feat(ci): add pre-commit FactId validation hook (#393)

Grep-based pre-commit check validating fact_id references in content YAML against canonical knowledge catalogs. Runs in advisory mode when catalogs are stubs (exit 0), switches to enforcing mode once populated (exit 1 on unknown fact_ids with file:line output). - tooling/check-fact-ids: core validation script (<2s runtime) - .config/hooks/pre-commit: hook dispatcher for modular checks - Makefile: check-fact-ids + setup-hooks targets, wired into setup - docs/DEVOPS.md: content validation and pre-commit hooks sections Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-13 17:17:34 +01:00
parent 3b757f5adc
commit fe204aa5f4
4 changed files with 160 additions and 3 deletions
@@ -0,0 +1,28 @@
+#!/usr/bin/env bash
+# Pre-commit hook dispatcher. Runs modular checks from tooling/.
+# Installed via: git config core.hooksPath .config/hooks
+set -euo pipefail
+
+REPO_ROOT="$(git rev-parse --show-toplevel)"
+ERRORS=0
+
+run_check() {
+    local script="$1"
+    local label="$2"
+    if [ -x "$REPO_ROOT/$script" ]; then
+        if ! "$REPO_ROOT/$script"; then
+            ERRORS=$((ERRORS + 1))
+        fi
+    else
+        echo "pre-commit: skipping $label ($script not found or not executable)"
+    fi
+}
+
+# --- Checks ---
+run_check "tooling/check-fact-ids" "fact_id validation"
+
+if [ "$ERRORS" -gt 0 ]; then
+    echo ""
+    echo "pre-commit: $ERRORS check(s) failed. Commit aborted."
+    exit 1
+fi
@@ -2,7 +2,7 @@ GODOT := $(shell command -v godot4 2>/dev/null || command -v godot 2>/dev/null)

 .PHONY: help setup build client server game stop test lint ci ci-client ci-server clean \
       decisions-sync decisions-coverage decisions-active decisions-orphan \
-       db-backup db-install validate-content content-ron
+       db-backup db-install validate-content content-ron check-fact-ids setup-hooks

 # --- Configuration ---

@@ -33,13 +33,16 @@ help:
 	@echo "  make decisions-active   List active decisions"
 	@echo "  make decisions-orphan   Decisions without implementing tickets"
 	@echo "  make validate-content   Validate content YAML against schemas"
+	@echo "  make check-fact-ids    Check fact_id references against knowledge catalogs"
 	@echo "  make content-ron       Convert content YAML to RON (build-time)"
 	@echo ""
+	@echo "  make setup-hooks       Install pre-commit hooks (included in setup)"
+	@echo ""
 	@echo "  GODOT_VERSION=4.6 make setup   Override Godot version"

 # --- Setup ---

-setup: setup-rust setup-godot setup-tooling decisions-sync
+setup: setup-rust setup-godot setup-tooling setup-hooks decisions-sync
 	@echo "Dev environment ready."

 setup-rust:
@@ -54,6 +57,10 @@ setup-tooling:
 	@command -v curl >/dev/null 2>&1 || { echo "Install curl (required for Godot download)"; exit 1; }
 	@command -v unzip >/dev/null 2>&1 || { echo "Install unzip (required for Godot download)"; exit 1; }

+setup-hooks:
+	@git config core.hooksPath .config/hooks
+	@echo "Git hooks path set to .config/hooks"
+
 # --- Build ---

 build: build-server build-client
@@ -149,6 +156,9 @@ decisions-orphan:
 validate-content:
 	@tooling/validate-content

