TeXRA

Appearance

ProgressBoard ​

The ProgressBoard is TeXRA's execution dashboard for tracking autonomous agents and inspecting their artifacts in real time. Whether supervising extended mathematical derivations or reviewing concise document edits, you can inspect streaming thoughts and tool calls, re-run tasks, or restore exact configurations with a single click.

CLI

The ProgressBoard is the VS Code extension's live view. The CLI shows the same streaming reasoning, tool calls, and diffs in its texra chat terminal UI. Past runs are shared across surfaces. Browse them with texra history list in the terminal, or in the Sessions tab of the TeXRA view in VS Code.

texra history
$texra history list -n 3
9f3a6c81d24e2025-11-04T14:31:08.412Zpolishcompleteddraft.tex
c4e19b07a52d2025-11-04T11:02:44.917Zresearchresumablesections/intro.tex
e2c70a94b18f2025-11-03T17:45:13.208Zcorrecterrorappendices.tex
$texra resume c4e19b07a52d
reopens the stored session in the chat TUI, on the saved agent and model

The board's runs, from a terminal: the same executions, one tab-separated row each. texra resume picks a stored session back up.

Opening the ProgressBoard ​

The ProgressBoard shares the TeXRA view with the launcher. Select the TeXRA icon in the Secondary Side Bar, then switch to the Sessions tab (the launcher is the New tab).

  • Automatic: It usually opens when you execute an agent.
  • Manual: Open it from the Command Palette (Ctrl+Shift+P or Cmd+Shift+P) with TeXRA: Show Progress, or press Ctrl+Alt+P (Cmd+Option+P on macOS).
  • Editor tab: Run TeXRA: Open Progress in Editor Tab to open the ProgressBoard as a full editor tab.
entanglement-paper — texra
% 3 references found · DOIs verified via Crossref
@article{wolff2021steady,
title = {Steady-state entanglement in driven spin chains},
author = {Wolff, S. and Kollath, C.},
journal = {Phys. Rev. A}, year = {2021},
doi = {10.1103/PhysRevA.103.022210}
}
Every entry resolves to a real DOI — no fabricated citations. ✓ 3/3 verified

The ProgressBoard: stream header and live log on the left, the run's output files on the right.

Layout overview ​

The ProgressBoard is split into two main sections (usually side by side, but configurable):

  1. Stream Tabs: A list on the side (often right) showing different agent runs (streams).
  2. Content Area: The main area (often left) displaying the header and log details for the selected stream.

Stream tabs section ​

This section lists the stored runs for the workspace, including runs from earlier sessions and from other TeXRA hosts; transcripts and run facts load from the workspace SQLite run database.

  • Switching streams: Select a stream name (e.g., polish: paper.tex) to view its logs and status in the Content Area.
  • Removing a stream: Each tab has an button that removes that stream and its logs from the ProgressBoard view.
  • Metadata: Tabs display the model and when the stream was last active on a second line. Icons indicate the agent type and whether multiple output files were generated.

Content area ​

This area shows the details for the stream selected in the Stream Tabs section.

The header provides a summary and actions for the selected stream:

  • Stream name: Displays the identifier of the current run. Tabs show the agent name (with #executionId when parallel runs would otherwise collide). Input files stay on the files panel, not on the tab chip. The model appears on the second line of the tab.
  • Status indicator: A colored circle shows the current status. The four states read at a glance:
RunningAgent is actively processing
WaitingPaused for your input or a follow-up
CompletedFinished (or cancelled) — grey
FailedThe run hit an error

The status dot: green while running, blue while waiting for input, gray once finished, red on error.

  • Token and cost summary: Displays the combined input and output token counts from all completed rounds (e.g., r0, r1, r2, …) along with the estimated cost.
  • Stream header actions: A toolbar of icon buttons acting on the selected stream. Workflow streams get Stop, Run New, Resume, Restore, Open in run storage, Export, Copy run context, Diff, Clean, and Pack; tool-use streams get Stop, AUTO-EDIT, AUTO-BASH, AUTO-TASK, Compact, Restore, Open in run storage, and Export. Export saves the conversation as Markdown, HTML, or PDF.
polish: paper.texr0–r2 · 48.2K in / 6.1K out · $0.21
StopAbort the running task
Run NewFresh run, same config
ResumeContinue saved outputs
RestoreLoad config into Launcher
OpenReveal run storage
CopyRun context to clipboard
Difflatexdiff vs. base
CleanDelete run folder
PackArchive to History

The stream header: identity and token/cost summary on the left, the action toolbar on the right, every icon mapped to its action.

