feat(reset): multi-agent-mux-reset skill - reset.sh, SKILL.md, packaging (#78)

.agents/skills/lib_py/reset.py

@@ -13,6 +13,8 @@ import datetime
 import json
 import os
 import shlex
+import shutil
+import sqlite3
 import subprocess
 import sys
 import tempfile
@@ -38,8 +40,50 @@ def spec_path(workspace: str) -> str:
     return os.path.join(_real(workspace), SPEC_REL)
 
 
-def _state() -> dict:
-    return json.loads(os.environ.get("MAM_STATE_JSON") or "{}") or {}
+def _state(workspace: str = "") -> dict:
+    raw = os.environ.get("MAM_STATE_JSON")
+    if raw is not None:
+        return json.loads(raw or "{}") or {}
+    yaml_path = os.environ.get("AGENT_SESSIONS_YAML") or (
+        os.path.join(_real(workspace), ".mam", "agent-sessions.yaml") if workspace else ""
+    )
+    if not yaml_path:
+        return {}
+    db_path = os.path.splitext(yaml_path)[0] + ".db"
+    if os.path.exists(db_path):
+        tmp_dir = tempfile.mkdtemp(prefix="mam-reset-ro.")
+        try:
+            tmp_db = os.path.join(tmp_dir, "agent-sessions.db")
+            shutil.copyfile(db_path, tmp_db)
+            for suf in ("-wal", "-shm"):
+                if os.path.exists(db_path + suf):
+                    shutil.copyfile(db_path + suf, tmp_db + suf)
+            conn = sqlite3.connect(tmp_db, timeout=60.0)
+            try:
+                d: dict = {}
+                row = conn.execute("SELECT data FROM state WHERE id=1").fetchone()
+                if row:
+                    d = json.loads(row[0])
+                cursor = conn.execute("SELECT data FROM sessions")
+                d["herdr_sessions"] = [json.loads(r[0]) for r in cursor.fetchall()]
+                return d
+            finally:
+                conn.close()
+        except Exception as exc:
+            raise ValueError("the registry %s cannot be read (%s); fix it first" % (yaml_path, exc))
+        finally:
+            shutil.rmtree(tmp_dir, ignore_errors=True)
+    if os.path.exists(yaml_path):
+        try:
+            import yaml
+            with open(yaml_path, encoding="utf-8") as fh:
+                data = yaml.safe_load(fh)
+            if data is not None and not isinstance(data, dict):
+                raise ValueError("top-level YAML is not a mapping")
+            return data or {}
+        except Exception as exc:
+            raise ValueError("the registry %s cannot be read (%s); fix it first" % (yaml_path, exc))
+    return {}
 
 
 # --------------------------------------------------------------------------- D2: target selection
@@ -638,8 +682,13 @@ def main(argv: Optional[List[str]] = None) -> int:
         return 0
 
     try:
-        state = _state()
+        state = _state(ws)
     except ValueError as exc:
+        if a.cmd == "dry-run":
+            refs = list(a.refusal or []) + [str(exc)]
+            out, rc = format_dry_run(ws, {}, os.environ, extra_refusals=refs)
+            print(out)
+            return rc
         if a.cmd == "precheck":
             print("registry: cannot parse MAM_STATE_JSON (%s)" % exc)
             return 1

