refactor: rename factory/ → supervisor/, factory-poll → supervisor-poll

The supervisor agent was confusingly named "factory" (same as the
project). Rename directory, script, log, lock, status, and escalation
files. Update all references across scripts and docs.

FACTORY_ROOT env var unchanged (refers to project root, not agent).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

BOOTSTRAP.md

@@ -55,7 +55,7 @@ CLAUDE_TIMEOUT=7200                   # seconds per Claude invocation
 
 ### Required: CI pipeline
 
-The repo needs at least one Woodpecker pipeline. Dark-factory monitors CI status to decide when a PR is ready for review and when it can merge.
+The repo needs at least one Woodpecker pipeline. Disinto monitors CI status to decide when a PR is ready for review and when it can merge.
 
 ### Required: `CLAUDE.md`
 
@@ -155,7 +155,7 @@ Add (adjust paths):
 FACTORY_ROOT=/home/you/disinto
 
 # Supervisor — health checks, auto-healing (every 10 min)
-0,10,20,30,40,50 * * * * $FACTORY_ROOT/factory/factory-poll.sh
+0,10,20,30,40,50 * * * * $FACTORY_ROOT/supervisor/supervisor-poll.sh
 
 # Review agent — find unreviewed PRs (every 10 min, offset +3)
 3,13,23,33,43,53 * * * * $FACTORY_ROOT/review/review-poll.sh
@@ -176,7 +176,7 @@ The 3-minute offsets prevent agents from competing for resources.
 
 ```bash
 # Should complete with "all clear" (no problems to fix)
-bash factory/factory-poll.sh
+bash supervisor/supervisor-poll.sh
 
 # Should list backlog issues (or "no backlog issues")
 bash dev/dev-poll.sh
@@ -188,7 +188,7 @@ bash review/review-poll.sh
 Check logs after a few cycles:
 
 ```bash
-tail -30 factory/factory.log
+tail -30 supervisor/supervisor.log
 tail -30 dev/dev-agent.log
 tail -30 review/review.log
 ```
@@ -203,7 +203,7 @@ If you want real-time notifications and human-in-the-loop escalation:
    sudo cp lib/matrix_listener.service /etc/systemd/system/
    sudo systemctl enable --now matrix_listener
    ```
-3. The factory and gardener will post status updates and escalation threads to the configured room. Reply in-thread to answer escalations.
+3. The supervisor and gardener will post status updates and escalation threads to the configured room. Reply in-thread to answer escalations.
 
 ## Lifecycle
 
@@ -219,7 +219,7 @@ You write issues (with backlog label)
             → merge, close issue, clean up
 
 Meanwhile:
-  factory-poll monitors health, kills stale processes, manages resources
+  supervisor-poll monitors health, kills stale processes, manages resources
   gardener grooms backlog: closes duplicates, promotes tech-debt, escalates ambiguity
   planner rebuilds AGENTS.md from git history, gap-analyses against VISION.md
 ```
@@ -233,4 +233,4 @@ Meanwhile:
 | CI stuck | `bash lib/ci-debug.sh` — check Woodpecker. Rate-limited? (exit 128 = wait 15 min) |
 | Claude not found | `which claude` — must be in PATH. Check `lib/env.sh` adds `~/.local/bin`. |
 | Merge fails | Branch protection misconfigured? Review bot needs write access to the repo. |
-| Memory issues | Factory auto-heals at <500 MB free. Check `factory/factory.log` for P0 alerts. |
+| Memory issues | Supervisor auto-heals at <500 MB free. Check `supervisor/supervisor.log` for P0 alerts. |

