Sam
|
d2cf643eca
|
Outline collection pushed; Obsidian note links the map and the collection; Headroom paths recorded
|
2026-11-12 08:45:30 +11:00 |
|
Sam
|
e883b11016
|
Write down exactly what a person must do to use Headroom, both paths
|
2026-11-11 21:12:48 +11:00 |
|
Sam
|
df861563cf
|
Correct the Headroom finding: LiteLLM does not know the router's models; install headroom-ai on all three machines
|
2026-11-11 19:19:43 +11:00 |
|
Sam
|
00abedb66b
|
Headroom: the tool path, measured; provider path documented as blocked
|
2026-11-11 19:00:13 +11:00 |
|
Sam
|
7a2d4358d3
|
Headroom measured and blocked; Mouse-1 triage command built and run
|
2026-11-11 18:39:38 +11:00 |
|
Sam
|
70e1f55486
|
Wrap overlay text instead of cutting it; the project check is a regression check, renamed check.sh; concrete Headroom steps; Mouse-1 measured
|
2026-11-11 16:35:44 +11:00 |
|
Sam
|
e02b39943d
|
Cleanup confirms and refreshes; projects switch sessions in place; explain verify.sh, headroom and Mouse-1
|
2026-11-11 15:57:42 +11:00 |
|
Sam
|
e44b0dff51
|
Confirmed by experiment: how a picker can assign skills per agent, and where the boundary is
|
2026-11-11 08:58:23 +11:00 |
|
Sam
|
47aacfd6d1
|
Correct the Pi advice: per-agent skills are the design; per-agent extensions via adapterConfig.command
|
2026-11-11 08:13:48 +11:00 |
|
Sam
|
77014d035b
|
Advice: how Pi agent configuration actually resolves under Paperclip, and what history is available
|
2026-11-11 08:03:00 +11:00 |
|
Sam
|
3d31243317
|
Findings: per-agent skills API, memory stack, MOUSE-1 policy, the old office scaffold, the dashboard endpoint
|
2026-11-10 21:00:42 +11:00 |
|
Sam
|
7b12b45064
|
Drop the icon sample row; give tool panes a working PATH and a reason to stay open; answer the open questions
|
2026-11-10 18:35:11 +11:00 |
|
Sam
|
7f18c548fe
|
Revert the pane split; write the plan that maps every Paperclip object to a screen
|
2026-11-10 16:41:17 +11:00 |
|