bytelyst/learning_ai_common_plat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(runtime): record FlowMonk runtime review UI

Browse Source
This commit is contained in:
Saravana Achu Mac 2026-04-04 14:37:10 -07:00
parent e6fb20f86b
commit e3f72fa22d
3 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/ecosystem/ECOSYSTEM_IMPLEMENTATION_TRACKER.md
View File

@ -270,11 +270,11 @@ These should be resolved before claiming the ecosystem docs are fully implementa
### 6.1 Remaining Direct Runtime TODOs
- FlowMonk: decide whether the new backend editing surfaces need dedicated product UI affordances now or can remain API-first.
- FlowMonk: decide whether the next runtime UI slice should prioritize run/action drill-in or resume controls.
### 6.2 Explicit Blockers And Questions
- Question: should FlowMonk approvals and todos stay API-first for now, or is a dedicated product UI the next priority?
- Question: should FlowMonk runtime UX go deeper on replay/action visibility next, or on checkpoint resume guidance?
---

9
docs/ecosystem/PHASE5_AGENT_RUNTIME_CONTRACT_EXECUTION_PLAN.md
View File

@ -113,15 +113,16 @@ Observed baseline:
- `4ff578e` Cowork checkpoint refs plus canonical session/task IPC event IDs
- `32b46f0` cowork-service runtime mapping for enriched checkpoint refs and IPC event IDs
- `6b1e52c` FlowMonk direct user-managed runtime todo and approval editing surfaces
- `da2db8e` FlowMonk dedicated runtime review web UI
## 7. Remaining Gaps
- Cowork now emits shared runtime projections from cowork-service, preserves Rust-side canonical event IDs on approval/audit records, and exposes persisted checkpoint-driven todo and resume review surfaces.
- Cowork session and task IPC projections now also expose canonical event IDs directly, and checkpoint summaries preserve artifact and memory refs when present.
- FlowMonk now emits direct runtime projections for planning sessions, tasks, todos, runs, approvals, actions, and checkpoints with persisted native runtime records plus direct PATCH editing surfaces for approvals and todos.
- Cowork session and task IPC projections now also expose canonical event IDs directly, and checkpoint summaries preserve artifact IDs plus artifact and memory refs when present.
- FlowMonk now emits direct runtime projections for planning sessions, tasks, todos, runs, approvals, actions, and checkpoints with persisted native runtime records, direct PATCH editing surfaces, and a dedicated runtime review web UI for approvals, todos, and checkpoints.
- remaining follow-through is now evolutionary rather than blocking:
- FlowMonk can later add richer UI affordances on top of the new backend editing surfaces
- FlowMonk can later deepen the runtime view with run/action drill-in if needed
## 8. Explicit Blockers And Questions
- Question: should FlowMonk approvals and todos remain API-first for now, or should a dedicated product UI become the next runtime slice?
- Question: should the next FlowMonk runtime slice focus on run/action drill-in or checkpoint resume controls?

2
docs/ecosystem/adoption/learning_ai_flowmonk.md
View File

@ -24,6 +24,7 @@
- [x] expose product-facing checkpoint summaries for planning-session resume
- [x] document the rule for when a scheduled entry becomes a new run under an existing session
- [x] add runtime approvals and todos direct user-managed editing surfaces
- [x] add a dedicated runtime review UI for approvals, todos, and checkpoints
Commits:
@ -32,3 +33,4 @@ Commits:
- `faf93ec` implemented direct runtime approvals and todos
- `86470b2` persisted native runtime todo, approval, and checkpoint records
- `6b1e52c` added direct user-managed runtime todo and approval editing surfaces
- `da2db8e` added the FlowMonk runtime review web UI