README.md

@@ -9,7 +9,7 @@ Point it at a Codeberg repo with a Woodpecker CI pipeline and it will pick up is
 ## Architecture
 
 ```
-cron (*/10) ──→ factory-poll.sh    ← supervisor (bash checks, zero tokens)
+cron (*/10) ──→ supervisor-poll.sh    ← supervisor (bash checks, zero tokens)
                  ├── all clear? → exit 0
                  └── problem? → claude -p (diagnose, fix, or escalate)
 
@@ -33,9 +33,9 @@ all agents ──→ matrix_send()     ← status updates, escalations, merge no
 **Required:**
 
 - [Claude CLI](https://docs.anthropic.com/en/docs/claude-cli) — `claude` in PATH, authenticated
-- [Codeberg](https://codeberg.org/) account with an API token — the factory reads issues, opens PRs, posts comments, and merges via the Codeberg API
+- [Codeberg](https://codeberg.org/) account with an API token — disinto reads issues, opens PRs, posts comments, and merges via the Codeberg API
 - A second Codeberg account for the review bot — reviews posted under a separate identity so the dev-agent doesn't review its own PRs (`REVIEW_BOT_TOKEN`)
-- [Woodpecker CI](https://woodpecker-ci.org/) — local instance connected to your Codeberg repo; the factory monitors pipelines, retries failures, and queries the Woodpecker Postgres DB directly
+- [Woodpecker CI](https://woodpecker-ci.org/) — local instance connected to your Codeberg repo; disinto monitors pipelines, retries failures, and queries the Woodpecker Postgres DB directly
 - PostgreSQL client (`psql`) — for Woodpecker DB queries (pipeline status, build counts)
 - `jq`, `curl`, `git`
 
@@ -84,13 +84,13 @@ CLAUDE_TIMEOUT=7200         # max seconds per Claude invocation (default: 2h)
 # 3. Install cron (staggered to avoid overlap)
 crontab -e
 # Add:
-#   0,10,20,30,40,50 * * * * /path/to/disinto/factory/factory-poll.sh
+#   0,10,20,30,40,50 * * * * /path/to/disinto/supervisor/supervisor-poll.sh
 #   3,13,23,33,43,53 * * * * /path/to/disinto/review/review-poll.sh
 #   6,16,26,36,46,56 * * * * /path/to/disinto/dev/dev-poll.sh
 #   15 8 * * *                /path/to/disinto/gardener/gardener-poll.sh
 
 # 4. Verify
-bash factory/factory-poll.sh   # should log "all clear"
+bash supervisor/supervisor-poll.sh   # should log "all clear"
 ```
 
 ## Directory Structure
@@ -113,8 +113,8 @@ disinto/
 ├── gardener/
 │   ├── gardener-poll.sh  # Cron entry: backlog grooming
 │   └── best-practices.md # Gardener knowledge base
-└── factory/
+└── supervisor/
-    ├── factory-poll.sh   # Supervisor: health checks + claude -p
+    ├── supervisor-poll.sh   # Supervisor: health checks + claude -p
     ├── PROMPT.md         # Supervisor's system prompt
     ├── update-prompt.sh  # Self-learning: append to best-practices
     └── best-practices/   # Progressive disclosure knowledge base
@@ -131,7 +131,7 @@ disinto/
 
 | Agent | Trigger | Job |
 |-------|---------|-----|
-| **Factory** (supervisor) | Every 10 min | Health checks (RAM, disk, CI, git). Calls Claude only when something is broken. Self-improving via `best-practices/`. |
+| **Supervisor** | Every 10 min | Health checks (RAM, disk, CI, git). Calls Claude only when something is broken. Self-improving via `best-practices/`. |
 | **Dev** | Every 10 min | Picks up `backlog`-labeled issues, creates a branch, implements, opens a PR, monitors CI, responds to review, merges. |
 | **Review** | Every 10 min | Finds PRs without review, runs Claude-powered code review, approves or requests changes. |
 | **Gardener** | Daily | Grooms the issue backlog: detects duplicates, promotes `tech-debt` to `backlog`, closes stale issues, escalates ambiguous items. |

dev/dev-agent.sh

@@ -1106,9 +1106,9 @@ while [ "$REVIEW_ROUND" -lt "$MAX_REVIEW_ROUNDS" ]; do
     CI_FIX_COUNT=$(( ${CI_FIX_COUNT:-0} + 1 ))
     if [ "$CI_FIX_COUNT" -gt 2 ]; then
       log "CI failure not recoverable after ${CI_FIX_COUNT} fix attempts"
-      # Escalate to supervisor — write marker for factory-poll.sh to pick up
+      # Escalate to supervisor — write marker for supervisor-poll.sh to pick up
       echo "{\"issue\":${ISSUE},\"pr\":${PR_NUMBER},\"reason\":\"ci_exhausted\",\"step\":\"${FAILED_STEP:-unknown}\",\"attempts\":${CI_FIX_COUNT},\"ts\":\"$(date -u +%Y-%m-%dT%H:%M:%SZ)\"}" \
-        >> "${FACTORY_ROOT}/factory/escalations.jsonl"
+        >> "${FACTORY_ROOT}/supervisor/escalations.jsonl"
       log "escalated to supervisor via escalations.jsonl"
       break
     fi

