FabledScribe/plugin/hooks/scribe_session_context.sh

#!/usr/bin/env bash
# Scribe plugin — SessionStart push channel (two tiers + compaction re-grounding).
#
# Tier 1 (STATIC, always fires, no auth, no network): injects the Claude Code
# adapter's own guidance (scribe_static_context.md) — where Scribe's reflexes
# are stated (the using-scribe skill), Claude Code's memory files, /compact,
# /scribe:sync, and what to do when Scribe is unavailable. Since milestone 410
# (decision #4027) it carries only what this client needs said; the reflexes
# themselves are owned by the shared skills and the server's index.
#
# Tier 2 (DYNAMIC, best-effort enrichment): curls the operator's Scribe instance
# for active-project context and appends it. Config comes from
# the plugin's userConfig, exported to hooks as:
#   CLAUDE_PLUGIN_OPTION_API_ENDPOINT  base URL, no trailing slash
#   CLAUDE_PLUGIN_OPTION_API_TOKEN     fmcp_ API key (sensitive)
# NOTE THE CASE: Claude Code uppercases the userConfig key when exporting it, so
# the `api_token` option arrives as CLAUDE_PLUGIN_OPTION_API_TOKEN. Reading the
# lowercase spelling silently yields nothing — that was issue #2198, and it
# disabled the dynamic tier, auto-inject, and the write-path trigger at once.
# The active project is resolved server-side from the working repo's git remote
# (see services/repo_bindings); bind each repo once with the bind_repo MCP tool.
#
# COMPACTION RE-GROUNDING: this hook is registered matcher-less, so it ALSO
# fires after a compaction (SessionStart input `source` == "compact"), when
# earlier turns have just been summarized and in-flight state is most at risk.
# On that source we lead with a banner telling the model to reload project +
# in-flight tasks from Scribe. This stays the durable path: record-as-you-go
# plus a post-compaction reload from the instance.
#
# The other half arrived with #3680. A host hook still cannot make the model
# flush before a compaction — but scribe_precompact_preserve.sh steers the
# SUMMARY, because a PreCompact hook's stdout becomes the compaction's custom
# instructions. The two are complementary, and neither replaces the other: that
# hook decides what survives into the summary, this one reloads from the record
# once the summary lands.
#
# IMPORTANT: do NOT pass config via `${user_config.*}` substitution in a
# shell-form hooks.json command — Claude Code rejects that outright (splicing a
# configured value into a shell command line would let the shell run whatever it
# contains). The env vars above are the supported channel; SCRIBE_URL /
# SCRIBE_TOKEN override for the settings.json dogfooding path.
#
# FAIL-OPEN, BUT NOT SILENT: the dynamic tier never blocks a session, and every
# way it can come up empty produces a short status line — failed fetch, missing
# token, and missing-everything alike. Nothing about the credential path is
# allowed to fail quietly; see the #2198 comment at the status block below.
set -uo pipefail

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

command -v jq >/dev/null 2>&1 || exit 0   # needed to emit the JSON envelope safely

# `CDPATH= cd` is deliberate, not a typo'd assignment: it runs this one `cd`
# with CDPATH empty, so an operator whose CDPATH happens to contain a matching
# directory name can't send us somewhere else — and `cd` won't echo the resolved
# path into our output. shellcheck can't tell that idiom from `CDPATH=cd`.
# shellcheck disable=SC1007
here=$(CDPATH= cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd) || exit 0

# SessionStart delivers a JSON event on stdin; `source` is startup|resume|compact|clear.
event=$(cat 2>/dev/null || true)
source=$(printf '%s' "$event" | jq -r '.source // empty' 2>/dev/null) || source=""