Each action in detail:

  • Stop: Stops the running task for this stream. For providers supporting AbortController (like OpenAI or Anthropic) the active request is aborted immediately; otherwise the current API call finishes before stopping.
  • Run New: Starts a fresh run of the task associated with this stream using the exact same configuration (agent, model, files, instruction), discarding previous outputs. Useful for retrying failed tasks or reproducing results.
  • Resume: Continues the run from its saved outputs, picking up where it left off instead of starting over.
  • Restore: Loads the configuration (agent, model, files, instruction) from this stream back into the main TeXRA view, so you can modify and re-run a previous task.
  • Diff: Runs latexdiff to compare the original input file(s) with the generated output .tex file(s) from this stream. If no base file was selected, TeXRA uses the original file. Requires latexdiff to be installed. Read the LaTeX Diff guide.
  • Open in run storage:Reveals the run folder under run storage so you can browse generated files, compile logs, mirrored dependencies, and intermediate artifacts yourself.
  • Copy run context: Copies therun identity, output paths, and compile failures to the clipboard as plain text, so you can paste them into a new tool-use chat. The button is disabled when the run has neither outputs nor compile failures.
  • Pack: Archives the output files and log for this stream into the History folder. Read the file management guide.
  • Clean: Deletes the run folder associated with this stream.

Reviewed outputs are accepted per file: each row under Generated Files has an Accept action that copies the edited version into your workspace.

Auto-approve toggles ​

The header has three auto-approve toggles for the current run, matching the CLI status-bar badges. AUTO-EDIT (pencil) auto-approves file edits; AUTO-BASH (terminal) auto-approves shell commands — those two are independent, so turning one on does not take the other with it. AUTO-TASK (rocket) auto-approves delegated agent tasks and also later edits and commands — turning AUTO-TASK off returns all three to asking, including an AUTO-EDIT or AUTO-BASH grant you made on its own. Use them for work you trust; turn them off when you want to review each step.

Context utilization ​

A small percentage next to the token count shows how full the model's context window is. When it climbs toward 100%, the conversation may get compacted automatically, or you may want to start a fresh session.

Todo list ​

When a tool-use agent works on a multi-step task, it shows a live checklist in the ProgressBoard. Each item moves from Pending to In Progress to Completed, so you can see what the agent is working on and how far along it is.

Todos (2/4)
Ground the literature
Derive the concurrence
Formalize subadditivity in Lean
Write the discussion

A live checklist: completed items are checked and struck through, the active item spins, pending items wait.

After a workflow run ​

To follow up on a finished workflow in chat, use Copy run context in the header toolbar to put the run's output paths and compile failures on the clipboard, then start a tool-use chat from the New view and paste that text into the instruction box.

When a run recorded a compile failure, Run latexFixer still appears under Generated Files and starts a repair chat from those logs.

Memory ​

Tool-use agents can remember things between sessions. When memory is enabled (toggle in the Dashboard's Memory tab), agents save useful notes about your project. You can browse, pin, and delete these notes from the Memory tab in the Dashboard, or by running TeXRA: Show Memory from the Command Palette. Read the memory guide for a full walkthrough.

Log content ​

This scrollable area displays the detailed, timestamped logs for the selected agent run.

  • Structure: Logs are organized into expandable groups (e.g., Initialization, Round 0, Model Operation). Response cycles are logged within the corresponding round group. Select the arrow next to a group name to expand or collapse it.
  • Log levels: Messages are prefixed with levels like INFO, DEBUG, WARN, ERROR to indicate severity. Verbose debug messages (DEBUG) are only shown when texra.logger.debugMode is set to true in <project>/.texra/config.json or ~/.texra/global-storage/config.json; TeXRA does not read VS Code settings.
  • Agent thinking: The log highlights model reasoning in purple Thinking blocks. These sections are flagged internally with a thinking type so you can spot when the model is exploring ideas.
  • Errors: Errors are highlighted and often show what went wrong.
ProgressBoardlogSearch log…
All Info Warn Error
  • 14:02:11INFORun r0 started · spectral-gap.tex#a3f1
  • 14:03:48OKWrote r0/output.xml — 4 files
  • 14:05:02WARNApproaching context window — 182k/200k tokens
  • 14:05:39ERRORlatexdiff exited 1 — see build logr0/build/diff.log:84 Undefined control sequence \DIFadd

The log: each row is color-keyed by severity (green for info/success, yellow for warnings, red for errors), with expandable nested detail and per-task IDs.

The log content is the main source for diagnosing problems and seeing how TeXRA and the models process your requests. Read the troubleshooting guide for more on using logs.