Simple Baselines (CoT, Vanilla, Retries, Warming), Renaming Agent Classes, Adding Prompting component & core module

[alckasoc]

🤔 Reasoning

1 - Zero-shot/Standard prompt (generate n-samples)
2 - Chain-of-Thought (generate n-samples)
3 - Retries (up to 5)
4 - Warming (gradually increase temperature from 0 to 0.5)

Generate N-samples
Generate N-samples with Retries/Warming/Rejection Sampling
Escalation (cheap to expensive models)
Chain-of-Thought Self-Consistency
Rejection Sampling

-> agential.cog.baselines.cot X
-> agential.cog.cot
-> nothing, you just write it yourself X

Retries -> Zero-shot or CoT?
Warming -> Zero-shot or CoT?
Retries Warming
Zero-shot/Standard X X
Chain-of-Thought

🚧 Changes

Describe the changes made...

✅ PR Checklist

• Using this PR template?
• Linked issue?
• Added feature?
  • Added/updated docs?
  • Added/updated tests?

[codecov]

Codecov Report

Attention: Patch coverage is 98.00333% with 12 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
agential/core/base/prompting/prompting.py	82.60%	4 Missing ⚠️
agential/agents/expel/agent.py	86.66%	2 Missing ⚠️
agential/agents/lats/agent.py	84.61%	2 Missing ⚠️
agential/core/base/prompting/strategies.py	84.61%	2 Missing ⚠️
agential/prompting/cot/prompting.py	97.95%	1 Missing ⚠️
agential/prompting/standard/prompting.py	97.95%	1 Missing ⚠️

Files with missing lines	Coverage Δ
agential/agents/critic/agent.py	100.00% <100.00%> (ø)
agential/agents/critic/functional.py	100.00% <100.00%> (ø)
agential/agents/critic/output.py	100.00% <100.00%> (ø)
agential/agents/critic/prompts.py	100.00% <ø> (ø)
agential/agents/critic/strategies/code.py	100.00% <100.00%> (ø)
agential/agents/critic/strategies/general.py	92.10% <100.00%> (ø)
agential/agents/critic/strategies/math.py	100.00% <100.00%> (ø)
agential/agents/critic/strategies/qa.py	98.80% <100.00%> (ø)
agential/agents/expel/functional.py	98.49% <100.00%> (ø)
agential/agents/expel/memory.py	99.30% <100.00%> (ø)
... and 76 more