T

meeks ee01487ce3 refactor: externalize coding agent system prompt to prompts/coding_agent.txt

- Moved 221-line system prompt from core/coding_prompt.py to prompts/coding_agent.txt
- core/coding_prompt.py now loads prompt from external file using pathlib
- Maintains backward compatibility with existing CODING_AGENT_SYSTEM_PROMPT export
- Enables separate version control and A/B testing of prompts

2026-08-01 20:01:46 +02:00

core

refactor: externalize coding agent system prompt to prompts/coding_agent.txt

2026-08-01 20:01:46 +02:00

gitea

Update default model ID to qwen3.6-35b-a3b-mtp@iq4_nl

2026-08-01 19:58:00 +02:00

prompts

refactor: externalize coding agent system prompt to prompts/coding_agent.txt

2026-08-01 20:01:46 +02:00

tests

refactor: replace Any types with specific types and update bad_code.md

2026-07-19 15:35:17 +02:00

.gitignore

refactor: replace Any types with specific types and update bad_code.md

2026-07-19 15:35:17 +02:00

AGENTS.md

Update default model ID to qwen3.6-35b-a3b-mtp@iq4_nl

2026-08-01 19:58:00 +02:00

bad_code.md

refactor: replace Any types with specific types and update bad_code.md

2026-07-19 15:35:17 +02:00

LICENSE

Initial commit

2026-07-02 19:03:58 +02:00

main.py

fix: FileTools uses local workspace before API for file content (#6.2)

2026-07-19 12:05:28 +02:00

pyproject.toml

Refactor code structure for improved readability and maintainability

2026-07-06 21:37:20 +02:00

README.md

Refactor code structure for improved readability and maintainability

2026-07-06 21:37:20 +02:00

uv.lock

Refactor code structure for improved readability and maintainability

2026-07-06 21:37:20 +02:00

VERIFICATION.md

Refactor code structure for improved readability and maintainability

2026-07-06 21:37:20 +02:00

README.md

Agent Instructions

Prefer using dataclasses when using data structures or similar objects to represent complex data.
Follow all instructions provided in the system prompt.
Keep responses concise and direct.
Minimize output tokens.
Use the Task tool for complex multi-step tasks.
Verify solutions with tests if possible.
Run lint and typecheck commands if provided.
Do not commit changes unless explicitly asked.
Use GitHub-flavored markdown for formatting.
Answer concisely with fewer than 4 lines of text.
ALWAYS use uv to run python commands. Do not use python3 directly.
Always commit and push changes at the end of a task.
NEVER push to the master or main branch.

Running the Agent

# Activate the virtual environment
uv sync

# Run the agent
uv run src/main.py

Resolved Issues

#2: Test issue for agent - Resolved by agent.