daemons · roster
Roster
Standing agents — orchestrator, ops, refine — and their liveness, grouped by project. Liveness is derived from each daemon's current cadence: heartbeat 15m + 5m grace; poll fast 60s · slow 15m · dormant 120m.
flower
expected: orchestrator · ops · refine
-
orchestrator dead wind-down · ready to close reset · retiredproc #1194 · session c70527d0-dae2-…context52%usage —last check-in 1h agopipeline 20
- #263 Decouple agent/process management from Solo → flower-native fleet (local-first, then remote) in progress
- #229 Operator-initiated non-resolving "Discuss/Clarify" decision affordance in progress
- #95 Let's figure out we can turn your "waiting on your approval/decision/c in progress
- #11 Briefs refinement loop + first-class daemon-agent roster (per-project agents, heartbeat, operator inbox) in progress
- #12 Operator → orchestrator inbox: project-scoped, MCP-interactive, reassignable async notes in progress
- #4 Worktree-isolated active work (MAIN = stable served/prod); flexible agents-per-worktree in progress
- #110 Let's get our flower.test site setup so it's available on the tailscal planned
- #87 UI Feedback/Requests /briefs view: 1) When/if the user clicks into/f refining
- #66 Notes for the /roster view: 1) Let's add a 'Go to room' button at the refining
- #281 Auto-generate worker dispatch task-packets (stop hand-authoring _dispatch-*.md in orchestrator context) idea
- #261 Fleet-wide work-stoppage / pause protocol — a universal "pending pause" sidecar on flower tool responses (coordinate Solo restart / update / laptop reboot / deploy across all daemons + agents + projects) idea
- #247 Epic-lead force — close the loop: orchestrator auto-executes flower:spawn-epic-lead (incl. epic branch/worktree provision) on a routed force brief (follow-up to #241) idea
- #245 Coordination-drain resilience: auto-complete a reset's own signals + stale-signal safety-net sweep + guarantee non-orch resets within one heartbeat (fb #123) idea
- #243 Review round: refresh daemon/agent charters + prompts + spawn/reset packets against current tools/workflows/features idea
- #200 Dispatched workers that spawn + orchestrate their own sub-agents (solo-playbook-guided) to deliver larger tasked work idea
- #172 App-wide health / audit-log + anomaly-watch system (model-event-sourced) idea
- #165 Bump dispatch auto_max_concurrent default 2 -> 4 (orchestrator concurrent-worker cap) idea
- #164 #78 build — clickable/slug entity references across flower UI (copy-ref + clickable id/slug labels + linked-context anchors) idea
- #100 Two-band daemon context reset — opportunistic (soft) recycle at a clean point + mandatory (hard) drain-and-reset idea
- #61 Operator feed v2: bidirectional operator↔daemon messaging (@-mention + room_post) idea
-
orchestrator liveproc #1203 · session 476c5949-5239-…context21%usage —last check-in 2m agopipeline 20
- #263 Decouple agent/process management from Solo → flower-native fleet (local-first, then remote) in progress
- #229 Operator-initiated non-resolving "Discuss/Clarify" decision affordance in progress
- #95 Let's figure out we can turn your "waiting on your approval/decision/c in progress
- #11 Briefs refinement loop + first-class daemon-agent roster (per-project agents, heartbeat, operator inbox) in progress
- #12 Operator → orchestrator inbox: project-scoped, MCP-interactive, reassignable async notes in progress
- #4 Worktree-isolated active work (MAIN = stable served/prod); flexible agents-per-worktree in progress
- #110 Let's get our flower.test site setup so it's available on the tailscal planned
- #87 UI Feedback/Requests /briefs view: 1) When/if the user clicks into/f refining
- #66 Notes for the /roster view: 1) Let's add a 'Go to room' button at the refining
- #281 Auto-generate worker dispatch task-packets (stop hand-authoring _dispatch-*.md in orchestrator context) idea
