bvandeusen
c569cdd0eb
Three defects, each of which independently made a hook a no-op, and all three failing silently — which is why the whole dynamic side of the plugin looked "shipped" while doing nothing. 1. Wrong env var case. Claude Code exports userConfig to hooks as CLAUDE_PLUGIN_OPTION_<KEY> with the key UPPERCASED. All four hooks read CLAUDE_PLUGIN_OPTION_api_endpoint / _api_token, so both values were always empty. That killed the SessionStart dynamic tier, process sync, prompt auto-inject, and the write-path prior-art trigger at once. 2. jq -rR is line-oriented. `@uri` under -R encodes input LINE BY LINE, so a multi-line payload came back as several encoded lines joined by raw newlines — an invalid URL, curl fails, hook exits 0 in silence. Now -sRr. This one hid behind (1): auto-inject only ever worked for single-line prompts, and prior-art (which posts code, always multi-line) could never have worked at all. 3. cut -c1-1200 caps each LINE, not the payload, so the prior-art code budget wasn't a budget. Now head -c 1200. Also widens the SessionStart warning: "neither URL nor token arrived" used to be treated as a benign unconfigured install and stayed quiet. That is exactly the state defect (1) produced, so the one install state that most needed a signal was the only one that emitted none. It now says so, and names the two other features it silently disables. Verified against the live instance: dynamic rules + project context load, auto-inject surfaces #2192 on a multi-line prompt, and the write-path trigger returns the [here] place-arm hit on a multi-line edit with session dedup suppressing the repeat. Refs #2198, #2082 Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01UaYUaouG9jjhATyuxCKrQs
85 lines
3.7 KiB
Bash
Executable File
85 lines
3.7 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Scribe plugin — sync stored Processes into auto-surfacing local skills.
|
|
#
|
|
# Fetches `GET /api/plugin/processes` and writes one
|
|
# ~/.claude/skills/scribe-proc-<slug>/SKILL.md
|
|
# per Process. The stub's frontmatter `description` is the auto-surface trigger;
|
|
# its body tells Claude to call get_process(<name>) and follow the LIVE procedure
|
|
# from Scribe (the DB stays the single source of truth — the stub is a pointer).
|
|
#
|
|
# WHY LOCAL ~/.claude/skills (not the plugin dir): the plugin is git-cloned and
|
|
# identical on every install, so instance-specific stubs can't live inside it.
|
|
# Personal skills in ~/.claude/skills are live-detected by Claude Code within the
|
|
# session, so a freshly written stub auto-surfaces without a restart.
|
|
#
|
|
# TRIGGERS: this runs at SessionStart (alongside the context hook) so stubs stay
|
|
# fresh each session, and on demand via the `/scribe:sync` command.
|
|
#
|
|
# FAIL-OPEN & SILENT: never blocks a session; emits NOTHING on stdout (so it's
|
|
# safe as a second SessionStart hook). On any fetch failure it exits without
|
|
# touching existing stubs — a transient outage must not wipe the user's skills.
|
|
# Config mirrors the context hook: CLAUDE_PLUGIN_OPTION_API_ENDPOINT /
|
|
# CLAUDE_PLUGIN_OPTION_API_TOKEN (userConfig key UPPERCASED by Claude Code — see
|
|
# #2198), with SCRIBE_URL / SCRIBE_TOKEN as the override.
|
|
set -uo pipefail
|
|
|
|
command -v jq >/dev/null 2>&1 || exit 0
|
|
command -v curl >/dev/null 2>&1 || exit 0
|
|
|
|
url=${SCRIBE_URL:-${CLAUDE_PLUGIN_OPTION_API_ENDPOINT:-}}
|
|
token=${SCRIBE_TOKEN:-${CLAUDE_PLUGIN_OPTION_API_TOKEN:-}}
|
|
# Guard against an unexpanded `${...}` placeholder arriving as a literal.
|
|
case "$url" in *'${'*) url="" ;; esac
|
|
case "$token" in *'${'*) token="" ;; esac
|
|
[ -n "$url" ] && [ -n "$token" ] || exit 0
|
|
|
|
body=$(curl -fsS --max-time 8 \
|
|
-H "Authorization: Bearer ${token}" \
|
|
"${url%/}/api/plugin/processes" 2>/dev/null) || exit 0
|
|
[ -n "$body" ] || exit 0
|
|
|
|
count=$(printf '%s' "$body" | jq -r '.processes | length' 2>/dev/null) || exit 0
|
|
[ -n "$count" ] && [ "$count" != "null" ] || exit 0
|
|
|
|
skills_dir="${HOME}/.claude/skills"
|
|
mkdir -p "$skills_dir" 2>/dev/null || exit 0
|
|
|
|
# Slugs written this run — anything else under scribe-proc-* is pruned below.
|
|
managed=" "
|
|
|
|
i=0
|
|
while [ "$i" -lt "$count" ]; do
|
|
name=$(printf '%s' "$body" | jq -r ".processes[$i].name // empty" 2>/dev/null)
|
|
slug=$(printf '%s' "$body" | jq -r ".processes[$i].slug // empty" 2>/dev/null)
|
|
desc=$(printf '%s' "$body" | jq -r ".processes[$i].description // empty" 2>/dev/null)
|
|
i=$((i + 1))
|
|
[ -n "$slug" ] && [ -n "$name" ] || continue
|
|
|
|
dir="${skills_dir}/scribe-proc-${slug}"
|
|
mkdir -p "$dir" 2>/dev/null || continue
|
|
# description folded to one line — YAML scalar must not contain a newline.
|
|
desc=$(printf '%s' "$desc" | tr '\n' ' ')
|
|
{
|
|
printf -- '---\n'
|
|
printf 'name: scribe-proc-%s\n' "$slug"
|
|
printf 'description: %s\n' "$desc"
|
|
printf -- '---\n\n'
|
|
printf '<!-- GENERATED by the Scribe plugin (scribe_sync_processes.sh). Do not edit here; edit the Process in Scribe and re-sync with /scribe:sync. -->\n\n'
|
|
printf 'This is a saved **Scribe Process**: `%s`.\n\n' "$name"
|
|
printf 'Do not improvise it. Call `get_process("%s")` via the Scribe MCP server to fetch the live procedure, then follow the returned body verbatim — including any "clarify first" steps it contains.\n' "$name"
|
|
} > "${dir}/SKILL.md" 2>/dev/null || continue
|
|
managed="${managed}${slug} "
|
|
done
|
|
|
|
# Prune stubs whose Process no longer exists (scoped to our scribe-proc-* prefix).
|
|
for d in "${skills_dir}"/scribe-proc-*; do
|
|
[ -d "$d" ] || continue
|
|
slug=$(basename "$d"); slug=${slug#scribe-proc-}
|
|
case "$managed" in
|
|
*" $slug "*) : ;;
|
|
*) rm -rf "$d" 2>/dev/null ;;
|
|
esac
|
|
done
|
|
|
|
exit 0
|