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
56 lines
1.7 KiB
Markdown
56 lines
1.7 KiB
Markdown
# Task ID: 50
|
|
|
|
**Title:** Implement progressive tool exposure for gated sessions
|
|
|
|
**Status:** done
|
|
|
|
**Dependencies:** 48 ✓, 49 ✓
|
|
|
|
**Priority:** high
|
|
|
|
**Description:** Modify tools/list behavior to only expose begin_session while gated, and expose all tools plus read_prompts after ungating.
|
|
|
|
**Details:**
|
|
|
|
1. Update tools/list handling in `/src/mcplocal/src/router.ts`:
|
|
```typescript
|
|
async handleToolsList(sessionId: string): Promise<Tool[]> {
|
|
const state = this.getSessionState(sessionId);
|
|
|
|
if (state.gated) {
|
|
// Only show begin_session while gated
|
|
return [this.getBeginSessionTool()];
|
|
}
|
|
|
|
// After ungating: all upstream tools + read_prompts
|
|
const upstreamTools = await this.discoverTools();
|
|
return [...upstreamTools, this.getReadPromptsTool()];
|
|
}
|
|
```
|
|
|
|
2. Block direct tool calls while gated:
|
|
```typescript
|
|
async handleToolCall(sessionId: string, toolName: string, args: any): Promise<any> {
|
|
const state = this.getSessionState(sessionId);
|
|
|
|
if (state.gated && toolName !== 'begin_session') {
|
|
// Intercept: extract keywords, match prompts, inject briefing
|
|
return this.handleInterceptedCall(sessionId, toolName, args);
|
|
}
|
|
|
|
// Normal routing
|
|
return this.routeToolCall(toolName, args);
|
|
}
|
|
```
|
|
|
|
3. Ensure notifications/tools/list_changed is sent after ungating
|
|
|
|
**Test Strategy:**
|
|
|
|
- Unit test: tools/list while gated returns only begin_session
|
|
- Unit test: tools/list after ungating returns all tools + read_prompts
|
|
- Unit test: begin_session not visible after ungating
|
|
- Unit test: Tool call while gated (not begin_session) triggers intercept
|
|
- Unit test: Tool call after ungating routes normally
|
|
- Unit test: notifications/tools/list_changed sent on ungate
|