Codeep has a new look — and it's the same look everywhere now.
Terminal, Mac app, VS Code: one agent timeline. PLAN → READ → EDIT → VERIFY. #AI#buildinpublic → https://t.co/8w6MUNZMR8
MiniMax M3.1 Flash is the new MiniMax default, with a thinking control, and M3 cached tokens are no longer priced at half their cost. 🔗 https://t.co/AurffDJLsv #macOS
TL;DR — MiniMax M3.1 Flash is the new MiniMax default ($0.15/$0.60, 1M context), and DeepSeek's deepseek-flash is now V4.1-Flash-1017 with no change to price or id. 🔗 https://t.co/U9bHshxh2n #buildinpublic
TL;DR — A terminal run can now tell your phone right away, or after 15 s, 30 s, 1 or 5 min (Telegram run notices after, in /settings). 1 minute stays the default. 🔗 https://t.co/AUl6X0GmJ8 #buildinpublic
TL;DR — A launcher can hand Codeep its prompt in a file with --prompt-file, so it stays out of the process list. The Omarchy bar widget's Ask field does that from plugin 1.1.0. 🔗 https://t.co/d6TIFpzhaQ #buildinpublic
Gemini 4 Argon joins the Google model list as its new default, and tool calls on Gemini models work again: the app now sends back the thought signature Google requires. 🔗 https://t.co/FFH7LyFejg #macOS
TL;DR — Gemini 4 Argon is the new Google default ($2/$10 until 1 December), tried against Google's API. Its thinking tokens are counted, streamed replies once, and 3.7 and 3.5 Flash move to 3.8 and… 🔗 https://t.co/w9rvAkDOjp #buildinpublic
Codeep on Omarchy
Codeep now feels at home on #Omarchy.
Full details → https://t.co/33jvkB6ko6
A coding agent that actually belongs on the agentic Linux desktop.
TL;DR — On Omarchy, Codeep now sends a desktop notification when a run ends or waits for you (opt-in on other Linux), codeep usage --json prints your usage, and bar plugins can see its status. 🔗 https://t.co/xMQk7XbK3Y #buildinpublic
Claude Haiku 5.5 arrives, priced by how long each prompt is, and a request the model declines no longer starts a build or a test run. 🔗 https://t.co/H15DAYyeuh #macOS
TL;DR — Claude Haiku 5.5 arrives at $0.10/$0.50 (five times that past 100K prompt tokens), far fewer runs end "without a summary", and Always Allow now lasts the whole chat. 🔗 https://t.co/qOntsRwwen #buildinpublic
TL;DR — A new machine gets its API keys with codeep account sync --keys, account push skips keys from environment variables, the welcome block follows the session, and agent runs no longer end on… 🔗 https://t.co/xeeHhPthhr #buildinpublic
TL;DR — On Omarchy, Codeep now appears in the Agents panel with its plan, and its models count toward the panel's "Mostly …" line. A new local usage ledger in ~/.codeep/usage keeps no prompt text or… 🔗 https://t.co/8mOs9V8Z0l #buildinpublic
A long run you start at the Mac can send its answer to Telegram, and a declined request now says so, through OpenRouter too, instead of telling you to check your API key. 🔗 https://t.co/qRKw27YKV0 #macOS
TL;DR — codeep --help and the README now say what --yolo leaves unchecked: a shell command runs without asking and can write the files the file tools still ask about. 🔗 https://t.co/tq4xY1zjBy #buildinpublic
TL;DR — Fixes found on Omarchy: a one-word answer is no longer pushed to "continue", text and Enter typed together send, y/n answer safe questions at once, the header shows granted access, setup… 🔗 https://t.co/r9y6NVjp15 #buildinpublic
The Codeep mascot moves into the app (and into the Dock, if you like), the icon's inner chevrons are the logo's again, and the name beside the logo is set the way https://t.co/8w6MUNZMR8 sets it. 🔗 https://t.co/5TNifZbFqg #macOS
TL;DR — codeep --yolo -- "[prompt]" starts Codeep for a launcher with nothing left to answer, Omarchy's skills in ~/.agents/skills load, and Codeep's colours follow the Omarchy theme. 🔗 https://t.co/yYzq23aKAg #buildinpublic
A new chat opens on a provider you have a key for, the toolbar says what the agent is actually doing, and the Run inspector starts over with each request. 🔗 https://t.co/Bxr6bFvlmb #macOS
@ndhawan1 Me first. Watching a thinking model sit between steps while the screen still said “Listing” a tool that was already done was the lie. Users calling it stuck was the same bug with a different name.
TL;DR — While a thinking model works between steps, the agent screen now says it is waiting for the model and for how long, not "Listing" a tool that already finished. Auto-verify's checks show as… 🔗 https://t.co/1xqZHl2Bcv #buildinpublic