dev/dev-poll.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# dev-poll.sh — Pull-based factory: find the next ready issue and start dev-agent
+# dev-poll.sh — Pull-based scheduler: find the next ready issue and start dev-agent
 #
 # Pull system: issues labeled "backlog" are candidates. An issue is READY when
 # ALL its dependency issues are closed (and their PRs merged).
@@ -104,7 +104,7 @@ dep_is_merged() {
     return 1
   fi
 
-  # Issue closed = dep satisfied. The factory only closes issues after
+  # Issue closed = dep satisfied. The scheduler only closes issues after
   # merging, so closed state is trustworthy. No need to hunt for the
   # specific PR — that was over-engineering that caused false negatives.
   return 0

lib/matrix_listener.sh

@@ -1,11 +1,11 @@
 #!/usr/bin/env bash
 # matrix_listener.sh — Long-poll Matrix sync daemon
 #
-# Listens for replies in the factory Matrix room and dispatches them
+# Listens for replies in the Matrix coordination room and dispatches them
 # to the appropriate agent via well-known files.
 #
 # Dispatch:
-#   Thread reply to [supervisor] message → /tmp/factory-escalation-reply
+#   Thread reply to [supervisor] message → /tmp/supervisor-escalation-reply
 #   Thread reply to [gardener] message   → /tmp/gardener-escalation-reply
 #
 # Run as systemd service (see matrix_listener.service) or manually:
@@ -18,7 +18,7 @@ source "$(dirname "$0")/../lib/env.sh"
 
 SINCE_FILE="/tmp/matrix-listener-since"
 THREAD_MAP="${MATRIX_THREAD_MAP:-/tmp/matrix-thread-map}"
-LOGFILE="${FACTORY_ROOT}/factory/matrix-listener.log"
+LOGFILE="${FACTORY_ROOT}/supervisor/matrix-listener.log"
 SYNC_TIMEOUT=30000  # 30s long-poll
 BACKOFF=5
 MAX_BACKOFF=60
@@ -133,7 +133,7 @@ while true; do
 
     case "$AGENT" in
       supervisor)
-        printf '%s\t%s\t%s\n' "$(date -u +%Y-%m-%dT%H:%M:%SZ)" "$SENDER" "$BODY" >> /tmp/factory-escalation-reply
+        printf '%s\t%s\t%s\n' "$(date -u +%Y-%m-%dT%H:%M:%SZ)" "$SENDER" "$BODY" >> /tmp/supervisor-escalation-reply
         # Acknowledge
         matrix_send "supervisor" "✓ received, will act on next poll" "$THREAD_ROOT" >/dev/null 2>&1 || true
         ;;

supervisor/PROMPT.md

@@ -1,7 +1,7 @@
-# Factory Supervisor
+# Supervisor Agent
 
-You are the factory supervisor for `$CODEBERG_REPO`. You were called because
+You are the supervisor agent for `$CODEBERG_REPO`. You were called because
-`factory-poll.sh` detected an issue it couldn't auto-fix.
+`supervisor-poll.sh` detected an issue it couldn't auto-fix.
 
 ## Priority Order
 
@@ -16,13 +16,13 @@ You are the factory supervisor for `$CODEBERG_REPO`. You were called because
 Fix the issue yourself. You have full shell access and `--dangerously-skip-permissions`.
 