.agents/skills/multi-agent-mux-reset/SKILL.md

@@ -0,0 +1,48 @@
+---
+name: multi-agent-mux-reset
+description: "Purge the control root's running resident agents and recreate each with the same name, agent, role, herdr server and workspace label, one at a time, with onboarding. Persists .mam/reset-spec.json before the first purge so an interrupted or skipped run resumes where it left off."
+version: 4.12.0
+author: godopu
+license: MIT
+platforms: [linux, macos]
+environments: [terminal, herdr]
+metadata:
+  hermes:
+    tags: [reset, purge, recreate, lifecycle, onboarding]
+    related_skills: [multi-agent-mux-stop, multi-agent-mux-create, multi-agent-mux-status]
+---
+
+# Multi-Agent Reset
+
+```bash
+bash .agents/skills/multi-agent-mux-reset/scripts/reset.sh --yes [--dry-run]
+```
+
+| Item | Behaviour |
+|---|---|
+| Targets | Every registry row with `status: running` and `realpath(pane.cwd) == realpath(WS)`. Worktree rows, `stopped`/`terminated` rows, and `orchestrator_uuids` are skipped and listed with their reason. |
+| Confirmation | `[y/N]` prompt; without a terminal `-y`/`--yes` is required (exits `3` otherwise). `--dry-run` inspects without `--yes` and changes nothing. |
+| Prechecks | Refuses before any change when an open job exists (prints the `registry.py ... close --request cancelled` command), when `.mam/loop-guard-active` or `.mam/update-in-progress` is held, when a target row lacks a valid agent or role, or when the caller itself is one of the targets. |
+| Lock & concurrency | Takes update admission (`mam_update_admit`), acquires `.mam/loop-guard-active` (`mam_acquire_loop_lock`), then releases update admission so `run_loop.sh`, `update.sh`, and concurrent resets refuse while the reset runs. |
+| Spec file & rerun | Writes `.mam/reset-spec.json` atomically before the first stop/purge and removes it only when all targets reach `done`. Rerunning resumes from the spec file without re-purging already recreated agents (`created` or `done`). |
+| Sequence per target | Sequential (never parallel): ① normal `stop_session.sh --reason reset` (captures verified ID onto the row while herdr is live and sets `status: stopped`), ② checks that the row has a recorded conversation ID, ③ `stop_session.sh --reason reset --purge-conversation --yes` (using the row's recorded ID, never a CLI UUID), then `create_session.sh` with the original name, agent, role, `--herdr-session`, and `--herdr-workspace` (onboarding enabled by default). |
+| When skipped (exit 4) | If step ② finds no recorded ID or step ③ exits `4` (in-use gate), the target is skipped and the reset continues to the next agent: the skipped agent is stopped but resumable (its row keeps its id) and its conversation files are untouched; rerun once its holders end, or resume it. |
+
+| Exit | Meaning |
+|---|---|
+| 0 | All targeted agents reached `done` and `.mam/reset-spec.json` was removed; or nothing to reset, cancelled at prompt, or `--dry-run` with no blockers |
+| 1 | Refused by precheck (nothing changed), corrupt/mismatched `.mam/reset-spec.json`, or a `stop`/`create` step failed (`.mam/reset-spec.json` is kept so rerunning resumes) |
+| 2 | Invalid arguments |
+| 3 | Not a terminal and `-y`/`--yes` was not passed; nothing was changed |
+| 4 | Completed the pass, but one or more agents were skipped (purge refused with stop exit 4, or no conversation ID recorded); `.mam/reset-spec.json` is kept for rerun |
+| 5 | No agent was skipped or failed, but one or more newly created post-discovered agents do not have their new conversation ID recorded yet; `.mam/reset-spec.json` is kept so rerunning re-checks without re-purging |
+| other | Under `set -e`, an unexpected sub-step failure passes its nonzero exit code through |
+
+## Safety Notes
+
+- **Irreversible**: purged conversations cannot be recovered. Confirm with `--dry-run` first.
+- **No external process termination**: processes holding conversation files open (reported via `lsof` in `in_use_hints`) are never signalled by MAM; end them yourself when safe, then rerun.
+- **Shared stores preserved**: Grok's shared `memory-v2.db` is left intact during purge; only session rows and per-session files are removed.
+- **Orchestrator hook during reset**: while `.mam/loop-guard-active` is held by the reset, the AGY orchestrator's direct file-edit hook (`loop_delegation_guard.sh`) blocks direct edits until the reset finishes.
+- **Post-precheck job submissions**: `multi-agent-mux-delegate-job submit` does not check `.mam/loop-guard-active`; do not submit new jobs to resident agents while a reset is running.
+- **Same-type post-discovered ordering**: when resetting multiple post-discovered agents of the same type, the second `create_session.sh` waits up to `MAM_ID_ORDER_WAIT_S` for the first agent's ID to be recorded; if it times out, rerun the reset once the ID is recorded.

