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

.taskmaster/tasks/task_048.md

@@ -0,0 +1,67 @@
+# Task ID: 48
+
+**Title:** Implement begin_session tool for gated sessions
+
+**Status:** done
+
+**Dependencies:** 46 ✓, 47 ✓
+
+**Priority:** high
+
+**Description:** Create the begin_session MCP tool that accepts 5 keywords, triggers prompt selection, returns matched content with encouragement, and ungates the session.
+
+**Details:**
+
+1. Add begin_session tool definition in `/src/mcplocal/src/router.ts`:
+   ```typescript
+   private getBeginSessionTool(): Tool {
+     return {
+       name: 'begin_session',
+       description: 'Start your session by providing 5 keywords that describe your current task. You\'ll receive relevant project context, policies, and guidelines. Required before using other tools.',
+       inputSchema: {
+         type: 'object',
+         properties: {
+           tags: {
+             type: 'array',
+             items: { type: 'string' },
+             maxItems: 10,
+             description: '5 keywords describing your current task'
+           }
+         },
+         required: ['tags']
+       }
+     };
+   }
+   ```
+
+2. Implement begin_session handler:
+   - Validate tags array (1-10 items)
+   - Call LlmPromptSelector or TagMatcher based on LLM availability
+   - Fetch full content for selected prompts
+   - Build response with matched content + index + encouragement
+   - Ungate session
+   - Send `notifications/tools/list_changed`
+
+3. Response format:
+   ```
+   [Priority 10 prompts - full content]
+   
+   [Tag-matched prompts - full content, priority-ordered]
+   
+   Other prompts available that may become relevant...
+   - name: summary
+   ...
+   If any seem related, request them with read_prompts({ tags: [...] }).
+   ```
+
+**Test Strategy:**
+
+- Unit test: begin_session with valid tags returns matched prompts
+- Unit test: begin_session includes priority 10 prompts always
+- Unit test: begin_session response includes encouragement text
+- Unit test: begin_session response includes prompt index
+- Unit test: Session ungated after successful begin_session
+- Unit test: notifications/tools/list_changed sent after ungating
+- Unit test: Empty tags handled (returns priority 10 only)
+- Unit test: Invalid tags rejected with error
+- Unit test: begin_session while already ungated returns error