Open source AI coding agent. Designed for large projects and real world tasks.
Go aiai-agentsai-developer-toolsai-toolsclicommand-linedeveloper-toolsgitgolanggpt-4llmopenaipolyglot-programmingterminalterminal-basedterminal-ui
1.0.0 release notes
Dane Schneiderea68350ffa7f
diff --git a/releases/server/versions/1.0.0.md b/releases/server/versions/1.0.0.mdindex 461c852d..1ae05bef 100644--- a/releases/server/versions/1.0.0.md+++ b/releases/server/versions/1.0.0.md@@ -1,25 +1,24 @@-## ☄️ 🌅 A new era for AI driven development: gpt-4o is the real deal for coding agents+## ☄️ 🌅 gpt-4o is the real deal for coding-- gpt-4o, OpenAI's latest model, is the new default model for Plandex. 4o offers a step-wise improvement over gpt-4-turbo for coding tasks and agent-based workflows. Another level of capabilities is now achievable.+- gpt-4o, OpenAI's latest model, is the new default model for Plandex. 4o is much better than gpt-4-turbo (the previous default model) in early testing for coding tasks and agent workflows.- If you have not used `plandex set-model` or `plandex set-model default` previously to set a custom model, you will now be use gpt-4o by default. If you *have* used one of those commands, use `plandex set-model` or `plandex set-model default` and select the new `gpt-4o-latest` model-pack to upgrade.-## 🛰️ 🏥 Major reliability improvements: 90% reduction in syntax errors in early testing+## 🛰️ 🏥 Reliability improvements: 90% reduction in syntax errors in early testing- Automatic syntax and logic validation with an auto-correction step for file updates.- Significantly improves reliability and reduces syntax errors, mistaken duplication or removal of code, placeholders that reference other code and other similar issues.- With a set of ~30 internal evals spanning 5 common languages, syntax errors were reduced by over 90% on average with gpt-4o.-- Logical errors are also drastically reduced (I'm still working on evals for those to get more precise numbers).-- Plandex is now much better at handling larger files and plans that make many updates to the same file. These could be problematic in previous versions.-- Plandex is much more resilient to incorrectly labelled file blocks where the model used the file label format incorrectly to explain something rather than for a file. i.e. "Run this script" and then a bash script block. Previously Plandex would mistakenly try to create a file called "Run this script". It now ignores these kinds of blocks based on a simple heuristic.-- If you tried Plandex previously but found it too error-prone, I'd recommend giving it another shot. With gpt-4o and auto-correction, it's a new ballgame. We'll of course have to see what the stats are like in the wild, but it certainly looks promising.+- Logical errors are also reduced (I'm still working on evals for those to get more precise numbers).+- Plandex is now much better at handling large files and plans that make many updates to the same file. Both could be problematic in previous versions.+- Plandex is much more resilient to incorrectly labelled file blocks when the model uses the file label format incorrectly to explain something rather than for a file. i.e. "Run this script" and then a bash script block. Previously Plandex would mistakenly create a file called "Run this script". It now ignores blocks like these.-## 🧠 🚞 Major improvements to core planning engine: better memory and less laziness allow you to accomplish larger and more complex tasks without errors or stopping early+## 🧠 🚞 Improvements to core planning engine: better memory and less laziness allow you to accomplish larger and more complex tasks without errors or stopping early- Plandex is now much better at working through long plans without skipping tasks, repeating tasks it's already done, or otherwise losing track of what it's doing.- Plandex is much less likely to leave TODO placeholders in comments instead of fully completing a task, or to otherwise leave a task incomplete.- Plandex is much less likely to end a plan before all tasks are completed.-## 🏎️ 📈 Major performance improvements: 2x faster planning and execution+## 🏎️ 📈 Performance improvements: 2x faster planning and execution- gpt-4o is twice as fast as gpt-4-turbo for planning, summarization, builds, and more.- If you find it's streaming too fast and you aren't able to review the output, try using the `--stop / -s` flag with `plandex tell` or `plandex continue`. It will stop the plan after a single response so you can review it before proceeding. Use `plandex continue` to proceed with the plan once you're ready.@@ -27,27 +26,27 @@## 💰 🪙 2x cost reduction: gpt-4o is half the per-token price of gpt-4-turbo-- For the same quantity of output, with improved quality and 2x speed, you'll pay roughly half-price. Not too shabby.+- For the same quantity of tokens, with improved quality and 2x speed, you'll pay half-price.## 👩💻 🎭 New `plandex-dev` and `pdxd` alias in development mode-- In order to avoid conflicts/overwrites with the `plandex` CLI and `pdx` alias, a new `plandex-dev` command anbd `pdxd` alias has been added in development mode.+- In order to avoid conflicts/overwrites with the `plandex` CLI and `pdx` alias, a new `plandex-dev` command and `pdxd` alias have been added in development mode.## 🐛 🛠️ Bug fixes-- Fixed a potential panic during account creation (https://github.com/plandex-ai/plandex/issues/76)+- Fix for a potential panic during account creation (https://github.com/plandex-ai/plandex/issues/76)+- Fixes for some account creation flow issues (https://github.com/plandex-ai/plandex/issues/106)- Fix for occasional "Stream buffer tokens too high" error (https://github.com/plandex-ai/plandex/issues/34).- Fix for potential panic when updating model settings. Might possibly be the cause of or somehow related to https://github.com/plandex-ai/plandex/issues/121 but hard to be sure (maybe AWS was just being flakey).-- Attempted fix for rare git repo race condition @jesseswell_1 caught in the wild that gives error ending with:+- Attempted fix for rare git repo race condition @jesseswell_1 caught that gives error ending with:```Exit status 128, output* Fatal: unable to write new_index file```-I'm now treating those like deadlocks and retrying the git command a few times with a backoff since previous attempts at airtight locking seem to still let some error cases slip through no matter the approach. If you see this error again, please let me know on Discord or GitHub. Fun fact: Plandex implemented this fix (with assistance from ChatGPT which first conceived the general approach). I was just the reviewer. 😄## 📚 🤔 Readme updates-- The [readme](https://github.com/plandex-ai/plandex) has been revamped to be more informative, easier to navigate, and easier on the eyes. Check it out!+- The [readme](https://github.com/plandex-ai/plandex) has been revamped to be more informative and easier to navigate.## 🏡 📦 Easy self-contained startup script for local mode and self-hosting@@ -63,11 +62,7 @@ cd plandex/app- As always, cloud has already been updated with the latest version. To upgrade the CLI, run any `plandex` command (like `plandex version` or `plandex help` or whatever command you were about to run anyway 🙂)-## 📝 📞 Feedback--- As always, if you have any questions, feedback, or issues, please don't hesitate to reach out on [Discord](https://discord.gg/plandex-ai) or [GitHub](https://github.com/plandex-ai/plandex). I'm here to help and make Plandex the best it can be for you.--## 💬 📆 Join me for office hours every Friday 11am-12:30pm PST in Discord, starting May 17th+## 💬 📆 Join me for office hours every Friday 12:30-1:30pm PST in Discord, starting May 17th- I'll be available by voice and text chat to answer questions, talk about the new version, and hear about your use cases. Come on over and hang out!- Join the discord to get a reminder when office hours are starting: https://discord.gg/plandex-ai\ No newline at end of file