Phase 1/2 Agent abstraction: multiple agents abstraction#46
Merged
Conversation
rcholic
changed the title
rcholic
changed the title
Phase 2/2: Conversational Agent
rcholic
pushed a commit
that referenced
this pull request
Jan 6, 2026
Phase 1/2 Agent abstraction: multiple agents abstraction
rcholic
pushed a commit
that referenced
this pull request
Jan 10, 2026
Phase 1/2 Agent abstraction: multiple agents abstraction
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Phase 1 is complete with:
Phase 1 Complete Summary
What Was Implemented:
LLM Provider Layer (sentience/llm_provider.py):
LLMProvider - Abstract base class
OpenAIProvider - GPT-4, GPT-4o, GPT-3.5
AnthropicProvider - Claude 3 Opus/Sonnet/Haiku
LocalLLMProvider - HuggingFace Transformers (Qwen, Llama, Gemma, Phi)
LLMResponse - Standardized response dataclass
SentienceAgent (sentience/agent.py):
Observe-Think-Act loop
Automatic context building from snapshots
Action parsing (CLICK, TYPE, PRESS, FINISH)
Token usage tracking
Execution history
Automatic retry logic
Tests (tests/test_agent.py):
16 unit tests for agent functionality
All tests passing
Mock LLM provider for isolated testing
Key Features:
95% code reduction: 348 lines → 15 lines for typical automation
Model agnostic: Swap LLMs without changing agent code
Token efficient: Only top 50 elements sent to LLM
Production ready: Retry logic, error handling, telemetry