.taskmaster/tasks/task_160.md

# Task ID: 160

**Title:** Deferred: Confidence signal and escalation dashboard placeholder

**Status:** pending

**Dependencies:** 131, 150

**Priority:** low

**Description:** Placeholder task for evidence-anchored confidence and human decision queue - blocked on design questions

**Details:**

DEFERRED - DO NOT IMPLEMENT YET

Blocked on docs/agentic-teams.md §15 Q12: web / TUI / CLI?

Concepts:
- Evidence-anchored confidence: retrieve K similar past tasks with outcomes, assess confidence
- Thresholds driving autonomy level
- Single cross-project human decision queue
- Retrieval quality is the crux - weak retrieval quietly poisons the model

Expand this task when the blocking design question is answered.

**Test Strategy:**

N/A - placeholder only
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			`# Task ID: 160`

			`Title: Deferred: Confidence signal and escalation dashboard placeholder`

			`Status: pending`

			`Dependencies: 131, 150`

			`Priority: low`

			`Description: Placeholder task for evidence-anchored confidence and human decision queue - blocked on design questions`

			`Details:`

			`DEFERRED - DO NOT IMPLEMENT YET`

			`Blocked on docs/agentic-teams.md §15 Q12: web / TUI / CLI?`

			`Concepts:`
			`- Evidence-anchored confidence: retrieve K similar past tasks with outcomes, assess confidence`
			`- Thresholds driving autonomy level`
			`- Single cross-project human decision queue`
			`- Retrieval quality is the crux - weak retrieval quietly poisons the model`

			`Expand this task when the blocking design question is answered.`

			`Test Strategy:`

			`N/A - placeholder only`