bvandeusenandClaude Opus 5
a49e7ed2af
CI & Build / Python lint (push) Successful in 2s
CI & Build / Plugin hooks (push) Successful in 9s
CI & Build / integration (push) Successful in 49s
CI & Build / TypeScript typecheck (push) Successful in 57s
CI & Build / Python tests (push) Failing after 1m7s
CI & Build / Build & push image (push) Skipped
Every hook opened `command -v jq >/dev/null 2>&1 || exit 0`, so on a machine without jq the operator got no session context, no rules, no prior art and no process sync — and not one word saying why, because `exit 0` is indistinguishable from "ran fine, nothing to say". jq is absent by default on macOS, on the Debian/Ubuntu slim images, on Alpine and in most CI containers. That is not a prerequisite to document; it is the plugin handing its own packaging problem to whoever installs it. `tac` was worse: GNU-only, so the prior-art hook's enclosing-definition arm did nothing at all on every Mac, silently, from the day it shipped. It is not replaced but removed — scribe_defs judges each line independently, so extracting forward and taking `tail -1` is the same answer as reversing and taking the head, and it drops the early-exit `head` that #4042 was filed for. No server contract changed, so a lagging plugin cache keeps working. scribe_json.awk JSON -> IDX<TAB>PATH<TAB>VALUE. Two modes: `whole` for an event or a response body, `lines` for a transcript, where an unparseable record is dropped and the rest still read — the `map(try fromjson catch empty)` the jq program opened with. Arrays also report their LENGTH at `[#]`, which is what keeps "zero notes" distinct from "no answer" (#2932). scribe_turn.awk the turn-bounding program, replacing the thirty lines of jq in the Stop hook. scribe_defs.sh scribe_json_flat / _pick / _list / _len / _list_minus read, scribe_json_out writes the envelope (five copies of one shape, gone), scribe_urlenc replaces `jq -sRr '@uri'`. Percent-encoding goes through `od -tu1` rather than an awk character loop on purpose: awk's idea of a character follows the locale, so gawk reads an accented letter as one and mawk as two, and an encoder built on substr() would emit a different URL depending on which awk is installed. Encoding is defined on bytes. Verified byte-identical to `jq -sRr '@uri'`. Measured, not assumed. The per-event path costs 8ms against jq's 3ms. The transcript path was 70x slower until two fixes: the Stop hook now finds where the turn starts with a fixed-string grep before parsing (a needle carrying unescaped quotes cannot occur inside a JSON string, so it matches only at a record's top level — checked against a full JSON parse of a 27MB transcript: 152 prompt records, 152 matches, no misses, no extras), and the parser reads each token out of a 1024-byte window instead of copying the rest of the buffer per token, which was quadratic in line length on the 400KB tool results a transcript carries. Differential-tested against the jq program it replaces over 724 windows cut from three real transcripts — 724 identical, 0 mismatched, 45 of them exercising a real task close and a real reply. That sweep is what caught `scribe_turn.awk` never setting FS, which truncated every multi-word reply at its first space and was invisible to a test whose replies were all empty. check_plugin.py's `jq -R` lint becomes a guard against either binary coming back, and three smoke checks lose their `shutil.which("jq")` skip. jq is not in `ci-python` either, so those three announced a skip on every CI run and had never once run there: removing the dependency from the product also closed a permanent hole in its verification. They pass now across all ten hooks. tests/test_hook_json_reader.py is a differential against Python's `json` over nested objects, arrays, unicode, escapes, control characters, empty cases and a value longer than the token window, plus the envelope, the encoder and the turn analyzer. 139 cases. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy
86 lines
3.6 KiB
Bash
Executable File
86 lines
3.6 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
|
|
|
|
# shellcheck source=plugin/hooks/scribe_defs.sh
|
|
. "$(dirname "${BASH_SOURCE[0]}")/scribe_defs.sh"
|
|
|
|
command -v curl >/dev/null 2>&1 || exit 0
|
|
|
|
scribe_config || exit 0
|
|
|
|
body=$(curl -fsS --max-time 8 \
|
|
-H "Authorization: Bearer ${token}" \
|
|
"${url%/}/api/plugin/processes" 2>/dev/null) || exit 0
|
|
[ -n "$body" ] || exit 0
|
|
|
|
body_flat=$(printf '%s' "$body" | scribe_json_flat)
|
|
# The array's LENGTH, which is "" when `.processes` is not an array at all —
|
|
# a different answer from 0, and the one that means the response was not what
|
|
# this hook expects.
|
|
count=$(scribe_json_len "$body_flat" '.processes')
|
|
case "$count" in ''|*[!0-9]*) exit 0 ;; esac
|
|
|
|
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=$(scribe_json_pick "$body_flat" ".processes[$i].name")
|
|
slug=$(scribe_json_pick "$body_flat" ".processes[$i].slug")
|
|
desc=$(scribe_json_pick "$body_flat" ".processes[$i].description")
|
|
i=$((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
|