This table row now says `agi.prompt.md` is "structured analysis" and "do not expose hidden chain-of-thought", but the actual `.github/prompts/agi.prompt.md` content doesn’t state that restriction and includes `enable_chain_of_thought=True`. Also, later in this same guide the example text still tells readers to use `agi.prompt` for chain-of-thought reasoning. Please align the guide with the prompt’s real behavior (or update the prompt).

[Bryan-Roe]

This table row now says agi.prompt.md is "structured analysis" and "do not expose hidden chain-of-thought", but the actual .github/prompts/agi.prompt.md content doesn’t state that restriction and includes enable_chain_of_thought=True. Also, later in this same guide the example text still tells readers to use agi.prompt for chain-of-thought reasoning. Please align the guide with the prompt’s real behavior (or update the prompt).

Originally posted by @Copilot in #128 (comment)