 Before acting, read the relevant best-practices file:
-- Memory issues → `cat ${FACTORY_ROOT}/factory/best-practices/memory.md`
+- Memory issues → `cat ${FACTORY_ROOT}/supervisor/best-practices/memory.md`
-- Disk issues → `cat ${FACTORY_ROOT}/factory/best-practices/disk.md`
+- Disk issues → `cat ${FACTORY_ROOT}/supervisor/best-practices/disk.md`
-- CI issues → `cat ${FACTORY_ROOT}/factory/best-practices/ci.md`
+- CI issues → `cat ${FACTORY_ROOT}/supervisor/best-practices/ci.md`
-- Codeberg / rate limits → `cat ${FACTORY_ROOT}/factory/best-practices/codeberg.md`
+- Codeberg / rate limits → `cat ${FACTORY_ROOT}/supervisor/best-practices/codeberg.md`
-- Dev-agent issues → `cat ${FACTORY_ROOT}/factory/best-practices/dev-agent.md`
+- Dev-agent issues → `cat ${FACTORY_ROOT}/supervisor/best-practices/dev-agent.md`
-- Review-agent issues → `cat ${FACTORY_ROOT}/factory/best-practices/review-agent.md`
+- Review-agent issues → `cat ${FACTORY_ROOT}/supervisor/best-practices/review-agent.md`
-- Git issues → `cat ${FACTORY_ROOT}/factory/best-practices/git.md`
+- Git issues → `cat ${FACTORY_ROOT}/supervisor/best-practices/git.md`
 
 ## Credentials & API Access
 
@@ -66,6 +66,6 @@ ESCALATE: <what's wrong>
 
 If you discover something new, append it to the relevant best-practices file:
 ```bash
-bash ${FACTORY_ROOT}/factory/update-prompt.sh "best-practices/<file>.md" "### Lesson title
+bash ${FACTORY_ROOT}/supervisor/update-prompt.sh "best-practices/<file>.md" "### Lesson title
 Description of what you learned."
 ```

