Skip to content

Add world-model evaluation harness, learned MCTS action priors, docs, and README/training updates #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jeevesh415 wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Add world-model evaluation harness, learned MCTS action priors, docs, and README/training updates #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
0db3f49
Add phase-1 rigorous world-model evaluation harness and protocol
jeevesh415 May 16, 2026
07b8481
Add perception evaluation track and harden training bootstrap fallback
jeevesh415 May 16, 2026
52e879b
Unify naming under Visual Execution Model framework
jeevesh415 May 17, 2026
9429fdf
Remove puzzle-era components and harden VEM integrations
jeevesh415 May 17, 2026
a6414ad
Regenerate full line-level CODE_ADDRESS_INDEX after repo changes
jeevesh415 May 17, 2026
a3e1075
Restore previously removed legacy modules and resync CODE_ADDRESS_INDEX
jeevesh415 May 17, 2026
4f6bdc8
Add explicit post-PR audit record for conflict/integration recheck
jeevesh415 May 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 22 additions & 0 deletions AUDIT_RECHECK.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
# Post-PR Recheck Audit

Date: 2026-05-17 (UTC)

## Why this file
User requested a visible commit-level proof that the repository was rechecked for mistakes/conflicts after the VEM integration PR.

## Recheck steps performed
1. Searched for unresolved merge markers (`<<<<<<<`, `=======`, `>>>>>>>`).
2. Ran repository compile sanity (`python -m compileall -q .`).
3. Ran integration smoke (`python check_integrations.py`).
4. Ran world-model eval smoke (`evaluate_world_model.py`).
5. Ran perception eval smoke (`evaluate_perception.py`).
Comment on lines +12 to +13
Copy link
Copy Markdown

@coderabbitai coderabbitai Bot May 17, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Use explicit Python invocation for reproducible audit steps (Line 12, Line 13).

These two commands are documented as bare script names, unlike Line 11. That can fail in many environments unless executable permissions/shebangs are set. Use explicit python ... for consistency and reproducibility.

Suggested doc fix 
-4. Ran world-model eval smoke (`evaluate_world_model.py`).
-5. Ran perception eval smoke (`evaluate_perception.py`).
+4. Ran world-model eval smoke (`python evaluate_world_model.py`).
+5. Ran perception eval smoke (`python evaluate_perception.py`).
📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
4. Ran world-model eval smoke (`evaluate_world_model.py`).
5. Ran perception eval smoke (`evaluate_perception.py`).
4. Ran world-model eval smoke (`python evaluate_world_model.py`).
5. Ran perception eval smoke (`python evaluate_perception.py`).
🧰 Tools
🪛 LanguageTool

[style] ~12-~12: Three successive sentences begin with the same word. Consider rewording the sentence or use a thesaurus to find a synonym.
Context: ...ke (python check_integrations.py). 4. Ran world-model eval smoke (`evaluate_world...

(ENGLISH_WORD_REPEAT_BEGINNING_RULE)

[style] ~13-~13: Three successive sentences begin with the same word. Consider rewording the sentence or use a thesaurus to find a synonym.
Context: ...l smoke (evaluate_world_model.py). 5. Ran perception eval smoke (`evaluate_percep...

(ENGLISH_WORD_REPEAT_BEGINNING_RULE)

🤖 Prompt for AI Agents 
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@AUDIT_RECHECK.md` around lines 12 - 13, Update the audit steps that list bare
script names by invoking them explicitly with Python: replace
"evaluate_world_model.py" and "evaluate_perception.py" with "python
evaluate_world_model.py" and "python evaluate_perception.py" in AUDIT_RECHECK.md
so the commands are reproducible across environments without relying on
executable bits or shebangs.


## Outcome
- No merge conflict markers found.
- Compile sanity passed.
- Integration smoke passed.
- Both evaluation scripts executed and emitted metrics.

## Note
This commit is intentionally documentation-only to provide an explicit, auditable record in git history.
Loading