@@ -7,27 +7,6 @@
77
88 ---
99
10-## Subagents are spawing more subagents for no reason.
11-
12-Sometimes, a subagent spawns another subagent to do a task, and it enters an endless loop of spawing more subagents.
13-
14----
15-
16-## `/model` thinking-effort toggle
17-
18-The idea specifies: *"/model allows the user to pick a model as well as thinking
19-effort for the model if supported. Selection persists across sessions."*
20-
21-`runTurn()` in `src/llm-api/turn.ts` builds `streamOpts` with no `providerOptions`,
22-so thinking effort is never forwarded to the SDK. The `settings` table (via
23-`getSetting`/`setSetting` in `src/session/db.ts`) is already available for
24-persistence alongside `preferred_model`.
25-
26-Research model capabilities and if we can fetch them automatically from providers (from the model list maybe?)
27-For the models that support reasoning, show the options when listing models with `/models`
28-
29----
30-
3110 ## LSP Diagnostics
3211
3312 We should have a closed loop feedback for LSP diagnostics on edits/reads.