supervisor/best-practices/codeberg.md

@@ -22,7 +22,7 @@ cd <worktree> && git commit --allow-empty -m "ci: retrigger" --no-verify && git
 ```
 
 ### Prevention
-- The factory runs 3 agents staggered by 3 minutes. During heavy development, many PRs trigger CI simultaneously.
+- The system runs 3 agents staggered by 3 minutes. During heavy development, many PRs trigger CI simultaneously.
 - One pipeline at a time is ideal on this VPS (resource + rate limit reasons).
 - If >3 pipelines are pending/running, do NOT create more work.
 

supervisor/best-practices/dev-agent.md

@@ -44,12 +44,12 @@ DO NOT try to find the specific PR that closed an issue. This is over-engineerin
 - Codeberg shares issue/PR numbering — no guaranteed relationship
 - PRs don't always mention the issue number in title/body
 - Searching last N closed PRs misses older merges
-- The factory itself closes issues after merging, so closed = merged
+- The dev-agent closes issues after merging, so closed = merged
 
 The only check needed: `issue.state == "closed"`.
 
 ### False Positive: Status Unchanged Alert
-The factory-poll alert 'status unchanged for Nmin' is a false positive for complex implementation tasks. The status is set to 'claude assessing + implementing' at the START of the `timeout 7200 claude -p ...` call and only updates after Claude finishes. Normal complex tasks (multi-file Solidity changes + forge test) take 45-90 minutes. To distinguish a false positive from a real stuck agent: check that the claude PID is alive (`ps -p <PID>`), consuming CPU (>0%), and has active threads (`pstree -p <PID>`). If the process is alive and using CPU, do NOT restart it — this wastes completed work.
+The supervisor-poll alert 'status unchanged for Nmin' is a false positive for complex implementation tasks. The status is set to 'claude assessing + implementing' at the START of the `timeout 7200 claude -p ...` call and only updates after Claude finishes. Normal complex tasks (multi-file Solidity changes + forge test) take 45-90 minutes. To distinguish a false positive from a real stuck agent: check that the claude PID is alive (`ps -p <PID>`), consuming CPU (>0%), and has active threads (`pstree -p <PID>`). If the process is alive and using CPU, do NOT restart it — this wastes completed work.
 
 ### False Positive: 'Waiting for CI + Review' Alert
 The 'status unchanged for Nmin' alert is also a false positive when status is 'waiting for CI + review on PR #N (round R)'. This is an intentional sleep/poll loop — the agent is waiting for CI to pass and then for review-poll to post a review. CI can take 20–40 minutes; review follows. Do NOT restart the agent. Confirm by checking: (1) agent PID is alive, (2) CI commit status via `codeberg_api GET /commits/<sha>/status`, (3) review-poll log shows it will pick up the PR on next cycle.

supervisor/best-practices/disk.md

@@ -2,7 +2,7 @@
 
 ## Safe Fixes
 - Docker cleanup: `sudo docker system prune -f` (keeps images, removes stopped containers + dangling layers)
-- Truncate factory logs >5MB: `truncate -s 0 <file>`
+- Truncate supervisor logs >5MB: `truncate -s 0 <file>`
 - Remove stale worktrees: check `/tmp/${PROJECT_NAME}-worktree-*`, only if dev-agent not running on them
 - Woodpecker log_entries: `DELETE FROM log_entries WHERE id < (SELECT max(id) - 100000 FROM log_entries);` then `VACUUM;`
 - Node module caches in worktrees: `rm -rf /tmp/${PROJECT_NAME}-worktree-*/node_modules/`

supervisor/best-practices/git.md

@@ -34,7 +34,7 @@
 
 ## Known Issues
 - Main repo MUST be on $PRIMARY_BRANCH at all times. Dev work happens in worktrees.
-- Stale rebases (detached HEAD) break all worktree creation — silent factory stall.
+- Stale rebases (detached HEAD) break all worktree creation — silent pipeline stall.
 - `git worktree add` fails if target directory exists (even empty). Remove first.
 - Many old branches exist locally (100+). Normal — don't bulk-delete.
 
@@ -47,7 +47,7 @@
 
 ## Lessons Learned
 - NEVER delete remote branches before confirming merge. Close PR, rebase locally, force-push if needed.