+check-fact-ids:
+	@tooling/check-fact-ids
+
 content-ron:
 	cd tooling/content-converter && cargo build --release
 	tooling/content-converter/target/release/content-converter --input content --output content-ron --verbose
@@ -95,6 +95,40 @@ CI targets chain lint → build → test sequentially. A failure in any stage st
 make clean              # Remove build artifacts and .cache/ contents
 ```

+### Content Validation
+
+```bash
+make validate-content     # Validate content YAML against JSON schemas
+make check-fact-ids       # Check fact_id references against knowledge catalogs
+```
+
+`check-fact-ids` operates in two modes:
+- **Advisory** — when knowledge catalogs (`content/global/knowledge/*.yaml`) have no fact definitions yet: lists referenced fact_ids and exits cleanly.
+- **Enforcing** — when catalogs are populated: fails on any `fact_id` reference that doesn't match a canonical definition.
+
+## Pre-commit Hooks
+
+Git hooks are stored in `.config/hooks/` (version-controlled). Activate them with:
+
+```bash
+make setup          # Includes hook installation
+make setup-hooks    # Just hooks
+```
+
+Or manually:
+
+```bash
+git config core.hooksPath .config/hooks
+```
+
+Active checks:
+
+| Check | Script | Behavior |
+|-------|--------|----------|
+| fact_id validation | `tooling/check-fact-ids` | Warns if catalogs are stubs; fails on unknown fact_ids when populated |
+
+The `core.hooksPath` setting uses a relative path (`.config/hooks`) that resolves per worktree, so it works correctly across all worktrees in the repository.
+
 ## Configuration Files

 The `.config/` directory holds shared configuration for linters, formatters, and CI. Examples of what goes here:
@@ -0,0 +1,85 @@
+#!/usr/bin/env bash
+# Validate fact_id references in content YAML against canonical knowledge catalogs.
+# Part of pre-commit checks (ticket #393). Grep-based, targets <2s runtime.
+#
+# Modes:
+#   Advisory — when knowledge catalogs have no fact definitions yet (exit 0)
+#   Enforcing — when catalogs are populated; fails on unknown fact_ids (exit 1)
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(dirname "$SCRIPT_DIR")"
+
+KNOWLEDGE_DIR="$REPO_ROOT/content/global/knowledge"
+CONTENT_DIR="$REPO_ROOT/content/campaigns"
+
+# --- Extract canonical fact_ids from knowledge catalogs ---
+# Matches YAML lines like:  fact_id: some_value  or  fact_id: "some_value"
+# Excludes entity-attributes.yaml (different schema: attribute keys, not fact_ids)
+CANONICAL_IDS=""
+if [ -d "$KNOWLEDGE_DIR" ]; then
+    CANONICAL_IDS=$(
+        grep -rh 'fact_id:\s*' "$KNOWLEDGE_DIR" \
+            --include='*.yaml' \
+            --exclude='entity-attributes.yaml' \
+        | sed 's/.*fact_id:\s*//' \
+        | sed 's/\s*#.*//' \
+        | sed "s/^[\"']\(.*\)[\"']$/\1/" \
+        | sort -u \
+        || true
+    )
+fi
+
+CANONICAL_COUNT=$(echo "$CANONICAL_IDS" | grep -c '\S' || true)
+
+# --- Extract referenced fact_ids from campaign content ---
+# Covers monologue prerequisites.facts[].fact_id and dialogue knowledge_grant.fact_id
+REFERENCED=""
+if [ -d "$CONTENT_DIR" ]; then
+    REFERENCED=$(
+        grep -rh 'fact_id:\s*' "$CONTENT_DIR" \
+            --include='*.yaml' \
+        | sed 's/.*fact_id:\s*//' \
+        | sed 's/\s*#.*//' \
+        | sed "s/^[\"']\(.*\)[\"']$/\1/" \
+        || true
+    )
+fi
+
+REFERENCED_UNIQUE=$(echo "$REFERENCED" | sort -u | grep '\S' || true)
+REF_COUNT=$(echo "$REFERENCED_UNIQUE" | grep -c '\S' || true)
+
+# --- Compare ---
+if [ "$CANONICAL_COUNT" -eq 0 ]; then
+    echo "check-fact-ids: WARNING — no canonical fact_ids in knowledge catalogs"
+    echo "  Catalogs not yet populated. Check is advisory only."
+    if [ "$REF_COUNT" -gt 0 ]; then
+        echo "  $REF_COUNT unique fact_ids referenced in content:"
+        echo "$REFERENCED_UNIQUE" | sed 's/^/    /'
+    fi
+    exit 0
+fi
+
+# Enforcing mode: catalogs have definitions
+ERRORS=0
+while IFS= read -r ref_id; do
+    [ -z "$ref_id" ] && continue
+    if ! echo "$CANONICAL_IDS" | grep -qxF "$ref_id"; then
+        echo "ERROR: unknown fact_id '$ref_id' — not in knowledge catalogs"
+        grep -rn "fact_id:\s*$ref_id" "$CONTENT_DIR" --include='*.yaml' \
+            | sed "s|$REPO_ROOT/||" \
+            | sed 's/^/  /'
+        ERRORS=$((ERRORS + 1))
+    fi
+done <<< "$REFERENCED_UNIQUE"
+
+if [ "$ERRORS" -gt 0 ]; then
+    echo ""
+    echo "check-fact-ids: FAILED — $ERRORS unknown fact_id(s)"
+    echo "  Canonical fact_ids defined in: content/global/knowledge/*.yaml"
+    echo "  Run 'make check-fact-ids' to recheck."
+    exit 1
+fi
+
+echo "check-fact-ids: OK — $REF_COUNT references validated against $CANONICAL_COUNT canonical facts"
+exit 0