manual_slop/TASKS.md

TASKS.md

Active Tracks

None currently active.

Completed This Session

• context_token_viz_20260301 — Token budget panel (color bar, breakdown table, trim warning, cache status, auto-refresh). All phases verified. Commit: d577457.

Planned: Next Track

mma_agent_focus_ux (not yet created)

Priority: High Depends on: nothing Origin: User feedback 2026-03-02 — token viz is agent-agnostic; MMA observability panels (comms, tool calls, discussion history, token budget) show global/session-scoped data with no way to isolate a specific tier or agent.

The Gap (audit-confirmed):

• _comms_log entries (gui_2.py:861–895) have no tier/agent tag — only direction, type, payload
• _tool_log entries (gui_2.py:897–900) are (script, result, ts) — no tier tag
• mma_streams dict uses stream_id ("Tier 1" etc.) — the only existing per-agent key
• _on_comms_entry never attaches caller tier/agent context
• Token stats are global (single ai_client provider, no per-tier history separation)

Intent:

1. Add a source_tier / agent_id field to comms log entries and tool log tuples at the point of emission
2. Add a "Focus Agent" selector widget to the MMA Dashboard (None = global; Tier 1–4 = filtered)
3. Filter _render_comms_history_panel, _render_tool_calls_panel, and _render_discussion_panel by the selected agent when focus is active
4. Token budget panel: when a tier is focused, show token stats for that tier's model/history (requires per-tier history tracking in ai_client or conductor engine)
5. Discussion history entries emitted by MMA workers (via history_add comms kind) already carry a role — use that to group by tier

Scope note: Item 4 (per-tier token stats) is the most architectural — may warrant a sub-track or phased deferral.

To initialize: Run /conductor-new-track mma_agent_focus_ux at start of next session after reading this file.