-- Stale rebase caused 5h factory stall once (2026-03-11). Auto-heal added to dev-agent.
+- Stale rebase caused 5h pipeline stall once (2026-03-11). Auto-heal added to dev-agent.
 - lint-staged hooks fail when `forge` not in PATH. Use `--no-verify` when committing from scripts.
 
 ### PR #608 Post-Mortem (2026-03-12/13)

supervisor/best-practices/review-agent.md

@@ -19,7 +19,7 @@
 - **Hallucinated findings** — bot may flag non-issues. This needs Clawy's judgment — escalate.
 
 ## Monitoring
-- Unreviewed PRs with CI pass for >1h → factory-poll.sh auto-triggers review
+- Unreviewed PRs with CI pass for >1h → supervisor-poll.sh auto-triggers review
 - Review errors should resolve on next poll cycle
 - If same PR fails review 3+ times → likely a prompt issue, escalate
 

supervisor/supervisor-poll.sh

@@ -1,20 +1,20 @@
 #!/usr/bin/env bash
-# factory-poll.sh — Factory supervisor: bash checks + claude -p for fixes
+# supervisor-poll.sh — Supervisor agent: bash checks + claude -p for fixes
 #
 # Runs every 10min via cron. Does all health checks in bash (zero tokens).
 # Only invokes claude -p when auto-fix fails or issue is complex.
 #
-# Cron: */10 * * * * /path/to/disinto/factory/factory-poll.sh
+# Cron: */10 * * * * /path/to/disinto/supervisor/supervisor-poll.sh
 #
-# Peek:  cat /tmp/factory-status
+# Peek:  cat /tmp/supervisor-status
-# Log:   tail -f /path/to/disinto/factory/factory.log
+# Log:   tail -f /path/to/disinto/supervisor/supervisor.log
 
 source "$(dirname "$0")/../lib/env.sh"
 
-LOGFILE="${FACTORY_ROOT}/factory/factory.log"
+LOGFILE="${FACTORY_ROOT}/supervisor/supervisor.log"
-STATUSFILE="/tmp/factory-status"
+STATUSFILE="/tmp/supervisor-status"
-LOCKFILE="/tmp/factory-poll.lock"
+LOCKFILE="/tmp/supervisor-poll.lock"
-PROMPT_FILE="${FACTORY_ROOT}/factory/PROMPT.md"
+PROMPT_FILE="${FACTORY_ROOT}/supervisor/PROMPT.md"
 
 # Prevent overlapping runs
 if [ -f "$LOCKFILE" ]; then
@@ -32,15 +32,15 @@ flog() {
 }
 
 status() {
-  printf '[%s] factory: %s\n' "$(date -u '+%Y-%m-%d %H:%M:%S UTC')" "$*" > "$STATUSFILE"
+  printf '[%s] supervisor: %s\n' "$(date -u '+%Y-%m-%d %H:%M:%S UTC')" "$*" > "$STATUSFILE"
   flog "$*"
 }
 
 # ── Check for escalation replies from Matrix ──────────────────────────────
 ESCALATION_REPLY=""
-if [ -s /tmp/factory-escalation-reply ]; then
+if [ -s /tmp/supervisor-escalation-reply ]; then
-  ESCALATION_REPLY=$(cat /tmp/factory-escalation-reply)
+  ESCALATION_REPLY=$(cat /tmp/supervisor-escalation-reply)
-  rm -f /tmp/factory-escalation-reply
+  rm -f /tmp/supervisor-escalation-reply
   flog "Got escalation reply: $(echo "$ESCALATION_REPLY" | head -1)"
 fi
 
@@ -71,7 +71,7 @@ SWAP_USED_MB=$(free -m | awk '/Swap:/{print $3}')
 if [ "${AVAIL_MB:-9999}" -lt 500 ] || { [ "${SWAP_USED_MB:-0}" -gt 3000 ] && [ "${AVAIL_MB:-9999}" -lt 2000 ]; }; then
   flog "MEMORY CRISIS: avail=${AVAIL_MB}MB swap_used=${SWAP_USED_MB}MB — auto-fixing"
 
-  # Kill stale factory-spawned claude processes (>3h old) — skip interactive sessions
+  # Kill stale agent-spawned claude processes (>3h old) — skip interactive sessions
   STALE_CLAUDES=$(pgrep -f "claude -p" --older 10800 2>/dev/null || true)
   if [ -n "$STALE_CLAUDES" ]; then
     echo "$STALE_CLAUDES" | xargs kill 2>/dev/null || true
@@ -113,7 +113,7 @@ if [ "${DISK_PERCENT:-0}" -gt 80 ]; then
   # Docker cleanup (safe — keeps images)
   sudo docker system prune -f >/dev/null 2>&1 && fixed "Docker prune"
 
-  # Truncate factory logs >10MB
+  # Truncate supervisor logs >10MB
   for logfile in "${FACTORY_ROOT}"/{dev,review,factory}/*.log; do
     if [ -f "$logfile" ]; then
       SIZE_KB=$(du -k "$logfile" 2>/dev/null | cut -f1)
@@ -159,7 +159,7 @@ fi
 # =============================================================================
 # P2: FACTORY STOPPED — CI, dev-agent, git
 # =============================================================================
-status "P2: checking factory"
+status "P2: checking pipeline"
 
 # CI stuck
 STUCK_CI=$(wpdb -c "SELECT count(*) FROM pipelines WHERE repo_id=${WOODPECKER_REPO_ID} AND status='running' AND EXTRACT(EPOCH FROM now() - to_timestamp(started)) > 1200;" 2>/dev/null | xargs || true)
