feat: add code policy authoring scheme

[TomCC7]

Contribution path

• Small, safe change that does not need a tracking issue
• Linked issue or discussion: DIM-XXX / #XXX / URL

Problem

Solution

How to Test

AI assistance

Checklist

• I have read and approved the CLA.

[codecov]

Codecov Report

❌ Patch coverage is 93.70861% with 19 lines in your changes missing coverage. Please review.
✅ All tests successful. No failed tests found.

Files with missing lines	Patch %	Lines
dimos/agents/code_policy_core.py	81.81%	11 Missing and 3 partials ⚠️
dimos/benchmark/evaluation/runtime.py	93.58%	3 Missing and 2 partials ⚠️

@@                         Coverage Diff                         @@
##           cc/feat/agent-eval-standardized    #3410      +/-   ##
===================================================================
+ Coverage                            76.32%   76.36%   +0.04%     
===================================================================
  Files                                 1219     1219              
  Lines                               117410   117671     +261     
  Branches                             10788    10807      +19     
===================================================================
+ Hits                                 89613    89860     +247     
- Misses                               24699    24710      +11     
- Partials                              3098     3101       +3     

Flag	Coverage Δ
OS-ubuntu-24.04-arm	70.71% <93.70%> (+0.04%)	⬆️
OS-ubuntu-latest	72.50% <93.70%> (+0.05%)	⬆️
Py-3.10	72.49% <93.70%> (+0.04%)	⬆️
Py-3.11	72.50% <93.70%> (+0.05%)	⬆️
Py-3.12	72.50% <93.70%> (+0.06%)	⬆️
Py-3.13	72.49% <93.70%> (+0.05%)	⬆️
Py-3.14	72.49% <93.70%> (+0.04%)	⬆️
Py-3.14t	72.50% <93.70%> (+0.05%)	⬆️
SelfHosted-Large	29.70% <23.84%> (-0.02%)	⬇️
SelfHosted-Linux	35.90% <23.84%> (-0.04%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files with missing lines	Coverage Δ
dimos/agents/test_code_policy_core.py	100.00% <100.00%> (ø)
dimos/benchmark/evaluation/protocol.py	100.00% <100.00%> (ø)
dimos/benchmark/evaluation/test_runner.py	100.00% <100.00%> (ø)
dimos/benchmark/evaluation/test_runtime.py	100.00% <100.00%> (ø)
dimos/benchmark/short_horizon_qa/evaluation.py	90.32% <100.00%> (+0.32%)	⬆️
...imos/benchmark/short_horizon_qa/test_evaluation.py	100.00% <100.00%> (ø)
dimos/benchmark/evaluation/runtime.py	88.82% <93.58%> (+5.06%)	⬆️
dimos/agents/code_policy_core.py	80.30% <81.81%> (+1.95%)	⬆️

... and 6 files with indirect coverage changes

🚀 New features to boost your workflow:

• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.