Files
FabledScribe/plugin/hooks/scribe_session_context.sh
T
bvandeusenandClaude Opus 5 5c9bb40777
CI & Build / Python lint (push) Successful in 6s
CI & Build / Plugin hooks (push) Successful in 11s
CI & Build / integration (push) Successful in 32s
CI & Build / TypeScript typecheck (push) Successful in 35s
CI & Build / Python tests (push) Failing after 1m0s
CI & Build / Build & push image (push) Skipped
feat(rules): a session is told when its rules move under it (#3244, milestone 323 step 5)
The rules payload carries a marker; the write-path hook hands it back; the
server says which rules moved. Nothing is said when nothing moved.

THE COUNT IS NOT DECORATION. max(updated_at) alone cannot see a DELETED rule
— it moves no timestamp — and that is the single change that takes an
instruction OUT of force, which is the one a session most needs to hear
about. The marker is `<max updated_at>|<count>`, and a deletion is reported
through the count because there is no row left to name.

THE HOOK IS THE CARRIER because it already fires before a write, which is the
moment acting on a stale rule costs something. One comparison, no payload,
no extra round trip.

WHERE THE MARKER IS CAPTURED, and it could not be anywhere else: the
SessionStart hook, from /api/plugin/context. The model also receives one from
list_always_on_rules, but a hook cannot see an MCP tool's result — so the
value the write path compares has to be stored where a shell script can
reach it. Keyed by session id in the state dir the prior-art hook already
uses, so "changed since" means since THIS session loaded its rules.

NOT ON rules_payload, against the task's letter. Those are applicable_rules —
a different, subscription-derived set. One key name over two sets is how a
comparison starts reporting phantom changes, and the write path compares
against the always-on set.

WHAT IT CANNOT SEE is stated in both the service and the write-path arm as a
table, because a reader who finds an etag will assume it covers staleness
generally:

  another session edits a rule mid-flight             | caught
  the session is misremembering a rule read hours ago | caught
  compaction summarised the rules out of context      | NOT caught

The third is the most common, and the marker is blind to it — the etag was in
context too and went with the rules. The SessionStart nudge is that case's
only mechanism and must not be softened because this shipped. A test asserts
both modules still explain that.

Instance-agnostic (rule 115): an install with no rules produces a stable
marker rather than an error, and "no rules" reads as a state rather than as a
change. An unreadable or absent marker reports nothing — a signal that cries
wolf is worse than none, because it trains a reader to skip the line that
will one day be true. The arm fails open like every other arm on this hook.

The delivery is tested through the real build_write_path_hint rather than the
helper alone: the feature IS a line arriving in a session, and the arithmetic
being right proves nothing about that.

Live acceptance is deploy-gated and not yet recorded on the task.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-30 13:02:00 -04:00

162 lines
9.7 KiB
Bash
Executable File

#!/usr/bin/env bash
# Scribe plugin — SessionStart push channel (two tiers + compaction re-grounding).
#
# Tier 1 (STATIC, always fires, no auth, no network): injects a bundled
# behavioral mandate (scribe_static_context.md) so a fresh session knows to
# reach for Scribe — record work, recall before acting — even when the instance
# is unreachable or unconfigured. The static tier is the load-bearing floor that
# does not depend on the key or the network.
#
# Tier 2 (DYNAMIC, best-effort enrichment): curls the operator's Scribe instance
# for always-on rules + 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. (PreCompact is the wrong tool here — a host hook
# can't make the model flush, and can't know the in-flight task ids; the durable
# path is record-as-you-go + this post-compaction reload.)
#
# 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=""
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
# Resolve the working repo's remote so the server can map it to a project.
repo_dir=${CLAUDE_PROJECT_DIR:-$PWD}
repo=$(git -C "$repo_dir" remote get-url origin 2>/dev/null || true)
q=""
if [ -n "$repo" ]; then
enc=$(printf '%s' "$repo" | jq -sRr '@uri' 2>/dev/null) || enc=""
[ -n "$enc" ] && q="?repo=${enc}"
fi
body=$(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)
# Stash the rules marker for the write-path hook (milestone 323). THIS is
# where it has to be captured: the model receives one from
# list_always_on_rules too, but a hook cannot see an MCP tool's result. Stored
# under the same state dir the prior-art hook already uses, keyed by session,
# so "changed since" means since THIS session loaded its rules.
#
# Written on `compact` as well as `startup`, and that is correct rather than
# convenient: a compact tells the session to re-pull its rules, so the marker
# should describe the set it is about to hold. It is also why this cannot
# cover the compaction case — see the table in services/plugin_context.py.
if [ -n "$body" ]; then
etag=$(printf '%s' "$body" | jq -r '.rules_etag // empty' 2>/dev/null) || etag=""
if [ -n "$etag" ]; then
sid=$(printf '%s' "$event" | jq -r '.session_id // empty' 2>/dev/null) || sid=""
safe_sid=$(printf '%s' "${sid:-nosession}" | tr -c 'A-Za-z0-9._-' '_')
etag_dir="${TMPDIR:-/tmp}/scribe-priorart"
# Best-effort throughout: a marker that cannot be stored costs a hint,
# never the session.
mkdir -p "$etag_dir" 2>/dev/null \
&& printf '%s' "$etag" > "$etag_dir/${safe_sid}.rules_etag" 2>/dev/null || true
fi
fi
[ -z "$dyn" ] && status="> ⚠️ Scribe: live rules/project context could not be loaded this session (instance unreachable or request failed). The standing guidance above still applies — pull rules with \`list_always_on_rules()\` 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; pull rules with \`list_always_on_rules()\` 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; pull rules with \`list_always_on_rules()\` and project context with \`enter_project()\`."
fi
[ -n "$dyn" ] && append "$dyn"
[ -n "$status" ] && append "$status"
# Compaction re-grounding: lead with a reload banner when this fire is a compact.
if [ "$source" = "compact" ]; then
prepend "> ⟳ This session was just COMPACTED — earlier turns are now a summary, so in-flight detail may be lost. Before continuing, reload your bearings from Scribe: re-pull the operator's binding rules with \`list_always_on_rules()\` (a compaction can summarize them out of context, leaving only generic harness defaults in their place), re-run \`enter_project()\` for the active project, check its open tasks and recent notes, and reconcile what you're mid-way through against what Scribe records. Don't trust half-remembered state — Scribe is the record."
fi
# Nothing at all to inject → stay silent.
[ -n "$out" ] || exit 0
jq -n --arg c "$out" \
'{hookSpecificOutput: {hookEventName: "SessionStart", additionalContext: $c}}'
exit 0