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

2.0 KiB

Raw Blame History

Task ID: 66

Title: Add unit tests for LLM prompt selection

Status: done

Dependencies: 46 ✓

Priority: high

Description: Create unit tests for the LLM-based prompt selection service covering LLM interactions, fallback behavior, and priority 10 handling.

Details:

Add tests in /src/mcplocal/tests/services/llm-prompt-selector.test.ts:

describe('LlmPromptSelectorService', () => {
  describe('priority 10 handling', () => {
    it('always includes priority 10 prompts', async () => {
      const result = await selector.selectPrompts(['unrelated'], promptIndex);
      expect(result.priority10).toContain(priority10Prompt);
    });
  });

  describe('LLM selection', () => {
    it('sends tags and index to heavy LLM', async () => {
      await selector.selectPrompts(['zigbee', 'mqtt'], promptIndex);
      expect(mockLlm.complete).toHaveBeenCalledWith(
        expect.stringContaining('zigbee')
      );
    });

    it('parses LLM response correctly', async () => {
      mockLlm.complete.mockResolvedValue(
        '[{"name": "prompt1", "reason": "relevant"}]'
      );
      const result = await selector.selectPrompts(['test'], promptIndex);
      expect(result.selected[0].name).toBe('prompt1');
    });
  });

  describe('fallback behavior', () => {
    it('falls back to tag matcher on LLM error', async () => { ... });
    it('falls back on LLM timeout', async () => { ... });
    it('falls back when no LLM available', async () => { ... });
  });

  describe('summary generation', () => {
    it('generates missing summaries with fast LLM', async () => { ... });
  });
});

Test Strategy:

This task IS the test implementation. Verify:

Priority 10 tests pass
LLM interaction tests use proper mocks
Fallback tests cover all error scenarios
Summary generation tests pass
Response parsing handles edge cases

2.0 KiB Raw Blame History

Task ID: 66

2.0 KiB

Raw Blame History