fix: bug: supervisor hardcodes ops repo expectation — fails silently on deployments without one (#544)

Add OPS repo presence detection in supervisor-run.sh with degraded mode support:
- Detect if OPS_REPO_ROOT is missing and log WARNING message
- Set OPS_REPO_DEGRADED=1 flag and configure fallback paths
- Bundle minimal knowledge files as fallback for degraded mode
- Update formula to use OPS_KNOWLEDGE_ROOT, OPS_JOURNAL_ROOT, OPS_VAULT_ROOT
- Support local vault destination and journal fallback when ops repo absent

Knowledge files bundled: disk.md, memory.md, ci.md, git.md, dev-agent.md,
review-agent.md, forge.md

The supervisor now runs with full functionality when ops repo is available,
or gracefully degrades to local paths when absent, making the failure mode
explicit rather than silent.

supervisor/AGENTS.md

@@ -40,6 +40,12 @@ P3 (degraded PRs, circular deps, stale deps), P4 (housekeeping).
 - `PRIMARY_BRANCH`, `CLAUDE_MODEL` (set to sonnet by supervisor-run.sh)
 - `WOODPECKER_TOKEN`, `WOODPECKER_SERVER`, `WOODPECKER_DB_PASSWORD`, `WOODPECKER_DB_USER`, `WOODPECKER_DB_HOST`, `WOODPECKER_DB_NAME` — CI database queries
 
+**Degraded mode (Issue #544)**: When `OPS_REPO_ROOT` is not set or the directory doesn't exist, the supervisor runs in degraded mode:
+- Uses bundled knowledge files from `$FACTORY_ROOT/knowledge/` instead of ops repo playbooks
+- Writes journal locally to `$FACTORY_ROOT/state/supervisor-journal/` (not committed to git)
+- Files vault items locally to `$PROJECT_REPO_ROOT/vault/pending/`
+- Logs a WARNING message at startup indicating degraded mode
+
 **Lifecycle**: supervisor-run.sh (cron */20) → lock + memory guard → run
 preflight.sh (collect metrics) → load formula + context → run claude -p via agent-sdk.sh
 → Claude assesses health, auto-fixes, writes journal → `PHASE:done`.

supervisor/preflight.sh

@@ -214,7 +214,9 @@ echo ""
 
 echo "## Pending Vault Items"
 _found_vault=false
-for _vf in "${OPS_REPO_ROOT}/vault/pending/"*.md; do
+# Use OPS_VAULT_ROOT if set (from supervisor-run.sh degraded mode detection), otherwise default to OPS_REPO_ROOT
+_va_root="${OPS_VAULT_ROOT:-${OPS_REPO_ROOT}/vault/pending}"
+for _vf in "${_va_root}"/*.md; do
   [ -f "$_vf" ] || continue
   _found_vault=true
   _vtitle=$(grep -m1 '^# ' "$_vf" | sed 's/^# //' || basename "$_vf")

supervisor/supervisor-run.sh

@@ -50,6 +50,26 @@ WORKTREE="/tmp/${PROJECT_NAME}-supervisor-run"
 # shellcheck disable=SC2034  # consumed by agent-sdk.sh and env.sh log()
 LOG_AGENT="supervisor"
 
+# ── OPS Repo Detection (Issue #544) ──────────────────────────────────────
+# Detect if OPS_REPO_ROOT is available and set degraded mode flag if not.
+# This allows the supervisor to run with fallback knowledge files and
+# local journal/vault paths when the ops repo is absent.
+if [ -z "${OPS_REPO_ROOT:-}" ] || [ ! -d "${OPS_REPO_ROOT}" ]; then
+  log "WARNING: OPS_REPO_ROOT not set or directory missing — running in degraded mode (no playbooks, no journal continuity, no vault destination)"
+  export OPS_REPO_DEGRADED=1
+  # Set fallback paths for degraded mode
+  export OPS_KNOWLEDGE_ROOT="${FACTORY_ROOT}/knowledge"
+  export OPS_JOURNAL_ROOT="${FACTORY_ROOT}/state/supervisor-journal"
+  export OPS_VAULT_ROOT="${PROJECT_REPO_ROOT}/vault/pending"
+  mkdir -p "$OPS_JOURNAL_ROOT" "$OPS_VAULT_ROOT" 2>/dev/null || true
+else
+  export OPS_REPO_DEGRADED=0
+  export OPS_KNOWLEDGE_ROOT="${OPS_REPO_ROOT}/knowledge"
+  export OPS_JOURNAL_ROOT="${OPS_REPO_ROOT}/journal/supervisor"
+  export OPS_VAULT_ROOT="${OPS_REPO_ROOT}/vault/pending"
+  mkdir -p "$OPS_JOURNAL_ROOT" "$OPS_VAULT_ROOT" 2>/dev/null || true
+fi
+
 # Override log() to append to supervisor-specific log file
 # shellcheck disable=SC2034
 log() {
@@ -105,6 +125,25 @@ export CLAUDE_MODEL="sonnet"
 # ── Create worktree (before prompt assembly so trap is set early) ────────
 formula_worktree_setup "$WORKTREE"
 
+# Inject OPS repo status into prompt
+if [ "${OPS_REPO_DEGRADED:-0}" = "1" ]; then
+  OPS_STATUS="
+## OPS Repo Status
+**DEGRADED MODE**: OPS repo is not available. Using bundled knowledge files and local journal/vault paths.
+- Knowledge files: ${OPS_KNOWLEDGE_ROOT:-<unset>}
+- Journal: ${OPS_JOURNAL_ROOT:-<unset>}
+- Vault destination: ${OPS_VAULT_ROOT:-<unset>}
+"
+else
+  OPS_STATUS="
+## OPS Repo Status
+**FULL MODE**: OPS repo available at ${OPS_REPO_ROOT}
+- Knowledge files: ${OPS_KNOWLEDGE_ROOT:-<unset>}
+- Journal: ${OPS_JOURNAL_ROOT:-<unset>}
+- Vault destination: ${OPS_VAULT_ROOT:-<unset>}
+"
+fi
+
 PROMPT="You are the supervisor agent for ${FORGE_REPO}. Work through the formula below.
 
 You have full shell access and --dangerously-skip-permissions.
@@ -117,6 +156,7 @@ ${PREFLIGHT_OUTPUT}
 ${CONTEXT_BLOCK}$(formula_lessons_block)
 ${SCRATCH_CONTEXT:+${SCRATCH_CONTEXT}
 }
+${OPS_STATUS}
 Priority order: P0 memory > P1 disk > P2 stopped > P3 degraded > P4 housekeeping
 
 ${FORMULA_CONTENT}