Viewing profile — azurewraith

...or that one time I blew 60% of my Codex x20 weekly usage allotment in under 24 hours... We've all had the same struggle, torn between wanting to run longer loops and maximize ou…

[dead]

Three layers working together: UserPromptSubmit hook: injects state context into every prompt... phase, available tools Instructions: the model sees transition() and get_state() as…

Here's a week 2 update. a lot shipped since this post... OSS: The `engine` and `agent` crates are now fully open (Apache 2.0). only the `gateway` and the various plugins are FSL wi…

update: I released the of the crates (with the exception of the gateway as FSL) as Apache 2.0 today (and uploaded to crates.io) along with a UI piece that's Apache 2.0 as well. You…

Interestingly enough we have found the same net result -- structural guardrails are the unlock for smaller models. Our approach in particular layers three things: a parse rescue fo…

yeah... I wanted the smaller models to behave more like their state of the art siblings and was a little shocked that it just didn't work well... so I made small models work better…

[dead]

[dead]

shipped ^_^

[dead]

Hey it's me again. Some things that didn't fit in the README or the original post -- less about features, more about where this goes. The plan/implement/test workflow is very basic…

> you might want to add an actual exclusion to the patents/licenses for those groups of people Done :) https://github.com/statewright/statewright/blob/main/PATENTS... Thank you for…

I feel you on the Claude pulsing thing. Running (or trying to) run Opencode with any model I could throw at it to perform useful work like the frontier/proprietary models do (a tal…

[dead]

the Cargo.toml covers the built Rust crates (engine, agent). the plugins/ directory has it's own LICENSE.md with the FSL terms. split license: the engine is completely open source,…

bingo! and that's where this journey began, it's been fun proving it out ^_^

the colors are based on the event name.... green for happy path events (READY, DONE, PASS), red for failure events (FAIL, ERROR) and purple for everything else they don't indicate …

you're not wrong and trimming context is legitimately the first thing that everyone should do. even with context trimming and a tight prompt the model still makes judgement calls a…

you're hitting the nail on the head... rules in prompts are suggestions the model can rationalize away. "the task is so simple that maybe I don't need worktrees" is the model overr…

Yes, the engine handles the full workflow schema including guards. There are some aspects of runtime enforcement (env vars/command filtering, etc. exposed via the UI) that currentl…

Nice project... the per-agent tool restriction is the same core insight (smaller tool space -> better reasoning) The main difference with Statewright is that tool access changes ov…

Great question... and there are two answers depending on what you were originally referring to: re: Claude Code... we actually don't filter or modify the tool list so all tools sta…