FabledScribe/plugin/hooks/scribe_after_write.sh

#!/usr/bin/env bash
# Scribe plugin — PostToolUse write-path trigger on Bash (#2901).
#
# scribe_prior_art.sh fires before a Write/Edit TOOL CALL. Code written any
# other way — sed, heredocs, python edit scripts, `cat > file` — never reached
# it, so a whole class of edits (the ones a long session makes most) got no
# prior-art hint, no ledger feed and no duplicate-family warning. This hook
# closes that: after EVERY Bash call it asks git what changed in the working
# tree since it last looked, and runs the same arms on the definitions that
# were just written — the local by-name duplicate arm, the recorded prior-art
# arms and the ledger's derive/divergence checks (#2900/#2793), via the same
# /api/plugin/prior-art endpoint the pre-write hook uses.
#
# Post-hoc by a few seconds, in the same moment and the same session: "the
# copy just landed; here is its family" — not "an audit found it later".
#
# Cheap when nothing changed: one `git status`. State per session, beside the
# pre-write hook's (its three dedup channels are SHARED, so a family named by
# one hook is not named again by the other):
#   ${TMPDIR:-/tmp}/scribe-afterwrite/<sid>.snap   path<TAB>blob-hash of every
#                                                  dirty/untracked file last seen
#   ${TMPDIR:-/tmp}/scribe-priorart/<sid>.*        the dedup channels
#
# NEVER BLOCKS. It returns `additionalContext` only (no decision — there is
# nothing left to decide, the write already happened). Any failure —
# unconfigured, unreachable, not a git repo, malformed — exits 0 in silence.
#
# Config (same as the other hooks):
#   CLAUDE_PLUGIN_OPTION_API_ENDPOINT  base URL, no trailing slash
#   CLAUDE_PLUGIN_OPTION_API_TOKEN     fmcp_ API key (sensitive)
#   SCRIBE_URL / SCRIBE_TOKEN override for the settings.json dogfooding path.
set -uo pipefail

command -v git >/dev/null 2>&1 || exit 0

# shellcheck source=plugin/hooks/scribe_defs.sh
. "$(dirname "${BASH_SOURCE[0]}")/scribe_defs.sh"

# PostToolUse delivers { session_id, cwd, tool_name, tool_input, tool_response }.
event=$(cat 2>/dev/null || true)
event_flat=$(printf '%s' "$event" | scribe_json_flat)
tool_name=$(scribe_json_pick "$event_flat" '.tool_name')
[ "$tool_name" = "Bash" ] || exit 0
session_id=$(scribe_json_pick "$event_flat" '.session_id')
event_cwd=$(scribe_json_pick "$event_flat" '.cwd')
work_dir=${event_cwd:-${CLAUDE_PROJECT_DIR:-$PWD}}
repo_root=$(git -C "$work_dir" rev-parse --show-toplevel 2>/dev/null) || exit 0
[ -n "$repo_root" ] || exit 0

safe_sid=$(printf '%s' "${session_id:-nosession}" | tr -c 'A-Za-z0-9._-' '_')
snap_dir="${TMPDIR:-/tmp}/scribe-afterwrite"
mkdir -p "$snap_dir" 2>/dev/null || true
snap="$snap_dir/${safe_sid}.snap"

# What is dirty now: every modified / added / untracked path, with the blob
# hash of its working-tree content. Hash, not mtime: portable (no stat
# flags), exact (a touch is not a change), and untracked files hash the same
# way tracked ones do.
current=""
while IFS= read -r line; do
  [ -n "$line" ] || continue
  status=${line:0:2}
  path=${line:3}
  case "$status" in
    D*|*D) continue ;;                       # a deletion defines nothing
  esac
  case "$path" in
    *" -> "*) path=${path##* -> } ;;          # rename: the new name
  esac
  # Porcelain quotes paths with special characters; those are skipped rather
  # than unquoted badly — a filename needing quotes is not where shapes live.
  case "$path" in
    \"*) continue ;;
  esac
  [ -f "$repo_root/$path" ] || continue
  sha=$(git -C "$repo_root" hash-object -- "$path" 2>/dev/null) || continue
  current="${current}${path}"$'\t'"${sha}"$'\n'
done < <(git -C "$repo_root" status --porcelain --untracked-files=all 2>/dev/null)

previous=""
[ -f "$snap" ] && previous=$(cat "$snap" 2>/dev/null || true)
first_run=0
[ -f "$snap" ] || first_run=1
# Write the new snapshot NOW, before anything can fail below — the next call
# must compare against this tree, whatever happens to this one's hint.
printf '%s' "$current" > "$snap" 2>/dev/null || true

