Arjun fd49334c33 move local-model concurrency to a turn-level defer lock ... Review feedback: drop the model-layer scheduler (per-call-site interactive/classifier/background priorities, local-provider hostname heuristic) in favor of app-level orchestration: - deferBackgroundTasks flag in models.json, surfaced as a settings toggle; auto-enabled once (UI logic) when the user connects Ollama - ChatActivity counter marked by both chat runtimes (sessions layer and legacy AgentRuntime.trigger) - startWhenPossible/runWhenPossible wrappers around the headless agent runner; all background invocations (knowledge pipeline, live notes, background tasks, scheduled + prebuilt agents) go through them and wait for chat-idle when the flag is set createLanguageModel keeps only the Ollama context-window middleware; the LM Studio capability probe now keys off the provider flavor instead of hostname sniffing. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>		2026-07-06 13:38:39 +05:30
..
docs	docs(x): stage 7 resolved — document the code-mode runs carve-out	2026-07-02 14:20:44 +05:30
scripts	Code mode: make packaged builds work via managed engine provisioning (#625)	2026-06-17 21:53:15 +05:30
src	move local-model concurrency to a turn-level defer lock	2026-07-06 13:38:39 +05:30
.gitignore	bootstrap new electron app	2026-01-16 12:05:33 +05:30
package.json	add whatsapp and telegram support	2026-07-03 19:25:06 +05:30
tsconfig.build.json	Refactor builtin file tools beyond workspace scope	2026-05-25 16:21:51 +05:30
tsconfig.json	feat: extract presentation generator into executable code with builtin tool	2026-01-30 13:30:06 +05:30
vitest.config.ts	Refactor builtin file tools beyond workspace scope	2026-05-25 16:21:51 +05:30