91–100 of 128 posts
This is really nice, thanks for sharing! If you don't mind a little feature request, I'd love to have a "thinking level" selector on the GUI for models that have it. I really like how easy it is to verify exactly what happened on each tool call, inspect the thinking blocks, etc.
Seems to work when I click the juggler.app in Ubuntu 24.04 (Noble Numbat) GNOME's desktop. Running same app via terminal does not launch the app. Appear to be a sandbox issue common in Noble Numbat. In this case, WebKitGTK's sandbox failing to initialize properly via bubblewrap.
Love the "session is a document, not a log" model — linear scrollback is the worst part of long agent sessions. When you fork a sub-thread, does the model get the full parent context up to the branch point, or can you trim what carries over? Context bloat across a lot of branches feels like the hard part.
So I've just made it so they don't inherit! If we find a situation where inheriting is useful and safe, it'd be easy to add again.
The "session is a document, not a log file" framing is the part I'd underline. Being able to inspect and edit the raw context JSON going to the model is criminally rare, most tools treat the context as a black box, and on long runs context bloat is the single biggest cause of the model quietly drifting. Making it inspectable and prunable is a real lever, not a gimmick. The thing I'm curious about: once you branch, ba…
Where I've found editing to be the most useful is e.g. when I've had a long task that got a bit rambling and digressed, and then I go away and need to resume it later. Leaving it means the provider will have lost the cache for it, but rather than spending a lot of tokens to /compact or just to continue the entire thread, you can go through and delete all the useless bits, maybe just leaving enough content in there for the LLM to figure out how to continue, and then get back on track quite cheaply
Mmm I added my Gemini Key and selected the model, but the Add Provider pop-up keeps appearing. In the Default Model tab it says: Provider is configured but has no API key. EDIT: it seems I have having network issues, the model selector in the chat input says it could not load models and yeah, now aistudio is also not loading.....story of my life hhhh EDIT2: not sure whats going on, my connection is back but now the P…
Mmm I added my Gemini Key and selected the model, but the Add Provider pop-up keeps appearing. In the Default Model tab it says: Provider is configured but has no API key. EDIT: it seems I have having network issues, the model selector in the chat input says it could not load models and yeah, now aistudio is also not loading.....story of my life hhhh EDIT2: not sure whats going on, my connection is back but now the P…
Hmm, if you spot anywhere you think the app could be more helpful in diagnosing the problem let me know..
Earlier quoted context omitted.
Hmm, if you spot anywhere you think the app could be more helpful in diagnosing the problem let me know..
Yeah some debugging like webinspector or some kind of console? I guess I should start it headless maybe to see whats going on?
Another VPN: $ [ERROR] computeProviders: list models from gemini failed: failed to list models from Gemini: HTTP 400
Earlier quoted context omitted.
Yeah some debugging like webinspector or some kind of console? I guess I should start it headless maybe to see whats going on?
I think it is my connection....$ [ERROR] computeProviders: list models from gemini failed: failed to list models from Gemini: Get " https://generativelanguage.googleapis.com/v1beta/models ": context deadline exceeded. Another VPN: $ [ERROR] computeProviders: list models from gemini failed: failed to list models from Gemini: HTTP 400
Earlier quoted context omitted.
I think it is my connection....$ [ERROR] computeProviders: list models from gemini failed: failed to list models from Gemini: Get " https://generativelanguage.googleapis.com/v1beta/models ": context deadline exceeded. Another VPN: $ [ERROR] computeProviders: list models from gemini failed: failed to list models from Gemini: HTTP 400
yeah, sounds like your network's in a muddle somehow