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_042.md

@@ -0,0 +1,58 @@
+# Task ID: 42
+
+**Title:** Implement prompt summary generation service
+
+**Status:** done
+
+**Dependencies:** 37 ✓
+
+**Priority:** high
+
+**Description:** Create a service that auto-generates summary (20 words) and chapters (key sections) for prompts, using fast LLM when available or regex fallback.
+
+**Details:**
+
+1. Create `/src/mcpd/src/services/prompt-summary.service.ts`:
+   ```typescript
+   export class PromptSummaryService {
+     constructor(
+       private llmClient: LlmClient | null,
+       private promptRepo: IPromptRepository
+     ) {}
+     
+     async generateSummary(content: string): Promise<{ summary: string; chapters: string[] }> {
+       if (this.llmClient) {
+         return this.generateWithLlm(content);
+       }
+       return this.generateWithRegex(content);
+     }
+     
+     private async generateWithLlm(content: string): Promise<...> {
+       // Send content to fast LLM with prompt:
+       // "Generate a 20-word summary and extract key section topics..."
+     }
+     
+     private generateWithRegex(content: string): { summary: string; chapters: string[] } {
+       // summary: first sentence of content (truncated to ~20 words)
+       // chapters: extract markdown headings via regex /^#+\s+(.+)$/gm
+     }
+   }
+   ```
+
+2. Integrate with PromptService:
+   - Call generateSummary on prompt create
+   - Call generateSummary on prompt update (when content changes)
+   - Cache results on the prompt record
+
+3. Handle LLM availability check via existing LlmConfig patterns
+
+**Test Strategy:**
+
+- Unit test: generateWithRegex extracts first sentence as summary
+- Unit test: generateWithRegex extracts markdown headings as chapters
+- Unit test: generateWithLlm calls LLM with correct prompt (mock LLM)
+- Unit test: generateSummary uses LLM when available
+- Unit test: generateSummary falls back to regex when no LLM
+- Unit test: Empty content handled gracefully
+- Unit test: Content without headings returns empty chapters array
+- Integration test: Creating prompt triggers summary generation