# Changed = a (path, hash) pair not in the previous snapshot. On the very
# first call of a session there is no previous snapshot; rather than report
# every pre-existing dirty file as "just written", take only files touched in
# the last minute — the Bash call that just ran is the likely author.
changed=""
while IFS=$'\t' read -r path sha; do
  [ -n "${path:-}" ] || continue
  if [ "$first_run" = 1 ]; then
    [ -n "$(find "$repo_root/$path" -mmin -1 2>/dev/null)" ] || continue
  else
    case "$previous" in
      *"${path}"$'\t'"${sha}"*) continue ;;
    esac
  fi
  scribe_skip_path "$path" && continue
  changed="${changed}${path}"$'\n'
done <<< "$current"
[ -n "$changed" ] || exit 0

scribe_config || :   # sets url/token; the call below is guarded on them
scope=$(scribe_scope_query "$repo_root")
repo_q=""
[ -n "$scope" ] && repo_q="&${scope}"

# The dedup channels are the PRE-write hook's files, on purpose (see header).
state_dir="${TMPDIR:-/tmp}/scribe-priorart"
mkdir -p "$state_dir" 2>/dev/null || true
idfile="$state_dir/${safe_sid}.ids"
syncfile="$state_dir/${safe_sid}.sync.ids"
derivefile="$state_dir/${safe_sid}.derive.ids"

combined=""
n_files=0
while IFS= read -r rel_path; do
  [ -n "${rel_path:-}" ] || continue
  # A Bash call that rewrote many files is a refactor or a generator, not a
  # shape being instantiated; four is enough to name what matters.
  n_files=$((n_files + 1))
  [ "$n_files" -le 4 ] || break
  file_path="$repo_root/$rel_path"

  # The code just written: the ADDED lines of the uncommitted diff for a
  # tracked file (sed, not cut: this strips one marker char per line, it is
  # not a payload cap), the whole file when untracked.
  if git -C "$repo_root" ls-files --error-unmatch -- "$rel_path" >/dev/null 2>&1; then
    code=$(git -C "$repo_root" diff -U0 -- "$rel_path" 2>/dev/null | grep '^+' | grep -v '^+++' | sed 's/^+//') || code=""
  else
    code=$(cat "$file_path" 2>/dev/null) || code=""
  fi
  [ -n "$code" ] || continue
  # `|| true` inside: an early-exiting `head` must not void its own output (#4042).
  names=$(printf '%s' "$code" | scribe_defs | sort -u | head -12 || true)
  # Nothing DEFINED in what was written (prose, data, a call-site edit) →
  # nothing to say; the arms are about shapes.
  [ -n "$names" ] || continue

  local_lines=$(scribe_local_dups "$repo_root" "$rel_path" <<< "$names") || local_lines=""
  local_context=""
  if [ -n "$local_lines" ]; then
    local_context="> Already defined elsewhere in this repo — \`${rel_path}\` (just written) adds another copy; check before keeping it (\`git grep\` shown; a nudge, not a gate):"$'\n'"${local_lines}"
  fi