.agents/skills/multi-agent-mux-reset/scripts/reset.sh

@@ -0,0 +1,272 @@
+#!/usr/bin/env bash
+# reset.sh — multi-agent-mux-reset (Issue #78): purge the control root's
+# running resident agents and recreate each with the same name, agent, role,
+# herdr server and workspace label, one at a time, with onboarding.
+# Usage:
+#   bash .agents/skills/multi-agent-mux-reset/scripts/reset.sh [-y|--yes] [--dry-run]
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+SKILL_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
+WS="$(cd -P "$SCRIPT_DIR/../../../.." && pwd -P)"
+export WORKSPACE_ROOT="$WS"
+export AGENT_SESSIONS_YAML="${AGENT_SESSIONS_YAML:-$WS/.mam/agent-sessions.yaml}"
+export PYTHONPATH="$SKILL_DIR:${PYTHONPATH:-}"
+
+usage() {
+  cat <<'USAGE'
+Usage: bash .agents/skills/multi-agent-mux-reset/scripts/reset.sh [-y|--yes] [--dry-run]
+
+Options:
+  -y, --yes    Confirm purging and recreating the control root's running agents
+  --dry-run    Inspect targets, skipped rows, spec progress and blockers without changing anything
+  -h, --help   Show this help
+USAGE
+}
+
+YES=0
+DRY_RUN=0
+while [ $# -gt 0 ]; do
+  case "$1" in
+    -y|--yes) YES=1; shift ;;
+    --dry-run) DRY_RUN=1; shift ;;
+    -h|--help) usage; exit 0 ;;
+    *) echo "ERROR: unknown arg: $1" >&2; usage >&2; exit 2 ;;
+  esac
+done
+
+if [ "$DRY_RUN" != "1" ] && [ "$YES" != "1" ] && [ ! -t 0 ]; then
+  echo "ERROR: not a terminal; run with -y/--yes (or --dry-run to inspect)" >&2
+  exit 3
+fi
+
+MAM="$WS/.mam"
+MARKER="${MAM_LOOP_MARKER:-$MAM/loop-guard-active}"
+SPEC_FILE="$MAM/reset-spec.json"
+
+# shellcheck disable=SC1091
+source "$SKILL_DIR/multi-agent-mux-loop/scripts/loop_lock.sh"
+
+if [ "$DRY_RUN" = "1" ]; then
+  if [ -x "$WS/.venv/bin/python" ]; then
+    PY="$WS/.venv/bin/python"
+  elif command -v python3 >/dev/null 2>&1; then
+    PY="python3"
+  else
+    PY="python"
+  fi
+  DRY_ARGS=()
+  if [ -f "$MAM/update-in-progress" ]; then
+    upd_st="$(_mam_lock_holder_state "$MAM/update-in-progress")"
+    case "$upd_st" in
+      stale) echo "NOTE: stale update marker $MAM/update-in-progress (its update is gone); not a reason to refuse" ;;
+      *) DRY_ARGS+=(--refusal "an update of $WS is in progress (pid $(_mam_lock_field "$MAM/update-in-progress" pid), holder $upd_st); wait for it to finish") ;;
+    esac
+  fi
+  if [ -f "$MARKER" ]; then
+    loop_st="$(_mam_lock_holder_state "$MARKER")"
+    case "$loop_st" in
+      stale) echo "NOTE: stale loop marker $MARKER (its loop is gone); not a reason to refuse" ;;
+      *) DRY_ARGS+=(--refusal "a review loop or another reset is running (pid $(_mam_lock_field "$MARKER" pid), holder $loop_st); wait for it to end") ;;
+    esac
+  fi
+  dry_rc=0
+  "$PY" -m lib_py.reset dry-run --workspace "$WS" ${DRY_ARGS[@]+"${DRY_ARGS[@]}"} || dry_rc=$?
+  if [ "$dry_rc" -eq 0 ]; then
+    exit 0
+  fi
+  exit 1
+fi
+
+# shellcheck disable=SC1091
+source "$WS/.agents/skills/lib.sh"
+PY="$(_delegate_py_bin)"
+
+mam_update_admit "$WS" || exit 1
+_acquire_rc=0
