Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

EvanFlow – A TDD driven feedback loop for Claude Code

github.com

Post reply on HN
Print view View original

71–75 of 75 posts

Re: EvanFlow – A TDD driven feedback loop for Claude Code

#71

Post by collingreen »

evanklem2004 wrote: post #63
shruubi wrote: post #8

Two questions 1) Do you not feel self-conscious or weird about calling this "EvanFlow"? Seems like a lot of people these days are naming their AI tools/skills/whatever after themselves which seems self-absorbed. Either that or they hope that if their thing takes off like OpenClaw did then they'll grab the fame that comes along with it. 2) Why does your TDD flow miss the refactor step of TDD?

1): you have things backwards, the EvanFlow is not something i came up with but rather something i discovered similar to the dao. i am named Evan after the EvanFlow not the other way around. 2): you're right and dmitry called this out below too. shipped a fix that puts REFACTOR per-cycle, instead of being a deferred "after all tests pass" step. the old step 4 was iterate-shaped not TDD-shaped.

> 1): you have things backwards, the EvanFlow is not something i came up with but rather something i discovered similar to the dao. i am named Evan after the EvanFlow not the other way around.

What does this mean?

Re: EvanFlow – A TDD driven feedback loop for Claude Code

#72

Post by kevinluddy39 »

thisisfatih wrote: post #66

The refactor-per-cycle fix lands in the right place. The harder problem shows up when EvanFlow forks into parallel coder/overseer mode: unit tests pass per agent, but the seams break at merge. Your note that "integration tests at touchpoints ARE the cohesion contract" is exactly right, but enforcement is what makes it stick. Each parallel branch needs its own failing test that can't be masked by another branch's gree…

The per-agent-green / merge-broken pattern is the diagonal failure mode of multi-agent systems. Unit testing each agent in isolation captures correctness within scope; what's invisible is the seam at handoff — argument schemas drifting between coder and overseer, response shapes that satisfy each agent's local validator but break the next's parser, error messages that get summarized into "no error" by the time they reach the orchestrator.

  Built tool-call-grader to instrument exactly this. Session-level statistics across the tool-call trace plus six pathology detectors (silent failure, tool fixation, response bloat, schema drift, irrelevant response, cascading failure). On a hand-designed multi-agent benchmark, 7/7 scenarios passed — including specifically the case you're describing:
  per-agent results look fine, schema-drift fires at the seam.  
  The detector runs over the trace, not the output. Catches the failure several turns before it shows up as "weird merge bug" the human has to debug. MIT licensed, npx-installable. Methodology in profile.

Re: EvanFlow – A TDD driven feedback loop for Claude Code

#73

Post by evanklem2004 »

collingreen wrote: post #71
evanklem2004 wrote: post #63

Earlier quoted context omitted.

1): you have things backwards, the EvanFlow is not something i came up with but rather something i discovered similar to the dao. i am named Evan after the EvanFlow not the other way around. 2): you're right and dmitry called this out below too. shipped a fix that puts REFACTOR per-cycle, instead of being a deferred "after all tests pass" step. the old step 4 was iterate-shaped not TDD-shaped.

> 1): you have things backwards, the EvanFlow is not something i came up with but rather something i discovered similar to the dao. i am named Evan after the EvanFlow not the other way around. What does this mean?

sit under the lotus tree and it will come to you

Re: EvanFlow – A TDD driven feedback loop for Claude Code

#74

Post by subscribed »

shruubi wrote: post #8

Two questions 1) Do you not feel self-conscious or weird about calling this "EvanFlow"? Seems like a lot of people these days are naming their AI tools/skills/whatever after themselves which seems self-absorbed. Either that or they hope that if their thing takes off like OpenClaw did then they'll grab the fame that comes along with it. 2) Why does your TDD flow miss the refactor step of TDD?

Now go challenge Linus Torvalds :D

Re: EvanFlow – A TDD driven feedback loop for Claude Code

#75

Post by collingreen »

evanklem2004 wrote: post #73
collingreen wrote: post #71

Earlier quoted context omitted.

> 1): you have things backwards, the EvanFlow is not something i came up with but rather something i discovered similar to the dao. i am named Evan after the EvanFlow not the other way around. What does this mean?

sit under the lotus tree and it will come to you

That's what I thought but I figured I'd give the benefit of asking first before I passed judgment on the snark.
Post reply on HN