  context=""
  body=""
  reached=""      # "" unconfigured (no call owed) · 1 answered · 0 did not
  unreached_context=""
  if [ -n "$url" ] && [ -n "$token" ]; then
    q=$(printf '%s' "$code" | head -c 1200)
    path_enc=$(printf '%s' "$rel_path" | scribe_urlenc) || path_enc=""
    code_enc=$(printf '%s' "$q" | scribe_urlenc) || code_enc=""
    shapes_q=""
    enc=$(printf '%s\n' "$names" \
      | awk -F'\t' 'NF>=2 {printf "%s%s:%s", (n++?",":""), $1, $2}' \
      | scribe_urlenc) || enc=""
    [ -n "$enc" ] && shapes_q="&shapes=${enc}"
    exclude_q=""; sync_exclude_q=""; derive_exclude_q=""
    if [ -f "$idfile" ]; then
      seen=$(tr '\n' ',' < "$idfile" 2>/dev/null | sed 's/,$//')
      [ -n "$seen" ] && exclude_q="&exclude_ids=${seen}"
    fi
    if [ -f "$syncfile" ]; then
      sync_seen=$(tr '\n' ',' < "$syncfile" 2>/dev/null | sed 's/,$//')
      [ -n "$sync_seen" ] && sync_exclude_q="&exclude_sync_ids=${sync_seen}"
    fi
    if [ -f "$derivefile" ]; then
      derive_seen=$(tr '\n' ',' < "$derivefile" 2>/dev/null | sed 's/,$//' | scribe_urlenc) || derive_seen=""
      [ -n "$derive_seen" ] && derive_exclude_q="&exclude_derive=${derive_seen}"
    fi
    # The rules marker is gone with the resident set it aged (milestone 394).
    # A session no longer holds a fixed set of rules from turn zero, so there
    # is nothing that can have drifted since it loaded them — each rule is
    # retrieved at the moment it applies.
    etag_q=""
    if [ -n "$path_enc" ]; then
      # 8s, not the pre-write hook's 5: this hook runs AFTER the tool, so it
      # gates nothing the session is waiting on, and the first prior-art call
      # after a redeploy is a cold start (embedding warm-up, ~4.6s observed)
      # that a 4s cap turned into a silent fail-open — the one write a
      # session most wants the ledger's word on lost it.
      reached=1
      body=$(curl -fsS --max-time 8 \
        -H "Authorization: Bearer ${token}" \
        "${url%/}/api/plugin/prior-art?path=${path_enc}&code=${code_enc}${repo_q}${exclude_q}${sync_exclude_q}${derive_exclude_q}${shapes_q}${etag_q}" 2>/dev/null) || { body=""; reached=0; }
      # A call that was owed and didn't come back is said, once per outage
      # (#2932) — shared marker with the pre-write hook, so one outage is one
      # line however the code was written.
      if [ "$reached" = 1 ]; then
        scribe_reached "$state_dir" "$safe_sid"
      else
        unreached_context=$(scribe_unreached "$state_dir" "$safe_sid" 8 "$rel_path")
      fi
    fi
    body_flat=""
    if [ -n "$body" ]; then
      body_flat=$(printf '%s' "$body" | scribe_json_flat)
      context=$(scribe_json_pick "$body_flat" '.context')
      if [ -n "$context" ]; then
        scribe_json_list_minus "$body_flat" '.note_ids' '.sync_note_ids' >> "$idfile" || true
        scribe_json_list "$body_flat" '.sync_note_ids' >> "$syncfile" || true
        scribe_json_list "$body_flat" '.derive_keys' >> "$derivefile" || true
        # Several files in one call may name the same family: keep each
        # token once, so the next request's exclude list stays exact.
        for f in "$idfile" "$syncfile" "$derivefile"; do
          [ -s "$f" ] && { sort -u -o "$f" "$f" 2>/dev/null || true; }
        done
      fi
    fi
  fi

  # The record nudge (#2664), same gate as the pre-write hook: duplication
  # demonstrated locally AND nothing recorded for it — and (#2932) never on a
  # call that did not answer; "nothing recorded" is a claim only an answer
  # can back.
  if [ -n "$local_lines" ] && [ "$reached" != 0 ]; then
    n_recorded=$(scribe_json_len "$body_flat" '.note_ids')
    if [ "${n_recorded:-0}" = "0" ] || [ "$n_recorded" = "" ]; then
      local_context="${local_context}"$'\n'"> None of those existing copies is recorded in Scribe. If the version just written is the canonical one — or this edit is consolidating the copies — record it now with create_snippet so the next session is offered it instead of writing another copy."
    fi
  fi

  part="$local_context"
  if [ -n "$context" ]; then
    [ -n "$part" ] && part="${part}"$'\n'
    part="${part}${context}"
  fi
  if [ -n "$unreached_context" ]; then
    [ -n "$part" ] && part="${part}"$'\n'
    part="${part}${unreached_context}"
  fi
  [ -n "$part" ] || continue
  [ -n "$combined" ] && combined="${combined}"$'\n'
  combined="${combined}${part}"
done <<< "$changed"

[ -n "$combined" ] || exit 0
scribe_json_out PostToolUse "$combined"
exit 0