FabledScribe/plugin/hooks/scribe_defs.sh

#!/usr/bin/env bash
# shellcheck shell=bash
# Scribe plugin — the pieces the hooks share (#2901, #2278).
#
# scribe_prior_art.sh fires BEFORE a Write/Edit tool call; scribe_after_write.sh
# fires AFTER a Bash tool call and diffs the working tree, so code written by
# sed/heredocs/scripts gets the same prior-art and ledger checks. Both need the
# same three things, kept here so they cannot drift apart:
#
#   scribe_skip_path PATH      formats that hold prose or data, not shapes
#   scribe_defs                stdin code → "kind<TAB>name" per definition
#   scribe_local_dups ROOT REL "kind<TAB>name" lines on stdin → the by-name
#                              local-duplicate lines (ARM 1, #2280)
#   scribe_unreached STATE SID SECS REL  the "Scribe didn't answer" line, once
#                              per outage (#2932) — or nothing, if said lately
#   scribe_reached STATE SID   the server answered: the next outage speaks again
#   scribe_config              sets `url` + `token` from the env, returns 0
#                              only if BOTH are usable (#2278)
#   scribe_rules_live FILE     live rule ids from the exclusion ledger,
#                              comma-joined; entries age out (#3751)
#   scribe_rules_append FILE   stdin ids -> the ledger, timestamped
#   scribe_scope_query DIR     `project_id=N` or `repo=<enc>` for DIR — the
#                              project-scope key EVERY hook sends (#4085).
#                              Helpers: scribe_marker_file, scribe_url_host,
#                              scribe_marker_read (id<TAB>why-not),
#                              scribe_marker_project (the id alone)
#
# Sourced, not executed: `. "$(dirname "${BASH_SOURCE[0]}")/scribe_defs.sh"`.

# Skip formats that hold prose or data rather than reusable code. Purely to
# avoid a pointless round-trip — the server would return nothing for these
# anyway. Config formats are NOT skipped: a CI workflow or a compose file is
# often exactly the thing worth reusing.
scribe_skip_path() {
  case "$1" in
    *.md|*.mdx|*.txt|*.rst|*.json|*.lock|*.log|*.csv|*.tsv|*.svg|*.png|*.jpg|*.jpeg|*.gif|*.ico|*.pdf)
      return 0 ;;
  esac
  return 1
}

# ---------------------------------------------------------------------------
# kind<TAB>name for each thing a piece of code DEFINES, in source order. One
# program, two consumers: the local duplicate arm (every definition in the
# payload) and the ledger feed (#2791, below: the definitions being written,
# or the one enclosing an Edit). Rule-for-rule mirrored by the server's
# services/coverage.py extract_shapes — ledger rows are keyed by what THAT
# sees, so the two must agree on what counts as a definition.
scribe_defs() {
  awk '
    {
      # CSS class definition: .name { or .name,
      if (match($0, /^[[:space:]]*\.[A-Za-z][A-Za-z0-9_-]*[[:space:]]*[,{]/)) {
        t = $0; sub(/^[[:space:]]*\./, "", t); sub(/[[:space:]]*[,{].*$/, "", t)
        if (t != "") print "css\t" t; next
      }
      line = $0; sub(/^[[:space:]]+/, "", line)
      # Strip leading declaration modifiers so the definition keyword is the
      # first word regardless of language (export/pub/private/suspend/...).
      sub(/^((pub(\([a-z]+\))?|export|default|private|internal|protected|public|static|suspend|async|open|sealed|data|abstract|final|inline|unsafe|extern|override)[[:space:]]+)*/, "", line)
      # Go method with receiver: func (r *T) Name(
      if (match(line, /^func[[:space:]]*\([^)]*\)[[:space:]]*[A-Za-z_]/)) {
        t = line; sub(/^func[[:space:]]*\([^)]*\)[[:space:]]*/, "", t)
        sub(/[^A-Za-z0-9_].*$/, "", t)
        if (t != "") print "sym\t" t; next
      }
      # Keyword-announced definitions, functions and named types alike.
      # Dunders are skipped: every class defines __init__, so "already defined
      # in N other files" is guaranteed noise for them — and noise is what
      # teaches sessions to skip the hint.
      if (match(line, /^(function|def|class|func|fun|fn|sub|struct|trait|interface|enum|object|protocol|type)[[:space:]]+[A-Za-z_$]/)) {
        t = line; sub(/^[a-z]+[[:space:]]+/, "", t)
        sub(/[^A-Za-z0-9_$].*$/, "", t)
        # `type` defines only when something follows the name (= or {); an
        # import specifier `type Foo,` is the same two words and defines
        # nothing (mirror of coverage.py, #2904).
        if (line ~ /^type[[:space:]]/) {
          rest = line; sub(/^type[[:space:]]+[A-Za-z_$][A-Za-z0-9_$]*/, "", rest)
          if (rest !~ /[={]/) next
        }
        if (t != "" && t !~ /^__.*__$/) print "sym\t" t; next
      }
      # Arrow/expression assignment: const name = (…) / let name = async (
      if (match(line, /^(const|let)[[:space:]]+[A-Za-z_$][A-Za-z0-9_$]*[[:space:]]*=[[:space:]]*(async[[:space:]]*)?[(<]/)) {
        t = line; sub(/^(const|let)[[:space:]]+/, "", t)
        sub(/[^A-Za-z0-9_$].*$/, "", t)
        if (t != "") print "sym\t" t; next
      }
    }
  ' 2>/dev/null
}


