Loretta
3d377c542d
Added critical instructions to AGENTS.md mandating that `.github/copilot-instructions.md` must be read first in every session, with all session-start steps executed before any code or query actions. Documented a strict sequential execution override, prohibiting parallel doc/code reads, and mapped Copilot tool names to Codex shell commands. No functional changes to appsettings.json.
1.3 KiB
1.3 KiB
CRITICAL: Your FIRST action in every session MUST be reading .github/copilot-instructions.md. Execute ALL session-start instructions found there before responding to any user query. It is the single source of truth for this repo.
SEQUENTIAL EXECUTION OVERRIDE
The AI AGENT CORE PROTOCOL in copilot-instructions.md requires STRICT SEQUENTIAL execution. This OVERRIDES any default parallelization behavior. Do NOT parallelize doc reads with code searches. The sequence is:
- Read copilot-instructions.md → process its rules FULLY
- Read ALL docs/ .md files listed in the protocol → wait for completion
- Output [LOADED_DOCS: ...] prefix
- ONLY THEN respond to the user's query or search code
Tool mapping for AI AGENT CORE PROTOCOL
The copilot-instructions.md references Copilot tool names. Codex works through its shell + apply_patch, not named tools. Map them to Codex actions:
get_file/file_search→ shell:cat,sed -n,rg --filescode_search/get_symbols_by_name/find_symbol→ shell:rgreplace_string_in_file/edit_file→apply_patch(update)create_file→apply_patch(add file)
Follow the protocol using YOUR tools. The rules (LOADED_DOCS prefix, hard-gate, no-re-read, context recovery, explicit consent) apply equally to Codex.