a869f77070
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
62 lines
1.9 KiB
Markdown
62 lines
1.9 KiB
Markdown
# Task ID: 30
|
|
|
|
**Title:** Add Gemini CLI LLM provider
|
|
|
|
**Status:** done
|
|
|
|
**Dependencies:** 25 ✓
|
|
|
|
**Priority:** medium
|
|
|
|
**Description:** Implement a new LLM provider that uses the Gemini CLI binary for local, free LLM inference as the preferred provider for pre-processing.
|
|
|
|
**Details:**
|
|
|
|
1. Create `src/mcplocal/src/providers/gemini-cli.ts`:
|
|
```typescript
|
|
import { spawn } from 'child_process';
|
|
|
|
export class GeminiCliProvider implements LlmProvider {
|
|
readonly name = 'gemini-cli';
|
|
private binaryPath: string;
|
|
|
|
constructor(config: GeminiCliConfig) {
|
|
this.binaryPath = config.binaryPath || 'gemini';
|
|
}
|
|
|
|
async isAvailable(): Promise<boolean> {
|
|
// Check if gemini binary exists and is executable
|
|
try {
|
|
await this.runCommand(['--version']);
|
|
return true;
|
|
} catch {
|
|
return false;
|
|
}
|
|
}
|
|
|
|
async complete(options: CompletionOptions): Promise<CompletionResult> {
|
|
const input = this.formatPrompt(options);
|
|
const output = await this.runCommand(['--prompt', input]);
|
|
return { content: output, model: 'gemini-cli' };
|
|
}
|
|
|
|
private async runCommand(args: string[]): Promise<string> {
|
|
// Spawn gemini CLI process and capture output
|
|
}
|
|
}
|
|
```
|
|
2. Research actual Gemini CLI interface and adjust implementation
|
|
3. Add to provider registry with high priority (prefer over API providers)
|
|
4. Add configuration: `geminiCliBinaryPath`
|
|
5. Handle timeout for slow inference
|
|
6. Add fallback to next provider if Gemini CLI fails
|
|
|
|
**Test Strategy:**
|
|
|
|
1. Unit test: Provider correctly detects CLI availability
|
|
2. Unit test: Prompt formatting is correct
|
|
3. Unit test: Output parsing handles various formats
|
|
4. Integration test: Full completion with actual Gemini CLI (if available)
|
|
5. Test timeout handling for slow responses
|
|
6. Test fallback when CLI is not installed
|