# ---------------------------------------------------------------------------
# ARM 1 — BY NAME, LOCALLY (#2280). Does a definition of this already exist?
#
# The recorded arms ask Scribe what was RECORDED; the ledger arm (#2900) asks
# what a BOUND repo's ledger knows. A helper nobody recorded, in a repo nobody
# bound, is invisible to both — which is how `.btn-primary` came to be defined
# four times, already diverged. This arm asks the one question only the
# developer's machine can answer, inside the repo, holding the code about to
# be written: no index, no storage, no server — it runs even on an install
# that has never configured Scribe.
#
# Definition-shaped patterns only. Grepping for bare occurrences would match
# every CALL site and drown the real finding — and a hint that is mostly noise
# is one people learn to skip, which is worse than none. ALL code, not a
# language shortlist (#2682): the same keyword family scribe_defs announces.
#
# $1 repo root, $2 repo-relative path of the file being written (excluded from
# the grep — it would always match itself on an Edit). Definitions on stdin.
# Prints one "> - `name` is already defined in N other file(s): …" per hit.
scribe_local_dups() {
  local root="$1" rel="$2" kind name pat hits count label files
  while IFS=$'\t' read -r kind name; do
    [ -n "${name:-}" ] || continue
    case "$kind" in
      css) pat="^[[:space:]]*\.${name}[[:space:]]*[,{]" ;;
      *)   pat="(function|def|class|func|fun|fn|sub|struct|trait|interface|enum|object|protocol|type)[[:space:]]+${name}[^A-Za-z0-9_]|func[[:space:]]*\([^)]*\)[[:space:]]*${name}[[:space:]]*\(|(const|let)[[:space:]]+${name}[[:space:]]*=" ;;
    esac
    # -I skips binaries; :(exclude) drops the file being written.
    # `|| true` INSIDE the substitution, not `|| hits=""` outside it (#4042):
    # under the hooks' `pipefail`, `head` exiting after four lines kills a
    # git grep that is still writing, the pipeline reports SIGPIPE, and an
    # outer fallback then wipes the four hits head already printed. The name
    # most duplicated — the one this arm exists for — was the one it dropped.
    hits=$(git -C "$root" grep -I -l -E -e "$pat" -- . ":(exclude)${rel}" 2>/dev/null | head -4 || true)
    [ -n "$hits" ] || continue
    count=$(printf '%s\n' "$hits" | grep -c . 2>/dev/null || echo 0)
    label=$([ "$kind" = css ] && printf '.%s' "$name" || printf '%s' "$name")
    files=$(printf '%s' "$hits" | tr '\n' ' ' | sed 's/ $//')
    printf '> - `%s` is already defined in %s other file(s): %s\n' "$label" "$count" "$files"
  done
}

