mirror of
https://github.com/hanzoai/bot.git
synced 2026-10-30 17:24:26 +00:00
zeekay
acaeda400a
Three coordinated things:
1. Resolve the committed upstream/main merge conflicts. 94 files were
sitting with raw <<<<<<< HEAD ... >>>>>>> upstream/main blocks. Every
conflict had HanzoBot/Bot on HEAD and OpenClaw on upstream. Resolved
by keeping HEAD everywhere — 540 conflict blocks.
2. Rewrite remaining OpenClaw text refs.
OPENCLAW → HANZO_BOT
OpenClaw → HanzoBot (PascalCase type identifiers)
openclaw → bot (codebase convention — botToken,
botUsername etc.; avoids invalid
hyphenated JS identifiers)
openclaw[_]/openclaw[A-Z] → bot[_]/bot[A-Z] (compound)
ai.openclaw.x → ai.hanzo.bot.x (JVM package path)
3. Delete or rename openclaw-named file paths (116 of them). Dead
duplicates with a Bot-named canonical from the partial migration:
deleted. Otherwise renamed.
ai/openclaw/** → deleted (ai/hanzo/bot/** canonical)
Sources/OpenClaw*/ → deleted (Sources/Bot* canonical)
Tests/OpenClawIPCTests/ → deleted (Tests/BotIPCTests canonical)
OpenClawKit/ → deleted (BotKit canonical)
openclaw-tools.*.ts → deleted (bot-tools.*.ts canonical)
openclaw-root.ts etc. → deleted (bot-root.ts canonical)
types.openclaw.ts → deleted (types.bot.ts canonical)
extensions/*/openclaw.plugin.json → renamed hanzo-bot.plugin.json
docs/start/openclaw.md → renamed hanzo-bot.md (+ zh-CN)
docs/assets/openclaw-*.png, whatsapp-openclaw*.jpg → deleted
scripts/.../openclaw-* → deleted (bot/hanzo-bot parallels)
openclaw.mjs → deleted (hanzo-bot.mjs is package.bin)
Then patched 65 broken JS/TS import strings where hanzo-bot had ended
up inside an import path ('./types.hanzo-bot.js' → './types.bot.js'
etc., since the on-disk filename uses the brand-neutral bot- prefix).
Pre-existing lint debt cleaned up to get oxlint --type-aware to 0/0:
removed the dead i18n test that referenced a path no longer existing;
defined the missing DIDConfig and WalletConfig types in types.base.ts
(they were imported but never declared); dropped unused imports;
collapsed redundant type assertion and a tautological meta.bot lookup
that the openclaw→bot rename made redundant.
The a2ui.bundle.js generated artifact is kept at its pre-rebrand
contents — it gets regenerated by 'pnpm canvas:a2ui:bundle' from
sources I cannot rebuild in this commit; the source side is clean.
Verified: 0 occurrences of openclaw (case-insensitive) in tree source
content, 0 file or directory paths with openclaw in the name; oxlint
--type-aware src test reports 0/0.
@hanzo/bot-recipes-brain
YAML ingest recipes for the Hanzo Brain. Daily-life automations — email today, calendar / Slack / X / Notion next.
A recipe defines: auth + cron + ingest + classify + draft + enqueue + on_swipe hooks. The bot runs it on a schedule, drops drafts into a queue, the Hanzo app shows the swipe UI. Every swipe is a training signal.
Flagship: email
hanzo-bot brain run-recipe email
hanzo-bot brain drafts list
hanzo-bot brain drafts approve <id> # sends via gmail
hanzo-bot brain drafts reject <id> # logs as decline-fact for training
See recipes/email.yaml for the spec. Auth is OIDC via hanzo.id (single sign-on across all Hanzo services). Cron defaults to every 30 minutes — adjust per inbox volume.
How a recipe runs
cron fires
→ ingest fetch new items from backend (gmail, calendar, …)
→ classify cheap model tags each item (needs_reply, priority, …)
→ draft main model writes a response using brain context:
• brain.recall(from_email) — facts about sender
• brain.search(thread_id) — prior thread
• brain.facts({entity, since:30d}) — recent activity
• brain.style(sender:me, recent:200) — your tone
→ enqueue drop into drafts.email queue (TTL 7d)
→ notify push to the Hanzo iOS / Android / macOS app
Swipe → train loop
Every swipe in the app feeds back into the brain:
- swipe right (send) → send via gmail, upsert fact
{subject:from_email, predicate:"replied"}, add(received, sent)pair to style examples - swipe left (reject) → delete draft, upsert fact
{predicate:"declined_reply"}, down-weight similar drafts - swipe up (snooze 24h) → reschedule
- tap edit → send → upsert fact
{predicate:"replied"}, add the edited version to style examples (highest-quality training pair)
After ~200 swipes, the draft quality compounds — the brain learns your tone from your own actions, not from a tone-tuning UI.
Adding a new recipe
Drop a <name>.yaml into recipes/. The loader walks the directory; the scheduler registers anything with a cron: field.
Minimal shape:
recipe: notion
version: 1
backend: notion
auth:
provider: hanzo.id
cron: "0 */2 * * *"
ingest:
source: workspace-pages
since: 12h
classify:
model: zen-2-haiku
schema: { needs_reply: bool, priority: one_of [P0,P1,P2,P3] }
draft:
when: needs_reply == true
model: zen-2
context:
- brain.recall(page_id)
- brain.search(title)
enqueue:
queue: drafts.notion
ttl: 7d
API
import { listRecipes, loadRecipe } from "@hanzo/bot-recipes-brain";
await listRecipes(); // ["email", "notion", …]
const recipe = await loadRecipe("email");
Plugin contract
import register from "@hanzo/bot-recipes-brain";
const { recipes } = await register(api, ["email", "notion"]);
// → registers each recipe as a cron job in the bot scheduler
YAML driver
Bot already depends on the yaml package (eemeli/yaml v2). No new deps.