Files
FabledGrimoire/plugin/hooks/scribe_tool_rules.sh
T
bvandeusenandClaude Opus 5.5 e99f1169f7
CI & Build / Python lint (push) Successful in 3s
CI & Build / Plugin hooks (push) Successful in 12s
CI & Build / TypeScript typecheck (push) Successful in 52s
CI & Build / integration (push) Successful in 1m1s
CI & Build / Python tests (push) Successful in 1m55s
CI & Build / Build & push image (push) Successful in 36s
rename(547): what people read says Grimoire
Step 1 of the Scribe -> Grimoire rename: every capitalised "Scribe" in prose
becomes "Grimoire" ("Fabled Scribe" -> "Fabled Grimoire") across the UI,
the PWA manifest and page title, the MCP instructions and tool docstrings,
hook and skill text, docs and README, with the tests that assert on that
prose moving with it. Old migrations keep their wording.

Identifiers are untouched here: the package, plugin name, MCP server key,
hook file names, env vars, the .scribe marker and FabledScribe repo/image
names move in steps 2 and 3, along with prose that quotes them.

The sweep matched "Scribe" only as a whole word, so describe/subscribe and
friends are untouched. The longer name took the MCP instructions one
character over their 1,600 budget; two phrases are shortened to fit.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-22 10:46:37 -04:00

