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

docs(runtime): record FlowMonk replay review

Browse Source
This commit is contained in:
Saravana Achu Mac 2026-04-04 15:02:26 -07:00
parent 1c92284314
commit 2a4d8a7b75
3 changed files with 8 additions and 5 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 replay affordances are worth adding on top of the current runtime review UI.
- FlowMonk: decide whether richer replay execution controls are worth adding on top of the current runtime review UI.
### 6.2 Explicit Blockers And Questions
- Question: should FlowMonk runtime UX add replay affordances next, or is the current review depth sufficient?
- Question: is the current FlowMonk runtime review depth sufficient, or should it grow into richer replay execution controls?
---

7
docs/ecosystem/PHASE5_AGENT_RUNTIME_CONTRACT_EXECUTION_PLAN.md
View File

@ -116,6 +116,7 @@ Observed baseline:
- `da2db8e` FlowMonk dedicated runtime review web UI
- `19fd4e1` FlowMonk runtime run and action drill-in
- `94420a8` FlowMonk checkpoint resume guidance and linked ref review
- `51cf948` FlowMonk replay-oriented run filtering and action payload drill-in
- `ec593d7` Phase 5 docs reconciled through FlowMonk checkpoint guidance
## 7. Remaining Gaps
@ -123,10 +124,10 @@ Observed baseline:
- 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 IDs plus artifact and memory refs when present.
- Cowork direct-vs-projected runtime semantics are now explicitly documented in the shared runtime contract.
- 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, checkpoints, runs, recent actions, and checkpoint resume guidance.
- 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, checkpoints, runs, recent actions, checkpoint resume guidance, and lightweight replay review.
- remaining follow-through is now evolutionary rather than blocking:
- FlowMonk can later add replay affordances if needed
- FlowMonk can later add richer replay execution controls if they become necessary
## 8. Explicit Blockers And Questions
- Question: should the next FlowMonk runtime slice focus on replay affordances?
- Question: are richer replay execution controls worth the added product complexity, or is the current review surface sufficient?

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

@ -27,6 +27,7 @@
- [x] add a dedicated runtime review UI for approvals, todos, and checkpoints
- [x] add runtime run and action drill-in inside the review UI
- [x] add checkpoint resume guidance and linked ref review inside the runtime UI
- [x] add replay-oriented run filtering and action payload drill-in
Commits:
@ -38,3 +39,4 @@ Commits:
- `da2db8e` added the FlowMonk runtime review web UI
- `19fd4e1` added FlowMonk runtime run and action drill-in
- `94420a8` added checkpoint resume guidance and linked ref review
- `51cf948` added replay-oriented run filtering and action payload drill-in