{"items":[{"id":"97fc2420-640e-4407-9a33-3a876fc2d962","type":"pull_request","org":"jeffwweee","repo":"devspace","title":"Fixed the AI workflow to require explicit design and plan approval before compacting history.","summary":"Previously, the AI assistant would automatically run a compact check right after saving a design or plan doc, effectively bypassing the review phase and auto-proceeding. The prompt definitions for brainstorming and writing plans have been refactored to explicitly wait for human approval signals (like \"LGTM\" or \"yes proceed\") before checking context limits and moving on. This puts the user back in control and guarantees your changes are actually reviewed before execution begins.","url":"https://nomit.dev/jeffwweee/devspace/status/db34cf2f23c9a908b75a365c2c48c23d9983b4d8d426f67f338aa8e55ebe7e92","author":"jeffwweee","contributors":["jeffwweee"],"updated_at":"2026-03-04T07:18:10+00:00"},{"id":"b3e1e08d-93d7-4369-99f1-9c1d38dcf220","type":"pull_request","org":"jeffwweee","repo":"devspace","title":"Fix blocking background tasks and introduce robust session management","summary":"Previously, the system blocked message processing for up to 60 seconds whenever it spawned a background task, causing unresponsiveness. This update makes background executions completely non-blocking so the main message loop immediately returns to action. We've also introduced phase completion markers, an `/end-session` command, and state tracking to handle transitions more gracefully. Your bot will now feel significantly snappier while juggling heavy asynchronous tasks.","url":"https://nomit.dev/jeffwweee/devspace/status/646d3d2145c6c7e2f89da6a39e9f3d353d3234de59febb18e5e389c233244b77","author":"jeffwweee","contributors":["jeffwweee"],"updated_at":"2026-03-04T06:45:48+00:00"},{"id":"18d85994-7bbe-425d-974e-0887afba56f9","type":"pull_request","org":"jeffwweee","repo":"devspace","title":"Implement retry tracking and escalate infinite loops while optimizing token efficiency","summary":"This update introduces a comprehensive retry tracking and escalation workflow to prevent agents from getting stuck in infinite failure loops. By enforcing a 3-retry limit and explicitly seeking confirmation before escalation, the workflow ensures persistent failures are addressed properly. Additionally, an extensive refactoring of eight core skills offloaded heavy context into reference files, resulting in an estimated 65% reduction in token usage per message. \n\n![Refactoring codebase](https://i.redd.it/xe4qa02fwi791.png)","url":"https://nomit.dev/jeffwweee/devspace/status/6875b0e1f0b8c36237f285818eb5be02d50918ec8cf9491aef959e643c480198","author":"jeffwweee","contributors":["jeffwweee"],"updated_at":"2026-03-04T03:51:41+00:00"},{"id":"f3e24f87-05e1-467c-bed5-c8b0002d25b0","type":"push","org":"jeffwweee","repo":"devspace","title":"Update Commander skill capabilities for file attachments and background task handling","summary":"The Commander skill documentation has been updated to include usage instructions for the `send-file.sh` helper script, allowing the bot to send file attachments like markdown files or documents directly to Telegram. The subagent workflow has also been revised to utilize the `background-tasks` skill, which keeps the bot responsive to new messages instead of blocking during long operations. This properly offloads heavy implementations and improves overall bot responsiveness.","url":"https://nomit.dev/jeffwweee/devspace/status/4db3f4dad45d886188a0faa10f7b34afa0b33244f8ff0a16c56ec9f9f19e8eec","author":"jeffwweee","contributors":["jeffwweee"],"updated_at":"2026-03-03T18:09:45+00:00"},{"id":"c6027583-c2a3-4b45-9645-0ba3fdc8f41f","type":"push","org":"jeffwweee","repo":"devspace","title":"Implement lazy-loading for memory files and optimize startup token usage","summary":"We've revamped how Commander handles its context to drastically reduce startup token usage from ~3500 to ~400 tokens. Memory files are now lazy-loaded on demand via a new `/memory` command, rather than being dumped in at the start of every session. We also added an `identity.md` file that is read on every message to ensure core identity persists through context compactions. This makes starting fresh sessions significantly cheaper and keeps the context window focused.","url":"https://nomit.dev/jeffwweee/devspace/status/b96f8533aa62ed64c8940c68290e0ea795401e5fe6e0791e85b62a468c7758d4","author":"jeffwweee","contributors":["jeffwweee"],"updated_at":"2026-03-03T17:33:51+00:00"}],"pagination":{"offset":0,"limit":5,"has_more":true}}