# --- The rule ledger outlives the context it describes (#3749) ---
#
# scribe_prior_art.sh and scribe_tool_rules.sh record every rule id they have
# named in <state>/<sid>.rules.ids and hand it back as exclude_rule_ids, so a
# rule is named once per session and then goes quiet. That is right while the
# session still HOLDS what it was told, and wrong the moment it does not.
#
# A compaction summarizes the earlier injections away and does not touch the
# filesystem, so the rule ends up absent from context AND still excluded —
# unreachable for the rest of the session. The banner below tells the model to
# re-pull its ALWAYS-ON rules, but a rule an arm surfaced is conditional and is
# not in that set, so it has no other way back. The rules most likely to be in
# this state are the ones that fire most often, which is to say the ones that
# apply most.
#
# The session id survives a compaction — the ledgers are keyed by it and are
# still found under the same name afterwards, so a stale ledger is genuinely
# reached again rather than orphaned. (This used to point at an etag marker as
# the evidence for that; milestone 394 removed the preload the etag described,
# and `plugin_context.py` records its retirement.)
#
# CLEARED ON THE SOURCES THAT DESTROY CONTEXT, AND ONLY THOSE:
#
#   compact  CLEAR — summarized away; the file survived.
#   clear    CLEAR — context wiped.
#   startup  nothing to do: a new session id means a new, empty file.
#   resume   KEEP. The context was genuinely restored, so the ledger still
#            describes what the session holds. Clearing here would re-surface
#            every rule after a restore that lost nothing — the mirror error.
#   fork     KEEP, and the answer is the same whichever way forks are keyed: a
#            fork carries the conversation, so if it inherits the id the ledger
#            is accurate, and if it gets a new one the file is empty anyway.
#
# EVERY LEDGER, AND THE NOTE ARMS NEEDED IT MOST (#4101).
#
# This used to clear the two rule ledgers by name and say, in a comment, that
# leaving `.ids` / `.sync.ids` / `.derive.ids` alone was "a decision rather than
# an oversight". Reading the note arms says otherwise, on two counts:
#
#   - They are HARD exclusions. `exclude_ids` goes into `semantic_search_notes`
#     itself, so a surfaced note is removed from the result set — it is not
#     rendered as a reference the way #3750 made a repeated rule. There is no
#     weaker form for it to fall back to.
#   - They never AGE. #3751 gave the rules ledger a TTL precisely because
#     salience decays without a context event; the note channels were left on a
#     flat read.
#
# Hard plus permanent plus never cleared means a note surfaced in the first
# minute of a session is unreachable for the rest of it, through any number of
# compactions. That is milestone 386's original defect, alive on the arms that
# fire most often, and nothing about it was decided.
#
# THE LIST WAS THE BUG, so the fix is not a longer list. `scribe_clear_session_
# ledgers` matches on the naming convention — a per-session ledger is
# `<sid>[.<kind>].ids` — which covers all five and covers the sixth on the day
# it is written. Best-effort, like every other filesystem touch in these hooks:
# a ledger that cannot be removed costs a repeated exclusion, never a session.
#
# NOT swept: `<sid>.unreached`, which records that the instance was unreachable
# rather than what the session holds, and survives on purpose.
case "$source" in
  compact|clear)
    sid=$(printf '%s' "$event" | jq -r '.session_id // empty' 2>/dev/null) || sid=""
    if [ -n "$sid" ]; then
      safe_sid=$(printf '%s' "$sid" | tr -c 'A-Za-z0-9._-' '_')
      scribe_clear_session_ledgers \
        "${TMPDIR:-/tmp}/scribe-priorart" "$safe_sid"
    fi
    ;;
esac

out=""
# Append $1 to $out, separated by a horizontal rule when $out already has content.
append() { if [ -n "$out" ]; then out="${out}"$'\n\n---\n\n'"$1"; else out="$1"; fi; }
# Prepend $1 above $out (used for the compaction banner so it's seen first).
prepend() { if [ -n "$out" ]; then out="$1"$'\n\n---\n\n'"${out}"; else out="$1"; fi; }

# --- Tier 1: static behavioral mandate (always, keyless, networkless) ---
[ -f "$here/scribe_static_context.md" ] && out=$(cat "$here/scribe_static_context.md")

# --- Which version is actually RUNNING (keyless, networkless) ---
#
# An install has two halves and only one self-updates:
#
#   marketplaces/…/scribe-plugin/    git clone — pulls on its own
#   cache/…/scribe/<version>/        what EXECUTES — refreshed only when the
#                                    manifest version changes
#
# So inspecting the clone shows a fix present while the broken copy keeps
# running, and the obvious debugging move actively misleads (#2209). Twice, the
# only detector was the operator saying "I don't think it updated".
#
# Naming the running version in every session makes that answerable from the
# transcript instead of by archaeology in the cache directory. Deliberately NOT
# a server round-trip or a stored per-user record: the state most needing
# diagnosis is the one where credentials never arrive, and this line still
# appears there.
manifest="$here/../.claude-plugin/plugin.json"
if [ -f "$manifest" ]; then
  plugin_version=$(jq -r '.version // empty' "$manifest" 2>/dev/null) || plugin_version=""
  if [ -n "$plugin_version" ]; then
    append "> Scribe plugin **v${plugin_version}** is executing in this session. A fix merged after this version has not reached it — the marketplace clone updates on its own, but the cache that runs only refreshes when the manifest version changes."
  fi
fi

# --- Tier 2: dynamic rules + active-project context (best-effort) ---
# Unconfigured is NOT a failure here: tier 1's static floor is still owed,
# so this records the answer rather than acting on it.
scribe_config || :