- #261 Fleet-wide work-stoppage / pause protocol — a universal "pending pause" sidecar on flower tool responses (coordinate Solo restart / update / laptop reboot / deploy across all daemons + agents + projects) idea
- #247 Epic-lead force — close the loop: orchestrator auto-executes flower:spawn-epic-lead (incl. epic branch/worktree provision) on a routed force brief (follow-up to #241) idea
- #245 Coordination-drain resilience: auto-complete a reset's own signals + stale-signal safety-net sweep + guarantee non-orch resets within one heartbeat (fb #123) idea
- #243 Review round: refresh daemon/agent charters + prompts + spawn/reset packets against current tools/workflows/features idea
- #200 Dispatched workers that spawn + orchestrate their own sub-agents (solo-playbook-guided) to deliver larger tasked work idea
- #172 App-wide health / audit-log + anomaly-watch system (model-event-sourced) idea
- #165 Bump dispatch auto_max_concurrent default 2 -> 4 (orchestrator concurrent-worker cap) idea
- #164 #78 build — clickable/slug entity references across flower UI (copy-ref + clickable id/slug labels + linked-context anchors) idea
- #100 Two-band daemon context reset — opportunistic (soft) recycle at a clean point + mandatory (hard) drain-and-reset idea
- #61 Operator feed v2: bidirectional operator↔daemon messaging (@-mention + room_post) idea
-
ops liveproc #1189 · session bb241486-419f-…context39%usage —last check-in 1m ago
-
refine liveproc #1154 · session 23496935-30ee-…context52%usage —last check-in 59s agopipeline 11
- #263 Decouple agent/process management from Solo → flower-native fleet (local-first, then remote) in progress
- #229 Operator-initiated non-resolving "Discuss/Clarify" decision affordance in progress
- #95 Let's figure out we can turn your "waiting on your approval/decision/c in progress
- #176 Direct-dispatch v2 — new worktree + Solo project + spawn agent (chained after #36 v1, gated on #103) planned
- #142 LLM/Model/Provider routing decisions/guidance Just something I want t planned
- #110 Let's get our flower.test site setup so it's available on the tailscal planned
- #104 Direct dispatch v2 — new-worktree + new-agent + Solo-project creation planned
- #103 Verify direct-dispatch v1 (#36) works end-to-end planned
- #196 Multiple project / cross-project support/usage How might we envision refining
- #182 Dedicated ingest-health page/banner (richer surface beyond #174's badge + per-project indicator) idea
- #181 Ingest coverage viz: git-commit history vs configured time-window (detect missing/at-risk activity) idea
2 agents
-
orchestrator dead wind-down · winding downproc #1102 · session 33dc21ad-a7e7-…context24%usage —last check-in 1d ago
-
refine dead wind-down · ready to closeproc #1103 · session d924b274-905e-…context27%usage —last check-in 1d agopipeline 4
- #214 home-tracker C: design rework — teal / playful / gamer-girl vibe planned
- #212 home-tracker A: point local app at Proxmox MySQL home_tracker (DB connectivity fix) planned
- #215 home-tracker D: cat-feeding & Home Assistant integration status refining
- #211 Project review & updates epic - Let's get this project updated approp refining
4 agents
-
orchestrator dead needs compaction compaction · in_progress wind-down · ready to close reset · retiredproc #1133 · session 9f79635d-71e6-…context89%usage —last check-in 9h ago
-
orchestrator dead wind-down · ready to closeproc #1187 · session 68d01a07-679a-…context22%usage —last check-in 7h ago
-
refine dead wind-down · ready to close reset · retiredproc #1134 · session f8a55631-6875-…context66%usage —last check-in 9h ago
-
refine dead wind-down · ready to closeproc #1188 · session 431fbc1c-b86a-…context13%usage —last check-in 8h ago
2 agents
-
orchestrator deadproc #984 · session 49c8de65dd085f…context6%usage —last check-in 4d ago
-
refine deadproc #985 · session 3a999f26-9770-…context7%usage —last check-in 4d ago