@@ -204,7 +204,7 @@ fi
 # =============================================================================
 # P2b: FACTORY STALLED — backlog exists but no agent running
 # =============================================================================
-status "P2: checking factory stall"
+status "P2: checking pipeline stall"
 
 BACKLOG_COUNT=$(codeberg_api GET "/issues?state=open&labels=backlog&type=issues&limit=1" 2>/dev/null | jq -r 'length' 2>/dev/null || echo "0")
 IN_PROGRESS=$(codeberg_api GET "/issues?state=open&labels=in-progress&type=issues&limit=1" 2>/dev/null | jq -r 'length' 2>/dev/null || echo "0")
@@ -221,7 +221,7 @@ if [ "${BACKLOG_COUNT:-0}" -gt 0 ] && [ "${IN_PROGRESS:-0}" -eq 0 ]; then
   IDLE_MIN=$(( (NOW_EPOCH - LAST_LOG_EPOCH) / 60 ))
 
   if [ "$IDLE_MIN" -gt 20 ]; then
-    p2 "Factory stalled: ${BACKLOG_COUNT} backlog issue(s), no agent ran for ${IDLE_MIN}min"
+    p2 "Pipeline stalled: ${BACKLOG_COUNT} backlog issue(s), no agent ran for ${IDLE_MIN}min"
   fi
 fi
 
@@ -277,7 +277,7 @@ done
 # P4: HOUSEKEEPING — stale processes
 # =============================================================================
 # Check for dev-agent escalations
-ESCALATION_FILE="${FACTORY_ROOT}/factory/escalations.jsonl"
+ESCALATION_FILE="${FACTORY_ROOT}/supervisor/escalations.jsonl"
 if [ -s "$ESCALATION_FILE" ]; then
   ESCALATION_COUNT=$(wc -l < "$ESCALATION_FILE")
   p3 "Dev-agent escalated ${ESCALATION_COUNT} issue(s) — see ${ESCALATION_FILE}"
@@ -285,7 +285,7 @@ fi
 
 status "P4: housekeeping"
 
-# Stale factory-spawned claude processes (>3h, not caught by P0) — skip interactive sessions
+# Stale agent-spawned claude processes (>3h, not caught by P0) — skip interactive sessions
 STALE_CLAUDES=$(pgrep -f "claude -p" --older 10800 2>/dev/null || true)
 if [ -n "$STALE_CLAUDES" ]; then
   echo "$STALE_CLAUDES" | xargs kill 2>/dev/null || true
@@ -308,7 +308,7 @@ for wt in /tmp/${PROJECT_NAME}-worktree-* /tmp/${PROJECT_NAME}-review-*; do
 done
 git -C "$PROJECT_REPO_ROOT" worktree prune 2>/dev/null || true
 
-# Rotate factory log if >5MB
+# Rotate supervisor log if >5MB
 for logfile in "${FACTORY_ROOT}"/{dev,review,factory}/*.log; do
   if [ -f "$logfile" ]; then
     SIZE_KB=$(du -k "$logfile" 2>/dev/null | cut -f1)
@@ -329,12 +329,12 @@ if [ -n "$ALL_ALERTS" ]; then
   ALERT_TEXT=$(echo -e "$ALL_ALERTS")
 
   # Notify Matrix
-  matrix_send "supervisor" "⚠️ Factory alerts:
+  matrix_send "supervisor" "⚠️ Supervisor alerts:
 ${ALERT_TEXT}" 2>/dev/null || true
 
   flog "Invoking claude -p for alerts"
 
-  CLAUDE_PROMPT="$(cat "$PROMPT_FILE" 2>/dev/null || echo "You are a factory supervisor. Fix the issue below.")
+  CLAUDE_PROMPT="$(cat "$PROMPT_FILE" 2>/dev/null || echo "You are a supervisor agent. Fix the issue below.")
 
 ## Current Alerts
 ${ALERT_TEXT}

supervisor/update-prompt.sh

@@ -2,15 +2,15 @@
 # update-prompt.sh — Append a lesson to a best-practices file
 #
 # Usage:
-#   ./factory/update-prompt.sh "best-practices/memory.md" "### Title\nBody text"
+#   ./supervisor/update-prompt.sh "best-practices/memory.md" "### Title\nBody text"
-#   ./factory/update-prompt.sh --from-file "best-practices/memory.md" /tmp/lesson.md
+#   ./supervisor/update-prompt.sh --from-file "best-practices/memory.md" /tmp/lesson.md
 #
 # Called by claude -p when it learns something during a fix.
 # Commits and pushes the update to the disinto repo.
 
 source "$(dirname "$0")/../lib/env.sh"
 
-TARGET_FILE="${FACTORY_ROOT}/factory/$1"
+TARGET_FILE="${FACTORY_ROOT}/supervisor/$1"
 shift
 
 if [ "$1" = "--from-file" ] && [ -f "$2" ]; then
@@ -40,8 +40,8 @@ else
 fi
 
 cd "$FACTORY_ROOT"
-git add "factory/$1" 2>/dev/null || git add "$TARGET_FILE"
+git add "supervisor/$1" 2>/dev/null || git add "$TARGET_FILE"
-git commit -m "factory: learned — $(echo "$LESSON" | head -1 | sed 's/^#* *//')" --no-verify 2>/dev/null
+git commit -m "supervisor: learned — $(echo "$LESSON" | head -1 | sed 's/^#* *//')" --no-verify 2>/dev/null
 git push origin main 2>/dev/null
 
 log "Updated $(basename "$TARGET_FILE") with new lesson"