# ---------------------------------------------------------------------------
# The blind spot made visible (#2932). Both write-path hooks fail OPEN when the
# instance is slow or down — right for noise, wrong for silence: a session
# cannot tell "the ledger checked and found nothing" from "the ledger never
# answered", and a self-surfacing system cannot afford an invisible miss (the
# first write after a redeploy lost its derive line to a 4s cold start and
# nobody knew). So a failed call says so — ONCE per outage: the marker holds
# the time it last spoke; within ten minutes of that it stays quiet, and a
# successful call clears it so the next outage announces itself afresh.
# Unconfigured installs never reach this: no URL/token means no call was owed.
# Where every hook gets its endpoint and credential. Four lines, and each of
# the five hooks carried its own copy until #2278 — which is exactly the
# missing-sibling shape: the `${...}` guard below is a correctness detail a
# sixth hook would have forgotten, and nothing would have failed loudly.
#
# Sets `url` and `token` as globals rather than echoing them: a token must not
# pass through a subshell's output, where it could land in a log or an `xtrace`
# line. Returns 0 only when both are usable, so a caller can either bail
# (`scribe_config || exit 0`) or carry on degraded — the session-context hook
# still owes its static floor when Scribe is unconfigured.
# Declared here, not just assigned inside the function: `scribe_defs.sh` owns
# these two names, and a sourcing hook should have them defined the moment it
# sources — before any code path that might reference them. It also lets
# the linter see the assignment, which it cannot follow into a function in
# another file without -x (SC2154).
url=""
token=""

scribe_config() {
  url=${SCRIBE_URL:-${CLAUDE_PLUGIN_OPTION_API_ENDPOINT:-}}
  token=${SCRIBE_TOKEN:-${CLAUDE_PLUGIN_OPTION_API_TOKEN:-}}
  # An unexpanded `${...}` placeholder arriving as a literal would be sent as a
  # garbage Bearer token and 401. Treat it as unset.
  case "$url"   in *'${'*) url="" ;;  esac
  case "$token" in *'${'*) token="" ;; esac
  [ -n "$url" ] && [ -n "$token" ]
}

_SCRIBE_UNREACHED_QUIET=600

scribe_unreached() {
  local marker="$1/$2.unreached" now last
  now=$(date +%s 2>/dev/null) || now=0
  if [ -f "$marker" ]; then
    last=$(cat "$marker" 2>/dev/null) || last=0
    case "$last" in ''|*[!0-9]*) last=0 ;; esac
    [ $((now - last)) -lt "$_SCRIBE_UNREACHED_QUIET" ] && return 0
  fi
  printf '%s' "$now" > "$marker" 2>/dev/null || true
  printf '> Scribe did not answer the prior-art check for `%s` within %ss — this write went UNCHECKED against the record and the shape ledger (the local by-name arm, if it spoke above, needed no server). If the name matters, check it yourself: `search` for the concept, `list_shapes(project_id, path=…)` for the ledger. Said once per outage; if it keeps happening the instance is slow or down.' "$4" "$3"
}

scribe_reached() {
  rm -f "$1/$2.unreached" 2>/dev/null || true
}

# ---------------------------------------------------------------------------
# THE RULE EXCLUSION LEDGER, and how entries in it AGE (#3751).
#
# Two hooks write this file and two read it, which is the whole reason the
# parsing lives here: `scribe_prior_art.sh` and `scribe_tool_rules.sh` share
# one ledger so a rule named by one arm is not re-offered by the other, and a
# format only one of them understood would break that on the first read.
#
# WHAT PROBLEM AGEING SOLVES. #3749 clears the ledger when an EVENT destroys
# context — a compaction or a /clear. This is the case with no event at all: a
# long session where the rule was named two hundred turns ago and has simply
# fallen out of attention. It is #3702's argument at the tier level (present in
# context and salient at the moment are different properties) applied to time
# instead of to tier.
#
# PER-ENTRY TIMESTAMPS, NOT A FILE MTIME. Clearing the whole ledger when the
# file is old is one line of shell and wrong in exactly the session that needs
# it: a single recent write keeps every stale id alive, and the ids that go
# stale first are the ones from the rules that fire most.
#
# WALL TIME, NOT A TURN COUNT, and the trade is real rather than dismissed. A
# turn count is a truer model of salience — an idle session does not forget —
# but a hook has no turn number without keeping its own counter, which is a
# second piece of session state to write, read, clear on compaction and get
# wrong. Wall time is available from `date` and costs nothing. The failure mode
# it accepts is a session left idle over lunch treating its rules as forgotten,
# which produces one extra full line per rule and no other harm.
_SCRIBE_RULE_TTL=2700