dyn=""
status=""
if [ -n "$url" ] && [ -n "$token" ] && command -v curl >/dev/null 2>&1; then
  # Which project is this directory's? A `.scribe` marker first, then the git
  # remote (#4085). scribe_scope_query answers that, and is shared with the
  # other five hooks so a directory scopes the same way everywhere; the pieces
  # are re-read here only to explain what happened when nothing resolved.
  repo_dir=${CLAUDE_PROJECT_DIR:-$PWD}
  marker=$(scribe_marker_file "$repo_dir")
  marker_read=$(scribe_marker_read "$marker")
  marker_id=${marker_read%%$'\t'*}
  marker_why=${marker_read#*$'\t'}
  repo=$(git -C "$repo_dir" remote get-url origin 2>/dev/null || true)
  scope=$(scribe_scope_query "$repo_dir")
  q=""
  [ -n "$scope" ] && q="?${scope}"
  body=$(curl -fsS --max-time 8 \
    -H "Authorization: Bearer ${token}" \
    "${url%/}/api/plugin/context${q}" 2>/dev/null) || body=""
  [ -n "$body" ] && dyn=$(printf '%s' "$body" | jq -r '.context // empty' 2>/dev/null)
  # The rules marker is gone with the resident set it described
  # (milestone 394). Nothing is preloaded, so there is no set whose
  # drift a later write could be told about — a rule is retrieved at
  # the moment it applies, which cannot be stale.
  [ -z "$dyn" ] && status="> ⚠️ Scribe: live project context could not be loaded this session (instance unreachable or request failed). The using-scribe skill still applies — ask for rules with \`search(content_type=\"rule\")\` and project context with \`enter_project()\` as needed."
elif [ -n "$url" ] && [ -z "$token" ]; then
  status="> ⚠️ Scribe: live context disabled this session — the API key is not configured (Scribe base URL is). Set it with \`/plugin\` → Scribe → configure, or export SCRIBE_TOKEN. Tools still work; ask for rules with \`search(content_type=\"rule\")\` and project context with \`enter_project()\`."
elif [ -z "$url" ] && [ -z "$token" ]; then
  # NEITHER value arrived. Previously this case stayed silent as "an unconfigured
  # install", which made issue #2198 invisible for weeks: a *casing* bug here
  # (reading CLAUDE_PLUGIN_OPTION_api_token when Claude Code exports the key
  # UPPERCASED) looks identical to never having configured the plugin, and
  # silently disabled auto-inject and the write-path trigger too. It is not a
  # benign state — the plugin prompts for both values at enable time, so if
  # neither reached the hook, something is wrong. Say so.
  status="> ⚠️ Scribe: live context disabled this session — neither the Scribe base URL nor the API key reached this hook. Configure the plugin (\`/plugin\` → Scribe), or export SCRIBE_URL + SCRIBE_TOKEN. Note this also disables prompt auto-inject and the write-path prior-art trigger. Tools still work; ask for rules with \`search(content_type=\"rule\")\` and project context with \`enter_project()\`."
fi

[ -n "$dyn" ]    && append "$dyn"
[ -n "$status" ] && append "$status"

# --- Nothing resolved: say WHICH nothing, and what would fix it (#4085) ---
#
# The server can say "no project is bound to this working directory", and
# until now that was the whole answer. It is the same sentence for a directory
# that is not a repo, a repo whose remote nobody bound, and a marker file
# naming a project this account cannot read — three different problems with
# three different fixes, and no way to tell them apart from inside the session.
#
# The marker is the adapter's convention, so the adapter explains it: the
# server reports whether a project resolved, and this hook — which knows what
# it sent and why — turns that into the sentence the operator can act on. The
# repo case is left to the server's existing "bind this repo" hint.
if [ -n "$dyn" ] && [ -z "$(printf '%s' "$body" | jq -r '.project.id // empty' 2>/dev/null)" ]; then
  host=$(scribe_url_host "$url")
  if [ -n "$marker_why" ]; then
    append "> ⚠️ Scribe: the marker file \`${marker}\` ${marker_why}, so no project context was loaded. Fix the file, or ignore it and bind this directory another way."
  elif [ -n "$marker_id" ]; then
    append "> ⚠️ Scribe: \`${marker}\` names project ${marker_id}, which this account cannot read on ${host} — it may belong to a different Scribe instance, or the project may have been deleted. Check with \`list_projects()\` and correct the file."
  elif [ -z "$repo" ]; then
    append "> ℹ️ Scribe: this directory is not a git repository and has no \`.scribe\` marker, so no project context was loaded — every hook this session is unscoped. If this work belongs to a Scribe project, call \`list_projects()\` and write the marker: \`{\"instance\": \"${url%/}\", \"project_id\": <id>, \"project\": \"<title>\"}\` in \`${repo_dir}/.scribe\`. Future sessions here load that project on their own."
  fi
fi

# Compaction re-grounding: lead with a reload banner when this fire is a compact.
if [ "$source" = "compact" ]; then
  prepend "> ⟳ This session was just COMPACTED — earlier turns are now a summary, so in-flight detail may be lost. Any rules that had been retrieved went into that summary with everything else, so treat yourself as holding none: before the next consequential act, ask again with \`search(content_type=\"rule\")\` rather than trusting a half-remembered one. Re-run \`enter_project()\` for the active project, check its recent milestones and open tasks, and reconcile what you are mid-way through against what Scribe records. Scribe is the record."
fi

# Nothing at all to inject → stay silent.
[ -n "$out" ] || exit 0

jq -n --arg c "$out" \
  '{hookSpecificOutput: {hookEventName: "SessionStart", additionalContext: $c}}'
exit 0