Record owner-approved computer-use Console audit and chat roadmap

.torch/prompts/COMMON.md

@@ -19,6 +19,23 @@ coordinate its Release/QA boundaries and request independent review. Do not
 dispatch other development items in this first pilot. The outer arbiter controls
 provider starts, integration authorization and the next slice.
 
+## Owner-approved parallel Console audit (2026-09-30)
+
+The owner additionally authorizes TASK-console-ux-audit for owner-console.
+Session Manager may triage and assign that exact task while diagnostics QA
+continues. The arbiter launches the assigned UI session; managers still must not
+launch providers. This is a browser-based audit and design proposal, not a
+dashboard rewrite or release. Audit the actual live Console through computer
+use: navigate every area, inspect screenshots and interactions at desktop and
+mobile sizes, and document coverage. Read applicable frontend-design and browser
+skills before browser use. If computer-use tools are unavailable, report that
+specific blocker; source inspection alone is not completion. Do not substitute
+generated screenshots for actually viewing the interface. Keep live state
+read-only; use the isolated demo for exploratory mutations. Publish task-owned
+screenshots/evidence and an audit report proposing focused separate views rather
+than one long anchor-linked page. Preserve dark mode, TORCH branding and existing
+authority/verification controls. No other implementation slice is authorized.
+
 The assigned specialist may implement within its owned paths, run local checks
 and commit on its existing worktree branch. Ask the responsible owner before
 editing shared/other-owned files. Name the task in commits, preserve all existing

docs/TODO.md

@@ -78,6 +78,23 @@ pilot reliability issues have also been added to the same backlog:
 - [ ] `TASK-provider-handover`: after release qualification, checkpoint and safely
   switch one session then the fleet to reviewed Claude Code/Pi profiles; preserve
   TORCH identity/tasks/messages but never reuse another harness's native session ID.
+- [ ] `TASK-owner-agent-chat`: persistent per-agent owner conversations for the
+  Manager and every activated domain, durable replies and clear queued/delivered/
+  running/failed outcomes. Reviewed wake-on-message must respect pauses, budgets
+  and runtime leases; qualify executor outcomes and starting presence first.
+
+The owner approved continuing the controlled pilot. Independent QA now has exact
+candidate `ae18a98e2911aa515d0484518013061b05ff6adf` and the Manager has a bounded
+next-slice planning request. The candidate's test/check/lint receipts pass; its
+dashboard receipt remains incomplete because the test writes tracked reports.
+Neither review launch nor controller exit is acceptance or landing evidence.
+There are now 41 owner-intake items, including agent chat and the UI audit.
+
+- [ ] `TASK-console-ux-audit`: Session Manager assigns Owner Console to audit
+  every live dashboard area through actual computer use and inspected screenshots,
+  including desktop/mobile and keyboard/refresh behavior. Owner rejects the long
+  single-page/anchor-navigation layout. Propose focused separate screens, concise
+  overview and contextual drilldowns. Audit/proposal only; no UI rewrite yet.
 
 ## First real self-host run (2026-09-30)
 

reports/audit/first-development-pilot-2026-09-30.md

@@ -104,3 +104,31 @@ Receipts are under `/tmp/torch-pilot-*`, including repaired full-source acceptan
 native parser tests, scheduler installation/reconciliation, durable wake/run
 state and owner-request messages. The live dashboard and actual branch state
 take precedence over historical progress descriptions in this report.
+
+## Continued pilot and owner UX feedback
+
+The owner approved continuing the controlled pilot and is watching the Console.
+Independent QA reviewed candidate `ae18a98e2911aa515d0484518013061b05ff6adf`:
+the lifecycle scenario independently PASSed 7/7, with no assertion relaxation.
+QA accepted code/scenario content, **not integration qualification**. Required
+dashboard receipt remains incomplete and canonical convergence remains required.
+QA's durable report is message `8275d64a-7b28-49ee-a379-2c6d0bdcacb3`.
+
+Two additional owner-intake proposals bring the backlog to 41:
+
+- `TASK-owner-agent-chat`: threaded durable owner conversations and reviewed
+  wake-on-message after executor/presence qualification. Current agent message
+  recipient validation does not permit the owner as a recipient; owner replies
+  need a distinct authorized API, not an invented specialist identity.
+- `TASK-console-ux-audit`: the owner rejects excessive scrolling and a generic
+  all-in-one-page dashboard. Session Manager has an explicit bounded assignment
+  request for existing Owner Console. Require actual computer-use navigation,
+  inspected screenshots of every current area, desktop/mobile and interaction
+  coverage, and a focused multi-screen proposal. Live state is read-only; demo
+  may exercise mutations. Missing browser tools are a blocker, not permission
+  to claim a source-only audit completed the request.
+
+Canonical COMMON now permits this audit in parallel with diagnostics QA, without
+authorizing UI implementation, unrelated dispatch, automatic wakes or release.
+The arbiter launches Owner Console only after actual manager assignment; a
+request in an inbox is not itself assignment evidence.