Conversation
Three modes: `rlm` launches interactive split-pane session, `rlm --replay [id]` opens session browser or step-through replay, `rlm --replay <id> --inspect` opens verifiers-style collapsible overview. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…ount order - Rename _running to _engine_running to avoid collision with Textual's MessagePump._running (was silently breaking all event handlers) - Show errors in session pane when engine init or API call fails - Add _extract_tool_call() to handle both engine log format and OpenAI wire format for tool calls - Fix MountError by passing children to Vertical() constructor instead of mounting into detached widget Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Panes now split next to their parent when a sub-agent spawns, with siblings stacking vertically — visual hierarchy mirrors the call tree. Replay mode creates panes incrementally as entries are stepped through (j/k), not all at once. Interactive mode rebuilds on new child discovery. Both modes share the same visual behavior. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
rlm), step-through replay (rlm --replay [id]), and verifiers-style collapsible inspection (rlm --replay <id> --inspect)prime evalTUIFiles changed
pyproject.toml— addtextual>=1.0dep,textual-devdev depsrc/rlm/cli.py— wire--replay/--inspectflags, replace_run_interactive()stubsrc/rlm/tui.py— full TUI:SessionData,SessionPane,PaneLayout,InspectionView,SessionBrowser,ReplayView,InteractiveView,RLMAppsrc/rlm/tui.tcss— warm-theme stylesheet with verifiers-inspired collapsible/panel/scrollbar stylingTest plan
rlm— interactive TUI launches, type prompt, watch live pane updatesrlm --replay— session browser shows past sessions with tree widgetrlm --replay <id>— step-through replay with j/k, split panes for nested sessionsrlm --replay <id> --inspect— collapsible overview, e/x expand/collapse alldtoggles dark/light theme in all viewszzooms focused pane in replay/interactive views🤖 Generated with Claude Code