tui: recover local no-output runs via history fallback

[TsekaLuk]

Summary

Fixes a TUI reliability bug where local runs can finalize as (no output) even though assistant text is persisted shortly after.

Code word: lobster-biscuit

Repro Steps

Related reports:

• bug(tui): MiniMax responses show '(no output)' until TUI restart #4499
• [Bug]: no output #15432

1. Start openclaw tui with a provider/model that intermittently emits empty chat.final payload text.
2. Trigger a run that finishes with (no output) in TUI.
3. Reopen/reconnect TUI and observe assistant text appears from history.

Root Cause

chat.final can occasionally arrive without renderable assistant text while transcript persistence catches up moments later. TUI currently finalizes immediately and never retries history for local runs, so users see (no output) until reconnect.

Behavior Changes

• For local runs only, if final text resolves to (no output) and stopReason is not error, schedule two short history refresh retries (200ms, 1000ms).
• Keep existing behavior unchanged for non-local runs and for runs with valid final output.
• Centralize no-output placeholder handling in formatter helpers.

Codebase and GitHub Search

• Code paths searched:
  • src/tui/tui-event-handlers.ts
  • src/tui/tui-stream-assembler.ts
  • src/tui/tui-formatters.ts
• Issue search checked:
  • bug(tui): MiniMax responses show '(no output)' until TUI restart #4499 (MiniMax responses show '(no output)' until TUI restart)
  • [Bug]: no output #15432 ([Bug]: no output)

Tests

• pnpm vitest src/tui/tui-event-handlers.test.ts src/tui/tui-formatters.test.ts --run
• pnpm check

Manual Testing

Prerequisites

• A TUI session connected to gateway.

Steps

1. Run a local TUI conversation where a final event may be empty.
2. Confirm TUI schedules short history fallback and self-recovers without restart.
3. Confirm normal final outputs still render once with no extra history churn.

Evidence

• Added targeted test: local final (no output) triggers 2 history retries in src/tui/tui-event-handlers.test.ts.

Sign-Off

• Models used: GPT-5 Codex
• Submitter effort (self-reported): High
• Agent notes (optional, cite evidence): Local targeted tests + lint/type checks passed.

[rmdmattingly]

CI note: a bunch of checks are marked cancelled (android/checks-windows/release-check/checks/macos/build-artifacts/changed-scope/install-smoke/label/label-issues). This looks like the workflow runs were cancelled rather than a code failure.

I don't have admin rights to rerun from CLI; maintainer rerun on branch codex/tui-no-output-history-fallback should be the next step.

One of the cancelled runs: https://github.com/openclaw/openclaw/actions/runs/21991887337

[TsekaLuk]

Hey! 👋 CI is all green on this one. Would you have time to take a look? Happy to make changes if needed. Thanks!

[TsekaLuk]

Thanks for the heads up! I don't have admin rights either. Could a maintainer with admin access kindly rerun the failed checks? Thanks!

[openclaw-barnacle]

This pull request has been automatically marked as stale due to inactivity.
Please add updates or it will be closed.