision): void {
    const key = this.computeKey(toolName, params);
    this.cache.set(key, decision);
  }
}

Add configuration options:
- tokenThreshold: number (default 1000 tokens)
- filterCacheSize: number (default 1000 entries)
- filterCacheTtl: number (default 3600 seconds)

Integrate into LlmProcessor:

async filterResponse(...) {
  const tokens = estimateTokens(JSON.stringify(rawResponse));
  if (tokens < this.config.tokenThreshold) {
    // Not worth filtering - return as-is
    return { filtered: false, response: rawResponse };
  }
  // Proceed with LLM filtering
}

Add metrics tracking:
- Total tokens processed
- Tokens saved by filtering
- Filter cache hit rate
- Average latency added by filtering

Test Strategy:

Unit test: Token estimation is reasonably accurate
Unit test: Cache correctly stores and retrieves decisions
Unit test: Threshold logic skips filtering for small responses
Unit test: Cache TTL expiration works correctly
Integration test: Metrics are recorded accurately
Performance test: Cache improves latency for repeated queries

2.3 KiB Raw Blame History

Task ID: 32

2.3 KiB

Raw Blame History