Only fetch remote catalog when interactive model pick needs it; otherwise
use config/--model/session and warm Tab cache in the background. Cap list
fetch at 5s so a dead API cannot hang startup.
asyncio signal handlers freeze ContextVars at install time; reinstalling
while allow_task_cancel was still False left cancel permanently disabled.
Use a process-level prompt depth counter and reinstall only after depth=0.
Complete /todos actions and todo ids, session ids for /resume|/delete
(from cache after /sessions), /rounds hints, and --flags. Pass prior
tokens so multi-arg completion works.
Create scratch dirs under system temp (tempfile), allow absolute paths
under them without rebinding the project workspace or session. Cleanup
owned temps on chat exit. Cap 16 concurrent temps; sanitize prefix.
classify_danger prompts on interactive shell/runtime launches and any -c
code (with argv + snippet preview). Confirm deny can attach a user comment
for the model. Restores ToolRegistry.execute after WIP breakage.
Add prek.toml so git commit runs ruff-pre-commit (fix then format) and
pdm-based basedpyright. Document install/install-hook; clear type warnings
that made basedpyright exit non-zero under recommended mode.
TOP = last element only for pop; multi-push puts first title on top for DFS
breakdown. Dropped nested-frame model; migrate old frames JSON to flat stack.
push of one or more titles opens a new frame (siblings at one depth);
pop leaves the frame. Supports T1,T2 → T1.1,T1.2 → pop → T2.1 pattern.
Legacy flat session JSON migrates to a single root frame.
Sub-task stack stored on session.todo_stack; model tools todo_*; slash
/todos for human ops; agent loop injects a review user message when open
todos exist and no todo_* tool ran this turn. Stack carries across /compact.
After /compact, reload seed from DB so _persist_from matches stored rows.
rebuild_client preserves the checkpoint via replace_messages. Clarify that
the active session is summary-only and full history stays on the old id.
Labels end with a newline before content. Switching reasoning↔assistant or
hitting tools/errors flushes the assistant markdown buffer so streams do not mix.
After each completed assistant+tool batch, persist and keep that prefix on
failure. Rollback only unfinished assistant/stream suffix. pending_retry
and /retry also apply when history ends with tool results (continue model
without re-executing tools).
Add agent config compact_system_prompt, compact_user_prefix, and
compact_seed_text; wire through summarize and seed messages. Fix default
user prefix to include {transcript}; use safe seed substitution so braces
in summaries do not break formatting.
Reject providers with no models into bad_providers and warn with reasons
on chat/providers. When /provider changes and the current model is not
listed, prompt for a new model (keep it when still supported).
Store provider_name/model on sessions (SQLite migrate); restore on
resume and persist on create//model//provider. Startup prefers session
selection over re-asking. ask/choose and provider/model pick use
readline with Tab completion when available.
NCBM