+mam_acquire_loop_lock "$MARKER" || _acquire_rc=$?
+case "$_acquire_rc" in
+  0) ;;
+  3)
+    mam_update_admit_release
+    _holder_pid="$(_mam_lock_field "$MARKER" "pid" 2>/dev/null || echo "unknown")"
+    echo "ERROR: reset refused; nothing was changed:" >&2
+    echo "  - a review loop or another reset is running (pid $_holder_pid); wait for it to end" >&2
+    exit 1
+    ;;
+  *)
+    mam_update_admit_release
+    echo "ERROR: reset refused; nothing was changed:" >&2
+    echo "  - cannot determine whether a review loop or another reset is running (ps unavailable?)" >&2
+    exit 1
+    ;;
+esac
+_release_reset_lock() {
+  mam_release_loop_lock "$MARKER" || true
+}
+trap _release_reset_lock EXIT INT TERM HUP
+mam_update_admit_release
+
+STATE_JSON=""
+if ! STATE_JSON="$(load_state_json strict)"; then
+  echo "ERROR: reset refused; nothing was changed:" >&2
+  echo "  - the registry $AGENT_SESSIONS_YAML cannot be read; fix it first" >&2
+  exit 1
+fi
+
+pre_out=""
+pre_rc=0
+pre_out="$(MAM_STATE_JSON="$STATE_JSON" "$PY" -m lib_py.reset precheck --workspace "$WS")" || pre_rc=$?
+if [ "$pre_rc" -ne 0 ]; then
+  echo "ERROR: reset refused; nothing was changed:" >&2
+  while IFS= read -r line; do
+    [ -n "$line" ] && echo "  - $line" >&2
+  done <<< "${pre_out:-lib_py.reset precheck failed (rc $pre_rc)}"
+  exit 1
+fi
+
+if [ -f "$SPEC_FILE" ]; then
+  MAM_STATE_JSON="$STATE_JSON" "$PY" -m lib_py.reset dry-run --workspace "$WS" || exit 1
+  if [ "$YES" != "1" ]; then
+    ans=""
+    read -r -p "Resume reset from $SPEC_FILE? [y/N]: " ans || ans=""
+    case "$ans" in
+      y|Y|yes|Yes|YES) ;;
+      *) echo "Reset cancelled; nothing was changed"; exit 0 ;;
+    esac
+  fi
+else
+  PLAN_JSON="$(MAM_STATE_JSON="$STATE_JSON" "$PY" -m lib_py.reset plan --workspace "$WS")" || exit 1
+  TARGET_COUNT="$(printf '%s' "$PLAN_JSON" | "$PY" -c 'import json,sys; print(len(json.load(sys.stdin).get("targets", [])))')"
+  MAM_STATE_JSON="$STATE_JSON" "$PY" -m lib_py.reset dry-run --workspace "$WS" || exit 1
+  if [ "$TARGET_COUNT" = "0" ]; then
+    echo "nothing to reset"
+    exit 0
+  fi
+  if [ "$YES" != "1" ]; then
+    ans=""
+    read -r -p "Purge and recreate $TARGET_COUNT agents? [y/N]: " ans || ans=""
+    case "$ans" in
+      y|Y|yes|Yes|YES) ;;
+      *) echo "Reset cancelled; nothing was changed"; exit 0 ;;
+    esac
+  fi
+  printf '%s' "$PLAN_JSON" | "$PY" -m lib_py.reset write-spec --workspace "$WS" || exit 1
+fi
+
+ENTRIES_OUT="$(MAM_STATE_JSON="$STATE_JSON" "$PY" -m lib_py.reset entries --workspace "$WS" --warn-new)" || exit 1
+ENTRY_NAMES=()
+while IFS= read -r line; do
+  [ -n "$line" ] || continue
+  eval "$line"
+  ENTRY_NAMES+=("$R_NAME")
+done <<< "$ENTRIES_OUT"
+
+SKIPPED_ARGS=()
+FAILED_SPEC=""
+
+for target_name in ${ENTRY_NAMES[@]+"${ENTRY_NAMES[@]}"}; do
+  if ! STATE_JSON="$(load_state_json strict)"; then
+    FAILED_SPEC="$target_name:stop:1"
+    break
+  fi
+  entry_line="$(MAM_STATE_JSON="$STATE_JSON" "$PY" -m lib_py.reset entries --workspace "$WS" --session "$target_name")" || {
+    FAILED_SPEC="$target_name:stop:1"