# 45 MINUTES, and the reasoning rather than the number (rule 32).
#
# There is no data on this yet, so it is a judgement made to be revised — the
# telemetry that would settle it is the one #3807 just built, and a reading of
# how often an aged-out rule gets PULLED after it returns is what should move
# this.
#
# Too short and the exclusion stops existing and the repetition it prevents
# comes back. Too long and it never fires at all in a session short enough to
# matter. 45 minutes is about one working stretch on a single task: long enough
# that a rule does not re-announce itself while you are still doing the thing
# it governs, short enough that a multi-hour session gets a genuine refresh
# rather than one 9am mention.
#
# Being wrong on the short side is now the cheaper error, which is why this
# leans short. Since #3750 an excluded rule is REFERENCED rather than withheld,
# so the ledger is no longer the only thing standing between a session and a
# rule it has forgotten — an expired entry costs one full line instead of one
# short one, and the exclusion re-arms the moment it is spent.

# Live ids from a ledger, comma-joined for `exclude_rule_ids`. Empty output for
# a missing, empty or fully-aged file — the callers already treat "" as "send
# no exclusions".
#
# THE LAST ENTRY FOR AN ID WINS, and this is what stops a rule ping-ponging.
# The file is append-only, so a rule that ages out, gets surfaced fresh and is
# appended again has TWO lines. Reading the first would leave it permanently
# expired and it would re-announce itself on every single call from then on —
# the loudest possible failure, from the mechanism meant to quieten things.
# Appends are chronological, so the last line for an id is its most recent.
#
# A BARE ID — no tab, no timestamp — IS LIVE. That is the pre-#3751 format, and
# a session in flight when this ships has a ledger full of them. Treating
# unknown as expired would make every one of those sessions re-announce every
# rule it had already been told, all at once, which is precisely the noise this
# exists to prevent. Unknown means "not measured" and never "old" — the same
# null discipline the retrieval_logs columns use. Those entries simply never
# age, which is bounded: the session ends.
scribe_rules_live() {
  local f="$1" now
  [ -n "$f" ] && [ -f "$f" ] || return 0
  now=$(date +%s 2>/dev/null) || now=0
  awk -F'\t' -v now="$now" -v ttl="$_SCRIBE_RULE_TTL" '
    {
      id = $1
      gsub(/[^0-9]/, "", id)
      if (id == "") next
      if (!(id in seen)) { seen[id] = 1; seq[++n] = id }
      stamp[id] = ($2 ~ /^[0-9]+$/) ? $2 : ""
    }
    END {
      out = ""
      for (i = 1; i <= n; i++) {
        id = seq[i]
        if (stamp[id] != "" && now > 0 && (now - stamp[id]) > ttl) continue
        out = out (out == "" ? "" : ",") id
      }
      print out
    }
  ' "$f" 2>/dev/null || true
}

# Append surfaced ids, stamped. Reads ids on stdin, one per line — the shape
# `jq -r '(.rule_ids // [])[]?'` already produces at both call sites.
scribe_rules_append() {
  local f="$1" now
  [ -n "$f" ] || return 0
  now=$(date +%s 2>/dev/null) || now=0
  awk -v ts="$now" 'NF { print $1 "\t" ts }' >> "$f" 2>/dev/null || true
}

# ---------------------------------------------------------------------------
# WHICH PROJECT IS THIS DIRECTORY'S? (#4085)
#
# Every hook here scopes its request to a project, and until this existed all
# six did it the same single way: `git remote get-url origin`, resolved
# server-side through the repo bindings. That works well inside a bound repo
# and not at all outside one — a session in a plain directory got no project
# scope from ANY hook, silently, because the one key the whole chain turns on
# only exists in a git repo.
#
# The second key is a `.scribe` file in the directory (or above it, the way
# git finds its root), naming the project the work belongs to. It is a
# POINTER, not a copy: an id and enough to check the id means what it says.
# Nothing Scribe should be holding goes in it.
#
#   {"instance": "https://scribe.example.com", "project_id": 2,
#    "project": "FabledScribe"}
#
#   instance    WHICH Scribe the id belongs to, and the reason this file is
#               not just a number. A project id means nothing on its own: id 2
#               is a different project on every instance, so a marker that
#               travels — a copied directory, a shared machine, a repo someone
#               else clones — would silently scope a session to the wrong
#               project. Compared HOST-ONLY against the configured endpoint, so
#               http/https and a trailing slash don't cause a false mismatch.
#               A mismatch drops the id: no project beats the wrong project.
#   project_id  the pointer itself. Required.
#   project     a human label. NOTHING READS IT. It is there so the file
#               answers "what is this?" when opened, and so a stale one is
#               visible rather than inert.
#
# A bare integer is also accepted (`echo 2 > .scribe`), because it is what a
# person writes by hand and it parses as JSON already. It skips the instance
# check by having nothing to check — deliberate, and the reason the written
# form carries `instance`.
#
# THE MARKER WINS over a git remote. Someone put the file there on purpose;
# a remote is just where the code happens to be pushed. That also makes the
# marker the way to override a binding for one directory.

