feat(v1.11.0): Research-Grounded OODA — the anti-maze methodology#78
Merged
Conversation
The f1 probe iterated without improving (local-optimum maze) because generation was anchored to model priors, not external ground truth. Heavy external research (graphics/physics/art + methodology literature) → a cited playbook + a 5-part fix: pre-generation research grounding (dev-cycle Step 3-PRE, AlphaCodium), reference targets (config.references/research), reference comparison in the 5-G critic, stall→REWRITE escalation with a Reflexion negative-example memo (evolve 2-G + recommend_rewrite()), and diagnose/fix isolation (MASAI). verify.py 64. plugin 1.10.1→1.11.0. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Root cause the f1 probe exposed: the loop iterates without improving (a local-optimum 'maze') because generation is anchored to model priors, not external ground truth.
Heavy external research (graphics/physics/art + the methodology literature) produced a cited playbook AND this 5-part fix, each grounded in published work:
config.references+config.research(named real-product levels + reference-impl URLs + research playbook path).recommend_rewrite()+ evolve 2-G: when incremental leaps themselves stall, rewrite from a cited reference with a Reflexion negative-example memo, before HALT.New helper + test. verify.py 64. plugin 1.10.1→1.11.0.
🤖 Generated with Claude Code