beardrive/plugin/commands/init.md at c88b8179f3eb44b766b72823e6076a7c380e4fb5

mirror of https://github.com/runbear-io/beardrive.git synced 2026-08-25 08:08:08 +02:00

Files

T

Snow LeeandClaude Fable 5 476113ebdc fix(hooks): read heat captures grep matches and shell-command reads, not just Read

Field report: an agent session read a dozen-plus files via Bash
(grep/cat/tail/find) and Grep, but read heat showed almost nothing —
the read-log hook only matched the native Read tool.

- matchers broadened per platform: claude Read|Grep|Bash, codex
  read_file|shell, gemini +search_file_content|run_shell_command,
  hermes read_file|grep|bash; plugin hooks.json matches Read|Grep|Bash
- read-log is now tool-aware: shell events mine the command line for
  existing files it names (redirect targets and flags excluded), grep
  events mine the response for the files the matches came from
  (content lines and filename lists), and listing tools (Glob, ls) are
  deliberately ignored — seeing a file's name is not reading it
- hooks install upgrades a registered hook's stale matcher in place, so
  re-running it after a binary upgrade rolls coverage out to existing
  projects instead of being skipped by the idempotency marker
- docs: SKILL.md platform table + read-heat wording, install/init
  commands, README command table

Note from the same report, verified not a bug: read-log resolves the
mount via the folder's own .bdrive/config.json (config.ResolveMount),
so a stale duplicate registry entry cannot swallow reads.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P5cxPQdSGJnjXCYY9GeWXt

2026-07-13 15:05:05 -07:00

4.4 KiB

Raw Blame History

description, argument-hint

description	argument-hint
Start syncing a project in this folder — create a new BearDrive project or connect an existing one, whole folder or a shared subfolder, and start the sync daemon	[folder] [--name <project> \| --project <p-id>] [--shared <dir>]

Start syncing a project with BearDrive. Arguments: $ARGUMENTS (optional folder, optional --name/--project/--shared).

Follow these steps:

Check the bdrive CLI is installed: run command -v bdrive. If missing, offer to install it (brew install runbear-io/tap/beardrive, or go install github.com/runbear-io/beardrive/cmd/bdrive@latest) and wait for the user's choice before installing.
Sign in if needed: run bdrive login --status. With no server or a stale token, run bdrive login (tell the user a browser window is coming; it completes by itself). Default server is beardrive.ai; pass a self-hosted URL if the user mentioned one.
Detect knowledge tooling (skip if the folder already contains .bdrive/ — then just run bdrive init --yes; it resumes syncing, including after a rename/move). Check, in order — first match wins, ask if two match (full playbook: the beardrive skill's "Connecting knowledge tooling" section):
- gbrain (gbrain.yml, or a gbrain MCP server / brain-first CLAUDE.md block) → offer to sync the brain's shared subfolder as its own project; never a brain root, and one enrichment owner per shared folder (everyone else indexes read-only — see the skill).
- OKF wiki (markdown with OKF frontmatter) → offer: connect the wiki dir via --shared, or keep it PR-gated and create a new shared folder.
- Wiki-ish folder (docs/wiki/notes full of markdown) → check git log -- <dir>; dormant → recommend connecting it, active PR traffic → recommend a new shared folder. Offer an OKF upgrade (openknowledge from) after connecting, as a separate consent.
- Nothing / empty → offer a starting point in this order: OKF (recommended), gbrain, blank, describe-it.
Initialize — two hard rules:
- Never sync a repo root: inside a repo, knowledge syncs as a scoped subfolder via --shared. A dedicated knowledge folder (empty dir, standalone vault) may be the mount itself.
- One transport per folder: a git-tracked dir must leave git tracking before it syncs (git rm -r --cached <dir> + gitignore; stage it, let the user commit). Offer one-way git snapshots if they want a git record; bdrive log -p <path> covers history for most.
```
bdrive init --name <project> --yes            # dedicated knowledge folder
bdrive init --name <project> --shared wiki    # in a repo: only ./wiki syncs
```
Register agent sync hooks: run bdrive hooks install <folder>. It detects the agent platforms in use (Claude Code, Codex, Gemini CLI, Hermes — by their config dirs in the project or home) and idempotently merges beardrive's sync hooks into each platform's own hook config, so files pull at every turn start, push after edits, every change is stamped with the agent session that made it, and agent file reads — native reads, grep matches, and files named in shell commands — feed the hub's read heatmap (queued locally by bdrive read-log, reported on the next sync). Tell the user which platforms got hooks; if Codex is among them, mention they must run /hooks inside Codex once to trust the project's .codex layer.
Verify: run bdrive status <folder> and confirm the daemon is running and pending is 0. Summarize: project name/id, what syncs, and that edits propagate to every team member within seconds. Offer the two-file agent orientation, each part as its own consent (full flow: the skill's "Teaching agents the folder" section): a synced <shared>/AGENTS.md mapping the folder — draft it if this user is creating the project, read and follow it if joining — and, for --shared mounts inside a repo, a short pointer to it in the repo root's AGENTS.md/CLAUDE.md (the only file Codex loads, and what makes any agent aware the folder matters). Then tell the user how teammates connect (invite link → bdrive init → same --shared scope, which is per-device).

For the full team setup (the AGENTS.md orientation + per-project sync hooks in .claude/settings.json), suggest /beardrive:install instead.

4.4 KiB Raw Blame History

4.4 KiB

Raw Blame History