# Nearest `.scribe` at or above DIR. Walks up to the filesystem root, capped so
# a pathological path cannot spin.
scribe_marker_file() {
  local dir="$1" depth=0
  [ -n "$dir" ] || return 0
  while [ "$depth" -lt 40 ]; do
    [ -f "$dir/.scribe" ] && { printf '%s' "$dir/.scribe"; return 0; }
    case "$dir" in ""|"/") return 0 ;; esac
    dir=$(dirname -- "$dir" 2>/dev/null) || return 0
    depth=$((depth + 1))
  done
  return 0
}

# Host of a URL, lowercased, port kept. "" for empty input.
scribe_url_host() {
  printf '%s' "${1:-}" \
    | sed -e 's#^[A-Za-z][A-Za-z0-9+.-]*://##' -e 's#^[^/@]*@##' -e 's#[/?].*$##' \
    | tr 'A-Z' 'a-z'
}

# Read a marker file: prints "ID<TAB>REASON", at most one of them non-empty.
#
#   "7\t"            use project 7
#   "\tnames no …"   a file is there and deliberately NOT used; say why
#   "\t"             no marker file at all — the ordinary case, say nothing
#
# One line rather than an id plus a global, because every caller reads this
# through `$( )` and a global set inside a command substitution dies with the
# subshell. The caller would then read an unset variable, which under the
# `set -u` these hooks all run with aborts the hook and costs the whole
# session's context — a failure far larger than the message it was fetching.
scribe_marker_read() {
  local f="$1" id inst want
  [ -n "$f" ] && [ -f "$f" ] || { printf '\t'; return 0; }
  command -v jq >/dev/null 2>&1 || { printf '\t'; return 0; }
  # A bare integer is valid JSON, so one filter reads both forms.
  id=$(jq -r 'if type=="number" then (.|floor|tostring)
              elif type=="object" then (.project_id // empty | tostring)
              else empty end' "$f" 2>/dev/null) || id=""
  case "$id" in ''|*[!0-9]*) id="" ;; esac
  if [ -z "$id" ] || [ "$id" = "0" ]; then
    printf '\tnames no project_id'
    return 0
  fi
  inst=$(jq -r 'if type=="object" then (.instance // empty) else empty end' "$f" 2>/dev/null) || inst=""
  if [ -n "$inst" ]; then
    want=$(scribe_url_host "${url:-}")
    inst=$(scribe_url_host "$inst")
    if [ -n "$want" ] && [ "$inst" != "$want" ]; then
      printf '\tpoints at %s, but this session is configured for %s' "$inst" "$want"
      return 0
    fi
  fi
  printf '%s\t' "$id"
}

# Just the id a marker names, or "" — the half scribe_scope_query needs.
scribe_marker_project() {
  scribe_marker_read "$1" | cut -f1
}

# The query args identifying DIR's project — `project_id=N` or `repo=<enc>` —
# with NO leading `?` or `&`, so each caller keeps its own separator. Empty
# when neither key is available. Requires `url` to be set (scribe_config) for
# the marker's instance check; without it a marker is still honoured, since an
# unconfigured hook is not going to send the request anyway.
scribe_scope_query() {
  local dir="$1" id repo enc
  id=$(scribe_marker_project "$(scribe_marker_file "$dir")")
  if [ -n "$id" ]; then
    printf 'project_id=%s' "$id"
    return 0
  fi
  repo=$(git -C "$dir" remote get-url origin 2>/dev/null || true)
  [ -n "$repo" ] || return 0
  command -v jq >/dev/null 2>&1 || return 0
  enc=$(printf '%s' "$repo" | jq -sRr '@uri' 2>/dev/null) || enc=""
  [ -n "$enc" ] && printf 'repo=%s' "$enc"
}