3 Commits

Author	SHA1	Message	Date
hermes	efef0cd7a2	fix: exclude backfilled data from success rate calculations (#189) ... Backfilled retro entries lack main_green/hermes_clean fields (survivorship bias). Now rates are computed only from measured entries. LOOPSTAT shows "no data yet" instead of fake 100%. Co-authored-by: Kimi Agent <kimi@timmy.local> Reviewed-on: http://localhost:3000/rockachopa/Timmy-time-dashboard/pulls/189 Co-authored-by: hermes <hermes@timmy.local> Co-committed-by: hermes <hermes@timmy.local>	2026-03-15 12:29:27 -04:00
hermes	56b08658b7	feat: workspace isolation + honest success metrics (#186) ... ## Workspace Isolation No agent touches ~/Timmy-Time-dashboard anymore. Each agent gets a fully isolated clone under /tmp/timmy-agents/ with its own port, data directory, and TIMMY_HOME. - scripts/agent_workspace.sh: init, reset, branch, destroy per agent - Loop prompt updated: workspace paths replace worktree paths - Smoke tests run in isolated /tmp/timmy-agents/smoke/repo ## Honest Success Metrics Cycle success now requires BOTH hermes clean exit AND main green (smoke test passes). Tracks main_green_rate separately from hermes_clean_rate in summary.json. Follows from PR #162 (triage + retro system). Co-authored-by: Kimi Agent <kimi@timmy.local> Reviewed-on: http://localhost:3000/rockachopa/Timmy-time-dashboard/pulls/186 Co-authored-by: hermes <hermes@timmy.local> Co-committed-by: hermes <hermes@timmy.local>	2026-03-15 12:25:27 -04:00
hermes	b960096331	feat: triage scoring, cycle retros, deep triage, and LOOPSTAT panel (#162)	2026-03-15 11:24:01 -04:00