Recordings and reports

Read the recording

Ask the agent for the recording’s path, then open transcript.md in that directory. It shows calls and results across all worker sessions, including recorded images and links to retained output. Links labeled “Session NNN source (QMD)” open source documents in sessions/session-NNN.qmd, one for each worker session that received source. Those files contain code and environment metadata; recorded results and images remain in transcript.md and the capture files. Raw text and images are grouped under capture/sessions/NNN/ by worker session and observed startup, cell, or post-cell interval. Completed files are read-only; copy a file before editing it. For the dice example in Get started, you can inspect both the simulation and the later comparison that reused its results.

The recording documents what happened; it does not save the live Python objects, R objects, or in-memory database for a later session. To repeat an analysis, you will need its inputs and reviewed code.

Retrieve omitted output

Console limits how much text it sends to the agent at once. When a response leaves out text, a notice points to the existing log file and says if any output could not be saved. The agent can read that file with its client’s file-reading tools, without running the code again.

The agent can also read the log while the code is still running. Console updates the log before sending each response. Reading it does not remove output from later responses.

Logs contain the text that R, Python, or SQL displayed. For example, if a table’s display includes only a few rows, the log contains that abbreviated display. To get the complete data, ask the agent to fetch it or save it to a file. For SQL, your agent can retrieve the last result in R or Python without running the query again.

Reference: Retrieve the last SQL result.

Turn the code into a report

Each sessions/session-NNN.qmd is a starting point for a report, not a replay or checkpoint. It contains the R, Python, and SQL source associated with that worker, including failed evaluations, rejected calls, and source submitted alongside a control. Restarts and automatic worker replacement begin a separate document; an interrupt that preserves the worker stays in the same document. The documents omit interactive input, polling, control operations, output, and recorded images.

Copy it before editing:

cp sessions/session-001.qmd report.qmd

Review the code, inputs, package declarations, and evaluation settings in report.qmd. Rendering executes code outside the Console sandbox.

After reviewing the copy:

uv tool run --from r-lib-ir ir render report.qmd

With ir already installed, use ir render report.qmd.

Rendering requires R, even when the original session used only Python. SQL chunks need a user-supplied DBI connection. Package declarations are not a lockfile or a complete history of the environment. Each document records accepted requirements for its worker session and describes the original working directory without setting the rendering directory. Copy required inputs beside the working copy or adjust their paths before rendering. Chunks permit errors so a recorded failure does not prevent reviewing later code; review those failures before relying on the report.

Reference: Recording storage, files, and retention.

For other workflows, the documentation index links to guides by what you want to do. To prepare Console for a particular project or agent, continue with Build a data assistant.