|
| ▲ | walthamstow 2 hours ago | parent | next [-] |
| I have used it for little more than 6 hours or so in total but I'm pretty sure it doesn't have compaction? |
| |
| ▲ | KeplerBoy 2 hours ago | parent | next [-] | | How else would it work? Less technical people don't even watch their context usage. | | |
| ▲ | macNchz 39 minutes ago | parent [-] | | In the olden times, aka like two years ago, AI chats would just stop working or just start slicing off the oldest parts of the context to fit the model's window. That said, compaction feels like an idea that should work reasonably well, but across all of the major providers and agent tools I've used has never actually produced compelling results, to where if I see I'm getting close to the token limit I prefer to start putting a bow on the project and readying it for a fresh start. Even when I provide a detailed compaction prompt it usually focuses on the wrong stuff. | | |
| ▲ | Vacyyyy 17 minutes ago | parent [-] | | Do you have experience with OAI's, it's been known to be to be good for a while now, going off public consensus and my experience. |
|
| |
| ▲ | honr an hour ago | parent | prev [-] | | It certainly has compaction (since the public launch I assume) and I HATE it. I have some remedies but nothing perfect yet. It never retains ALL the crucial bits. If a conversation runs into two compactions it is often a sign that I have to abandon it and retain whatever I can, to form a seed prompt for an adjacent conversation. | | |
| ▲ | tobias2014 a minute ago | parent [-] | | That is really the biggest beef I have with agy over others, the forced auto compaction at the 250k token threshold (3.8-flash), while the model itself (via API) would be fine with a 1M context window. Even if the model is great, restricting context to 250k tokens (and auto compacting no matter what) limits certain applications and workflows somewhat. |
|
|
|
| ▲ | sarjann 2 hours ago | parent | prev | next [-] |
| Auto mode? |
| |
| ▲ | KeplerBoy 2 hours ago | parent [-] | | It absolutely has auto mode. | | |
| ▲ | smartbit an hour ago | parent | next [-] | | agy cli does not have auto mode. I've tried and tried and tried to work with agy cli sandbox-mode and just failed. agy --dangerously-skip-permissions
in my experience is the only workable solution that doesn't ask confirmation for every step. And I hate working in YOLO mode. Seemingly the Antigravity GUI had some features added in a recent release, but a) I don't want to work with the GUI and b) it was poorly implemented as I couldn't get it to work. VS Code plugins are allowed with subscriptions, but is not the CLI experience of Claude Code I want.gemini-cli supported 'pre-write diff tabs' (y/n) in external editors like vscode. In Claude Code I heavily use 'pre-write diff tabs' for documentation and miss it sincerely in agy cli. IMHO Gemini 3.8 flash is fast and good enough, but the agy-suite is below par to say it nice. Someone else in this thread calls agy a terrible harness which is probably more accurate. | |
| ▲ | SomaticPirate an hour ago | parent | prev | next [-] | | I think it only has "--dangerously-skip-permissions"
Claude and codex auto mode will reject certain actions.
No secondary check on gemini/agy AFAIK | |
| ▲ | levelZero 2 hours ago | parent | prev | next [-] | | Via cli switch, but in process w/o fine graining? If so please tell | |
| ▲ | LoganDark an hour ago | parent | prev [-] | | Auto mode means that another model reviews tool calls to attempt to disallow less safe ones. It's different from bypass permissions mode which typically just doesn't filter at all. |
|
|
|
| ▲ | arizen 2 hours ago | parent | prev | next [-] |
| Does it have /goal feature similar to Codex? |
| |
|
| ▲ | esafak 2 hours ago | parent | prev [-] |
| I use a variety of models for various subagents. I don't want to change my harness every time I change models, or be beholden to companies for something the open source community can handle better. |
