Gemini CLI v0.69.0 maps your token usage and stops silent network hangs
1 day ago
Gemini CLI v0.69.0 adds /stats heatmap, a calendar of your daily token usage, and stops the silent multi-minute spinner when the network fails. It also stops hours of quota retries, lets long-thinking requests wait past 60 seconds, fixes out-of-memory crashes and resume errors in long sessions, and fixes piped input, /model with a name, standalone theme.json themes, PowerShell commands with parentheses and macOS sandbox folder trust.
Links
Ask about this presentation
Chapters
0:00A calendar of your token usage
0:12Name a day and the heatmap breaks it down
0:2501: When the network fails
0:27A failing network now says so
0:39An exhausted quota stops instead of waiting hours
0:50Long-thinking requests can wait past 60 seconds
1:0102: Long sessions
1:02Long sessions stop running out of memory
1:15Resuming an interrupted session works
1:2803: Scripts and commands
1:29Headless runs get every byte and the right exit code
1:41/model takes a model name and checks it
1:53Custom colors can live in their own theme.json
2:06Gemini CLI won't start a second copy inside shell mode
2:1804: Windows, macOS and VS Code
2:20PowerShell commands with parentheses run again
2:33The macOS sandbox remembers trusted folders
2:47The VS Code companion is 80 percent smaller
3:01Should you upgrade?
Show transcriptHide transcript
Gemini CLI now draws your token usage as a calendar. The stats heatmap command shows 28 weeks of daily usage in GitHub style, with your current streak and your longest.
Add a date, or yesterday, and the heatmap splits that day's tokens into input, output and cached, with each model's share. It counts local chat sessions only.
When the network fails.
A dropped connection could leave Gemini CLI spinning for up to twenty minutes with no error. Now each network retry shows on screen, and an unreachable host fails on the first try.
When your quota ran out with a reset hours away, Gemini CLI kept retrying until the reset. Now it stops at once, and an interactive session offers the fallback prompt.
A request that thought for over a minute before answering was dropped and sent again. Now you can raise that 60-second limit, on Vertex AI and API keys too.
Long sessions.
Sessions that kept reading files, screenshots or PDFs could crash with a JavaScript heap out of memory error. Now older images and PDFs leave the history, and tool output is capped.
If you stopped Gemini CLI while the model was thinking, resuming could fail with a 400 error. That is fixed, and long session files load without freezing the terminal.
Scripts and commands.
In headless mode, Gemini CLI dropped piped input slower than half a second. Now it waits for the whole pipe, kills its child shells on Ctrl+C, and exits with the right code.
The model command ignored a name typed after it and opened the picker. Now it switches straight to that model, rejects unknown names, and tab-completes valid ones.
Custom themes can now live in their own file, theme.json, in your Gemini folder. Palette generators like pywal and matugen can rewrite it without touching your settings.
Typing gemini in shell mode started a second Gemini CLI inside the shell pane, and the two fought over the screen. Now that is blocked, and headless prompts still run.
Windows, macOS and VS Code.
For several releases, Gemini CLI blocked ordinary PowerShell commands with parentheses as command substitution. They run again, and a substitution you approve now actually runs.
In the macOS Seatbelt sandbox, Gemini CLI asked to trust the folder on every launch, then failed to save your answer. Now it remembers, and shell commands stop leaking terminal handles.
The VS Code companion bundled all of Gemini CLI's core, about 14 megabytes loaded at startup. Now it ships under 2 megabytes and starts its server only when Gemini CLI connects.
I would say yes, if you use Gemini CLI through Code Assist on Google Cloud and your sessions run long. It still isn't tuned for Gemini 4 models. The rest is in the release notes.
Up next
3:04Gemini CLI v0.70.0 lets long requests finish and asks before shell globs
@gemini-cli
9 hours ago
3:26Gemini CLI v0.68.0 isn't tuned for Gemini 4, and counts down rate limits
@gemini-cli
1 week ago
3:18Gemini CLI v0.67.0 opens VS Code diffs from inside Docker and gVisor sandboxes
@gemini-cli
2 weeks ago
3:13Gemini CLI v0.66.0 isn’t optimized for Gemini 4 Argon, so Google points you to Antigravity
@gemini-cli
2 weeks ago
2:30Gemini CLI v0.65.0 stops deleting your chat history when you resume and quit
@gemini-cli
1 month ago
3:03Gemini CLI v0.64.0 stops parallel agents overwriting each other’s edits
@gemini-cli
1 month ago
3:04Gemini CLI v0.63.0 caps memory in long agent runs
@gemini-cli
1 month ago
2:38Gemini CLI v0.62.0 keeps you signed in with Google
@gemini-cli
1 month ago
3:05Gemini CLI v0.61.0 adds Gemini 3.8 Flash and guards build files
@gemini-cli
1 month ago
2:36Gemini CLI v0.58.0
@gemini-cli
2 months ago