165 lines
7.9 KiB
Bash

#!/usr/bin/env bash
# Grimoire — PreToolUse rule arm for ACTIONS.
#
# The sibling of scribe_prior_art.sh. That hook is registered on Write|Edit and
# asks "what is recorded about the file being written". This one asks "does a
# standing rule speak to the command about to be run" — which is how a rule
# about which tool to reach for arrives at all.
#
# WHY A HOOK AND NOT AN INSTRUCTION. A reflex generates no query:
# you reach for `curl` confidently, with no moment of doubt, so a surface that
# waits to be asked never fires. Here nothing is asked — the tool call IS the
# query, and the reflex has to become a tool call before it can do anything.
#
# SILENT ON OUTAGE, deliberately, unlike the prior-art hook. A write is
# occasional; a Bash call is not, and an "instance did not answer" line before
# every command is the noise that gets a channel muted. scribe_prior_art.sh
# still speaks for both when the instance is down.
#
# Env:
# SCRIBE_URL / SCRIBE_TOKEN override for the settings.json dogfooding path.
command -v curl >/dev/null 2>&1 || exit 0
# Sourced FIRST, because the JSON reader below lives there. It defines
# functions and clears `url`/`token`; nothing here runs before it is needed.
# shellcheck source=plugin/hooks/scribe_defs.sh
. "$(dirname "${BASH_SOURCE[0]}")/scribe_defs.sh"
# PreToolUse delivers { session_id, cwd, tool_name, tool_input: {...}, ... }
event=$(cat 2>/dev/null || true)
event_flat=$(printf '%s' "$event" | scribe_json_flat)
tool_name=$(scribe_json_pick "$event_flat" '.tool_name')
session_id=$(scribe_json_pick "$event_flat" '.session_id')
event_cwd=$(scribe_json_pick "$event_flat" '.cwd')
[ -n "$tool_name" ] || exit 0
# The action, as text. `.command` is Bash's field; the fallbacks let the matcher
# in hooks.json widen to other tools without this script changing — which is the
# whole reason the server side takes a name and a string rather than a schema.
command_text=$(scribe_json_pick "$event_flat" '.tool_input.command')
[ -n "$command_text" ] || command_text=$(scribe_json_pick "$event_flat" '.tool_input.url')
[ -n "$command_text" ] || command_text=$(scribe_json_pick "$event_flat" '.tool_input.prompt')
[ -n "$command_text" ] || exit 0
# scribe_config, not a hand-rolled pair of parameter expansions: it also treats
# an UNEXPANDED `${...}` placeholder as unset, which would otherwise be sent as
# a garbage Bearer token and 401 on every call.
scribe_config || exit 0
# Bounded before encoding: a heredoc or a pasted script can be enormous, and
# the verb and its target — the part a rule is about — sit at the front. The
# server bounds it again; this keeps a huge payload off the wire in the first
# place. `head -c`, never `cut -c`: cut truncates each LINE and caps nothing.
command_text=$(printf '%s' "$command_text" | head -c 2000)
# Whole, never line by line: per-line encoding joins a multi-line command with
# raw newlines — an invalid URL.
# scribe_urlenc reads bytes and has no notion of a line.
cmd_enc=$(printf '%s' "$command_text" | scribe_urlenc)
tool_enc=$(printf '%s' "$tool_name" | scribe_urlenc)
[ -n "$cmd_enc" ] && [ -n "$tool_enc" ] || exit 0
repo_q=""
lookup_dir=${event_cwd:-${CLAUDE_PROJECT_DIR:-$PWD}}
scope=$(scribe_scope_query "$lookup_dir")
[ -n "$scope" ] && repo_q="&${scope}"
# Where the command runs, against the repo's root: the paths a
# command names are relative to its cwd or absolute, and a System's patterns
# are relative to the root. The server does the arithmetic; this sends both.
where_q=""
repo_root=$(git -C "$lookup_dir" rev-parse --show-toplevel 2>/dev/null || true)
if [ -n "$repo_root" ]; then
where_q="&root=$(printf '%s' "$repo_root" | scribe_urlenc)&cwd=$(printf '%s' "$lookup_dir" | scribe_urlenc)"
fi
# THE SHARED SESSION LEDGER, and the thing most worth getting right here.
#
# scribe_prior_art.sh keeps the rules it has already named in
# <state>/<sid>.rules.ids and passes them as exclude_rule_ids. This hook reads
# and appends to that SAME file rather than keeping its own: two ledgers would
# mean a rule named by one arm gets re-offered by the other, and the hint that
# fires most often is exactly the one that must not repeat itself.
#
# The directory keeps the prior-art name on purpose — renaming it would orphan
# every live session's state for a cosmetic gain.
state_dir="${TMPDIR:-/tmp}/scribe-priorart"
mkdir -p "$state_dir" 2>/dev/null || true
rulefile=""
rule_exclude_q=""
rulingsfile=""
rulings_q=""
if [ -n "$session_id" ]; then
safe_sid=$(printf '%s' "$session_id" | tr -c 'A-Za-z0-9._-' '_')
rulefile="$state_dir/${safe_sid}.rules.ids"
# Ageing, not a flat read: an id named two hours ago is not one the
# session is still holding. scribe_rules_live carries the reasoning.
rule_seen=$(scribe_rules_live "$rulefile")
[ -n "$rule_seen" ] && rule_exclude_q="&exclude_rule_ids=${rule_seen}"
# What the session actually OPENED, as against what it was shown.
rule_exclude_q="${rule_exclude_q}$(scribe_held_query "$state_dir/${safe_sid}.opened.ids")"
# The Systems whose rulings were shown in full — shared with the write-path
# hook, for the reason the rule file is.
rulingsfile="$state_dir/${safe_sid}.rulings.ids"
rulings_q=$(scribe_rulings_query "$rulingsfile")
fi
# `|| exit 0` here, unlike the prior-art hook: there is no local arm whose
# finding would be discarded, and an outage line before every command is worse
# than silence. See the header.
body=$(curl -fsS --max-time 5 \
-H "Authorization: Bearer ${token}" \
"${url%/}/api/plugin/tool-rules?tool=${tool_enc}&command=${cmd_enc}${repo_q}${where_q}${rule_exclude_q}${rulings_q}" 2>/dev/null) || exit 0
body_flat=$(printf '%s' "$body" | scribe_json_flat)
context=$(scribe_json_pick "$body_flat" '.context')
# Remember what was named so it is not repeated this session. BEFORE the
# checkpoint branch and before the empty-context exit: the ledger records what
# the server chose to surface, which happened whichever way this hook then
# renders it. Doing it inside one branch is how the two arms' ledgers came to
# disagree once already.
if [ -n "$rulefile" ]; then
scribe_json_list "$body_flat" '.rule_ids' | scribe_rules_append "$rulefile"
fi
if [ -n "$rulingsfile" ]; then
scribe_json_list "$body_flat" '.ruling_system_ids' >> "$rulingsfile" || true
fi
# ── The pre-act checkpoint ───────────────────────────────────────────────
#
# WHY THIS ARM AND NOT THE WRITE PATH. scribe_prior_art.sh carries an explicit,
# tested property that it never returns a permissionDecision — a recall aid may
# not stand in the way of a write, which is the operator's decision and is
# guarded by test_hook_never_returns_a_permission_decision. No equivalent
# decision covers this arm, and the command-side misses are the ones a stop
# actually reaches: a commit message asserting what CI said, a verification
# script that checks nothing.
#
# WHAT THE STOP IS FOR. Everything else this plugin emits is additionalContext,
# which Claude Code delivers alongside the tool RESULT — so the rule is read
# after the call is written and reads as commentary on a decision already made.
# A deny returns the reason to the
# model with the call unrun, so the rule's own text can be read before the act
# exists. It costs the operator nothing: no prompt reaches them, and the model
# clears it by reading one record and re-submitting.
#
# It cannot recur. `scribe_checkpoint_allowed` holds at most one act per rule
# and at most five per session, so the worst case of a mis-set floor is a noisy
# session rather than one that cannot move.
cp_rule=$(scribe_json_pick "$body_flat" '.checkpoint.rule_id')
cp_reason=$(scribe_json_pick "$body_flat" '.checkpoint.reason')
if [ -n "$cp_rule" ] && [ -n "$cp_reason" ] && [ -n "$session_id" ]; then
if scribe_checkpoint_allowed "$state_dir/${safe_sid}.checkpoint.ids" "$cp_rule"; then
scribe_json_deny PreToolUse "$cp_reason"
exit 0
fi
fi
[ -n "$context" ] || exit 0
scribe_json_out PreToolUse "$context"
exit 0