fix(tui): responsive /compress with live progress + CLI-parity feedback (#17661)

* fix(tui): offload manual compaction RPC

Route TUI session compression through the existing long-handler pool so slow compaction does not block other gateway RPCs.

* fix(tui): show compaction progress immediately

Print a local status line before the compress RPC starts so slow manual compaction does not look like a no-op.

* feat(tui): rich /compress feedback parity with CLI

Show pre-compaction message count and rough token estimate immediately, emit a status update so the bottom bar reflects ongoing compaction, and report a multi-line summary (headline + token delta + optional note) using the shared summarize_manual_compression helper.

* fix(tui): show live compaction estimate in transcript

Mirror compression progress status into the transcript so users see the backend message count and token estimate while /compress is still running.

* fix(tui): single live compaction line with spinner glyph

Drop the redundant local "compressing context..." placeholder and prefix the live backend status line with a braille spinner glyph so /compress reads as a single in-progress row.

* fix(tui): address review nits on /compress feedback

Reuse the precomputed token estimate inside _compress_session_history so the gateway does not redo the O(n) work while holding history_lock, keep the status bar pinned during long manual compactions instead of auto-restoring after 4s, and drop the redundant noop bullet that doubled with the system role glyph.

* fix(tui): release history_lock during compaction LLM call

Move the snapshot/commit pattern into _compress_session_history so the lock is held only across the in-memory bookkeeping, not during agent._compress_context. Also emit a final neutral status update from session.compress so the pinned compressing indicator clears even on errors.

* fix(tui): rebuild prompt cleanly + sync session_key after compress

Pass system_message=None so AIAgent._compress_context rebuilds the system prompt without nesting the cached identity block. Reuse the handler's pre-snapshotted history inside _compress_session_history to avoid a second O(n) copy under the lock. After compaction, when AIAgent._compress_context rotates session_id, sync the gateway session_key, migrate approval notify + yolo state, restart the slash worker, and clear the stale pending title. Mirrors HermesCLI._manual_compress.

* Avoid /compress lock re-entry in slash side effects.

Stop pre-locking history before _compress_session_history in slash command mirroring, keep session-key sync parity with manual compression, and add a regression test that asserts /compress is invoked without holding history_lock.
This commit is contained in:
brooklyn!
2026-04-29 18:01:18 -07:00
committed by GitHub
parent 98f5be13fa
commit fc7f55f490
7 changed files with 309 additions and 29 deletions
@@ -119,6 +119,19 @@ describe('createGatewayEventHandler', () => {
expect(getTurnState().todos).toEqual(todos)
})
it('prints compaction progress status into the transcript', () => {
const appended: Msg[] = []
const ctx = buildCtx(appended)
const onEvent = createGatewayEventHandler(ctx)
onEvent({
payload: { kind: 'compressing', text: 'compressing 968 messages (~123,400 tok)…' },
type: 'status.update'
} as any)
expect(ctx.system.sys).toHaveBeenCalledWith('compressing 968 messages (~123,400 tok)…')
})
it('clears the visible todo list when the todo tool returns an empty list', () => {
const appended: Msg[] = []
const todos = [{ content: 'Boil water', id: 'boil', status: 'in_progress' }]