Oracle bundles your prompt + selected files into one “one-shot” request so another model can answer with real repo context (API or browser automation). Treat output as advisory: verify against code + tests.
Default workflow here: --engine browser with GPT‑5.2 Pro in ChatGPT. This is the common “long think” path: ~10 minutes to ~1 hour is normal; expect a stored session you can reattach to.
Recommended defaults:
--engine browser)--model gpt-5.2-pro or --model "5.2 Pro")--dry-run + --files-report).oracle --helpnpx -y @steipete/oracle --help (avoid pnpx here; sqlite bindings).oracle --dry-run summary -p "" --file "src/" --file "!/.test." oracle --dry-run full -p "" --file "src/**" oracle --dry-run summary --files-report -p "" --file "src/**" oracle --engine browser --model gpt-5.2-pro -p "" --file "src/**" oracle --render --copy -p "" --file "src/**" --copy is a hidden alias for --copy-markdown.--file)--file accepts files, directories, and globs. You can pass it multiple times; entries can be comma-separated.
--file "src/**"--file src/index.ts--file docs --file README.md--file "src/" --file "!src//.test.ts" --file "!/.snap"node_modules, dist, coverage, .git, .turbo, .next, build, tmp (skipped unless explicitly passed as literal dirs/files)..gitignore when expanding globs.--file ".github/**").api when OPENAI_API_KEY is set; otherwise browser.--engine api for Claude/Grok/Codex or multi-model runs.--browser-attachments auto|never|always (auto pastes inline up to ~60k chars then uploads).oracle serve --host 0.0.0.0 --port 9473 --token oracle --engine browser --remote-host --remote-token -p "" --file "src/**" ~/.oracle/sessions (override with ORACLE_HOME_DIR).oracle status --hours 72oracle session --render --slug "<3-5 words>" to keep session IDs readable.--force only when you truly want a fresh run.Oracle starts with zero project knowledge. Assume the model cannot infer your stack, build tooling, conventions, or “obvious” paths. Include:
.env, key files, auth tokens). Redact aggressively; share only what’s required.For long investigations, write a standalone prompt + file set so you can rerun days later:
Oracle runs are one-shot; the model doesn’t remember prior runs. “Restoring context” means re-running with the same prompt + --file … set (or reattaching a still-running stored session).
共 1 个版本