plsql-intelligence: Instructions file for Codex

AGENTS.md — plsql-intelligence

Operating rules for agents working in this repository.

This is a greenfield Rust project now in active implementation. The working plan lives in plan.md; read it before doing anything substantive. If code and plan disagree, fix one or the other deliberately, never silently.

• Project key (for beads, agent mail, cass-memory): plsql-intelligence
• Repo name on disk: oracle/ (not the same as the project key)
• Language: Rust (Cargo workspace). No JS/TS/Python in this repo.
• Status: Pre-GA implementation. Foundational crates exist; higher layers are still in progress.
• Web access: allowed. Use WebFetch / WebSearch for OSS docs, Oracle reference material, crate research, etc.

Founder constraints (plan.md §3, non-negotiable)

• C1/C2: No ML training on private data; no private code through founder-owned inference infra.
• C5/C6 + private estate: Private PL/SQL test material lives in the directory named by the PLSQL_PRIVATE_ESTATE environment variable. Strictly local-only. Never publish, copy, or git add anything from that path into this repo or any other git repository. Treat it as pattern reference only; test cases mirroring its patterns are re-synthesized from grammar + description, never copied.
• C7 (operational, supersedes plan.md §3 literal text): Agents may commit and push via the git skills below. Never run destructive ops (git reset --hard, git clean -fd, git push --force, branch deletion, git stash drop, rm -rf on tracked paths) without explicit in-session approval.

If unsure whether an action would violate one of these, stop and ask.

Plan rules to internalize (plan.md §4)

• R10 / R11: Every CLI ships --robot-json and a doctor subcommand.
• R13: No uncertainty is silently dropped; every blind spot becomes a typed UnknownReason with provenance.
• R17: No telemetry by default.
• R20: Parser backend isolation is mandatory; no downstream crate depends on ANTLR-generated types.