+    break
+  }
+  eval "$entry_line"
+
+  case "$R_STATE" in
+    done|created)
+      continue
+      ;;
+    pending)
+      STOP_CMD=(bash "$SKILL_DIR/multi-agent-mux-stop/scripts/stop_session.sh" --session "$R_NAME" --agent "$R_AGENT")
+      if [ -n "$R_SERVER" ]; then
+        STOP_CMD+=(--herdr-session "$R_SERVER")
+      fi
+      STOP_CMD+=(--reason reset)
+
+      echo "reset [$R_NAME]: ${STOP_CMD[*]}"
+      stop_rc=0
+      "${STOP_CMD[@]}" || stop_rc=$?
+      if [ "$stop_rc" -ne 0 ]; then
+        FAILED_SPEC="$R_NAME:stop:$stop_rc"
+        break
+      fi
+
+      if ! STATE_JSON="$(load_state_json strict)"; then
+        FAILED_SPEC="$R_NAME:stop:1"
+        break
+      fi
+      entry_line="$(MAM_STATE_JSON="$STATE_JSON" "$PY" -m lib_py.reset entries --workspace "$WS" --session "$R_NAME")" || {
+        FAILED_SPEC="$R_NAME:stop:1"
+        break
+      }
+      eval "$entry_line"
+      if [ -z "$R_ROW_ID" ]; then
+        echo "skipped $R_NAME: no conversation id is recorded, so a purge would drop the row and leave the conversation on disk; resume it, or purge it by hand (stop_session.sh --session $R_NAME --purge-conversation --yes) and rerun the reset to recreate it"
+        SKIPPED_ARGS+=(--skipped "$R_NAME:no_id")
+        continue
+      fi
+
+      echo "reset [$R_NAME]: ${STOP_CMD[*]} --purge-conversation --yes"
+      purge_rc=0
+      "${STOP_CMD[@]}" --purge-conversation --yes || purge_rc=$?
+      if [ "$purge_rc" -eq 4 ]; then
+        echo "skipped $R_NAME: its purge was refused (stop exit 4); the row (now stopped, id recorded) and the conversation are kept; the processes above hold it - they are not killed; rerun the reset once they end"
+        SKIPPED_ARGS+=(--skipped "$R_NAME:purge_refused")
+        continue
+      fi
+      if [ "$purge_rc" -ne 0 ]; then
+        FAILED_SPEC="$R_NAME:stop:$purge_rc"
+        break
+      fi
+      R_STATE="purged"
+      ;;
+  esac
+
+  if [ "$R_STATE" = "purged" ]; then
+    CREATE_CMD=(bash "$SKILL_DIR/multi-agent-mux-create/scripts/create_session.sh" --workspace "$WS" --agent "$R_AGENT" --role "$R_ROLE" --session "$R_NAME")
+    if [ -n "$R_SERVER" ]; then
+      CREATE_CMD+=(--herdr-session "$R_SERVER")
+    fi
+    if [ -n "$R_LABEL" ]; then
+      CREATE_CMD+=(--herdr-workspace "$R_LABEL")
+    fi
+
+    echo "reset [$R_NAME]: ${CREATE_CMD[*]}"
+    create_rc=0
+    "${CREATE_CMD[@]}" || create_rc=$?
+    if [ "$create_rc" -ne 0 ]; then
+      FAILED_SPEC="$R_NAME:create:$create_rc"
+      break
+    fi
+  fi
+done
+
+STATE_JSON="$(load_state_json strict)" || exit 1
+TABLE_ARGS=(--workspace "$WS")
+if [ ${#SKIPPED_ARGS[@]} -gt 0 ]; then
+  TABLE_ARGS+=("${SKIPPED_ARGS[@]}")
+fi
+if [ -n "$FAILED_SPEC" ]; then
+  TABLE_ARGS+=(--failed "$FAILED_SPEC")
+fi
+table_rc=0
+MAM_STATE_JSON="$STATE_JSON" "$PY" -m lib_py.reset table "${TABLE_ARGS[@]}" || table_rc=$?
+case "$table_rc" in
+  0)
+    rm -f "$SPEC_FILE"
+    exit 0
+    ;;
+  4)
+    exit 4
+    ;;
+  5)
+    exit 5
+    ;;
+  *)
+    exit 1
+    ;;
+esac