feat(custom-model): generate Run-menu entries from saved endpoint profiles - #430

Draft

opticon454 wants to merge 22 commits into

Ark0N:masterfrom

opticon454:feature/run-menu-custom-model-picker

Commits on Sep 15, 2026

feat(custom-model): generate Run-menu entries from saved endpoint profiles

opticon454
and
claude
committed
25fae9a
docs(wiki): document Custom Model Endpoints and the Run-menu picker

opticon454
and
claude
committed
98d26e1
fix(test): strip the custom-model Run-menu picker's injected script too

opticon454
and
claude
committed
fed6582
fix(custom-model): act on the draft review — unparseable onclick, unwrapped envelope, wrong-session apply, missing lock, no tests

opticon454
and
claude
committed
60e1bd5

Commits on Sep 16, 2026

feat(custom-model): ask which model on launch when an endpoint has more than one, and re-discover models every 5 minutes

opticon454
and
claude
committed
5a9ff07
fix(custom-model): bound the model-picker dialog's height and make its list scroll

opticon454
and
claude
committed
9a9e542
fix(custom-model,toast): surface the real apply error, and make error toasts sticky with a close button

opticon454
and
claude
committed
409a6e6
fix(custom-model): wait for a freshly launched session to go idle before applying

opticon454
and
claude
committed
5c25a52
fix(custom-model): isolate Claude config dir and inject real context length

opticon454
and
claude
committed
0e8b198
fix(custom-model): pre-approve the injected API key in the isolated Claude config dir

opticon454
and
claude
committed
97464bf
test(custom-model): update session-custom-model route test for CLAUDE_CONFIG_DIR isolation

opticon454
and
claude
committed
25f22b9
feat(custom-model): detect llama-swap model conflicts before switching

opticon454
and
claude
committed
bcebc81
docs(changeset): add changeset for the Run-menu custom-model picker PR

opticon454
and
claude
committed
fbee1b2
feat(custom-model): launch directly on the endpoint, no restart, for 7 of 8 CLIs

opticon454
and
claude
committed
f865f74
fix(custom-model): show a status toast during Claude's native-boot-then-restart window

opticon454
and
claude
committed
83033b4
fix(custom-model): replace the native confirm() popup with an in-app modal

opticon454
and
claude
committed
2936ba6
fix(custom-model): move the switching/loading status to a centred banner

opticon454
and
claude
committed
01b32ee
fix(custom-model): actually trigger the llama-swap load, not just watch for it

opticon454
and
claude
committed
0929694
fix(custom-model): poll llama-swap readiness every 1s, check immediately, extend the cap

opticon454
and
claude
committed
0af233c
feat(custom-model): estimate model load time from its discovered size

opticon454
and
claude
committed
55dae31
feat(custom-model): live countdown on the loading banner; timeout is now an error

opticon454
and
claude
committed
7bbe408
fix(custom-model): stop trusting /props's n_ctx, parse the real context size from /running's cmd

opticon454
and
claude
committed
9937102

Navigation Menu

feat(custom-model): generate Run-menu entries from saved endpoint profiles - #430

feat(custom-model): generate Run-menu entries from saved endpoint profiles#430
opticon454 wants to merge 22 commits into
Ark0N:masterfrom
opticon454:feature/run-menu-custom-model-picker

Commits on Sep 15, 2026

feat(custom-model): generate Run-menu entries from saved endpoint profiles

docs(wiki): document Custom Model Endpoints and the Run-menu picker

fix(test): strip the custom-model Run-menu picker's injected script too

fix(custom-model): act on the draft review — unparseable onclick, unwrapped envelope, wrong-session apply, missing lock, no tests

Commits on Sep 16, 2026

feat(custom-model): ask which model on launch when an endpoint has more than one, and re-discover models every 5 minutes

fix(custom-model): bound the model-picker dialog's height and make its list scroll

fix(custom-model,toast): surface the real apply error, and make error toasts sticky with a close button

fix(custom-model): wait for a freshly launched session to go idle before applying

fix(custom-model): isolate Claude config dir and inject real context length

fix(custom-model): pre-approve the injected API key in the isolated Claude config dir

test(custom-model): update session-custom-model route test for CLAUDE_CONFIG_DIR isolation

feat(custom-model): detect llama-swap model conflicts before switching

docs(changeset): add changeset for the Run-menu custom-model picker PR

feat(custom-model): launch directly on the endpoint, no restart, for 7 of 8 CLIs

fix(custom-model): show a status toast during Claude's native-boot-then-restart window

fix(custom-model): replace the native confirm() popup with an in-app modal

fix(custom-model): move the switching/loading status to a centred banner

fix(custom-model): actually trigger the llama-swap load, not just watch for it

fix(custom-model): poll llama-swap readiness every 1s, check immediately, extend the cap

feat(custom-model): estimate model load time from its discovered size

feat(custom-model): live countdown on the loading banner; timeout is now an error

fix(custom-model): stop trusting /props's n_ctx, parse the real context size from /running's cmd