daniel.w
/
LazyBoy2
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
LazyBoy2/README.md

5.3 KiB
Raw Blame History

GrokBoy

Minimal local GrokBot-like CLI agent. Phase P6: scenario playbooks + confirm-before-post. P7 UX: natural chat, max-round summary, blocked recovery. P8: auto-continue chunks like Grok Bot (progress beats, total ceiling).

Status

Phase Status
P0 streaming chat done
P1 shell / files + ReAct done
P2 completion / loop guard / truncation done
P3 browser (Playwright DOM) done (optional)
P4 human handoff done
P5 interactive agent REPL done
P6 scenario playbooks + confirm done
P7 agent UX polish done (slice)
P8 auto-continue chunks done

No Docker desktop, no Codex/LazyBoy fork. Product notes: docs/PRODUCT.md.

Setup (macOS)

export GROKBOY_API_KEY=your_key   # or XAI_API_KEY
# optional:
# export GROKBOY_BASE_URL=https://api.x.ai/v1
# export GROKBOY_MODEL=grok-4.6
# export GROKBOY_CONTEXT_CHARS=100000
# export GROKBOY_MAX_ROUNDS=12          # rounds per chunk
# export GROKBOY_MAX_ROUNDS_TOTAL=48    # absolute ceiling across auto-continues
# export GROKBOY_PROGRESS=0             # silence 〔續跑〕 progress beats
# export GROKBOY_BROWSER_HEADED=1       # visible Chromium (recommended for handoff / agent)

cd ~/GrokBoy
cargo run -p grokboy -- chat

Optional: Playwright browser tools

Browser tools are always registered but fail closed until you install the helper:

cd ~/GrokBoy/tools/playwright
npm install
npx playwright install chromium

Then the agent can use browser_navigate, browser_snapshot, browser_click, browser_type, browser_eval, and browser_handoff (DOM/selector/role — not screenshot-first).

Human handoff (P4)

When the agent hits a login / OTP / captcha wall it calls browser_handoff:

  1. Chromium opens headed (visible) — or relaunches headed if it was headless.
  2. Terminal prints why it paused (ZH-TW + English) and what to do.
  3. You complete the wall in the browser, then press Enter in that terminal (or type abort).
  4. Agent resumes with a fresh DOM snapshot.
# Prefer headed for runs that may need handoff:
export GROKBOY_BROWSER_HEADED=1
cargo run -p grokboy -- run "打開需要登入的頁面並完成任務"
# or interactive:
cargo run -p grokboy -- agent

Tests / CI: GROKBOY_HANDOFF_AUTO=1 auto-resumes (no interactive Enter).

Scenario playbooks (P6)

Reusable acceptance pattern: Phase A research+draft (no publish) → auth browser_handoff + request_user_confirm → Phase B publish only after approve.

export GROKBOY_BROWSER_HEADED=1
cargo run -p grokboy -- agent
# paste prompts/examples/shopee-threads-phase-a.txt  (or your filled template)
# review draft → paste phase-b or say「核准，請發佈…」

Tests: GROKBOY_CONFIRM_AUTO=1 auto-approves; abort denies.

Commands

  • grokboy chat — interactive streaming chat (no tools)
  • grokboy run "<prompt>" — one-shot agent with tools
  • grokboy run --session <id> "<prompt>" — continue a saved session (one shot)
  • grokboy agent — interactive multi-turn agent REPL with tools (auto session)
  • grokboy agent --session <id> — resume an agent session
  • grokboy smoke — offline checks (no API key / no interactive handoff)
  • grokboy help

In agent REPL: /exit or /quit leave; /session show id; empty line ignored.

Tools: shell, list_dir, read_file, write_file, report_done, report_blocked, browser_navigate, browser_snapshot, browser_click, browser_type, browser_eval, browser_handoff, request_user_confirm.

Sessions are stored under ~/.grokboy/sessions/<id>.json (may include last_browser_url).

The agent stops on report_done / report_blocked, blocks identical tool rounds (×3), and truncates old context when over budget. Long tasks auto-continue across chunks (GROKBOY_MAX_ROUNDS per beat, up to GROKBOY_MAX_ROUNDS_TOTAL) with 〔續跑〕 progress on stderr — like Grok Bot — instead of hard-stopping for a user re-prompt after every chunk.

Traditional Chinese

本機終端機 coding assistant。P6 支援可推廣的情境劇本（Phase A 草稿 → confirm → Phase B 發佈）與 request_user_confirm。P5 grokboy agent；P4 browser_handoff（登入牆）。範例：蝦皮→Threads，見 docs/scenarios/。

export GROKBOY_API_KEY=你的金鑰
export GROKBOY_BROWSER_HEADED=1
cd ~/GrokBoy
cargo run -p grokboy -- smoke
# 可選瀏覽器：
cd tools/playwright && npm install && npx playwright install chromium
cargo run -p grokboy -- agent
cargo run -p grokboy -- run "打開 example.com 並 snapshot"
cargo run -p grokboy -- chat

Layout

crates/grokboy-core/   # config, model, tools, browser, agent, session
crates/grokboy/        # CLI binary
tools/playwright/      # optional Node Playwright helper (JSONL)
docs/PRODUCT.md
docs/ACCEPTANCE.md
docs/scenarios/          # playbook pattern + examples
prompts/templates/       # Phase A/B placeholders
prompts/examples/        # filled example prompts