fix(issue-10,11,13,15): complete agy purge, orchestrator purge, workspace-anchored registry

Issue #10 - agy purge_artifacts left resumable pieces behind: it now also
removes the SQLite sidecars (-wal/-shm/-journal), the title annotation and
the presence lock (the lock only once no live process references the
conversation), and residual_artifacts() reports anything under
~/.gemini/antigravity-cli still carrying the uuid.

Issue #13 - the orchestrator has no herdr_sessions row, so its conversation
could not be purged by any skill. `lib_py.agents purge <agent|auto> <uuid>`
resolves the adapter from what is on disk (orchestrator_uuids stores bare
uuids), refuses while a live process names the uuid (conversation_in_use:
process list minus the caller's own lineage, plus lsof), and prints what it
purged. `orc_onboard.sh --remove <uuid> --purge-conversation --yes [--agent]`
runs it before the registry update so a refusal changes nothing (exit 4
without --yes, 5 while in use).

Issue #11 - "Successfully removeed": conjugate add/remove explicitly.

Issue #15 - the job registry and audit log followed the caller's cwd, so the
pytest suite (create_session.sh with its default onboarding job, run from the
repo root) had left 593 test records in the real .mam/jobs. Defaults now
resolve MAM_JOBS_DIR / DELEGATE_JOB_LOGS_DIR, then $WORKSPACE_ROOT/.mam/...,
then the cwd (mqtt_common.default_registry_dir / get_logs_dir; registry.py,
publish_event.py, service.py, create_session.sh, stop_session.sh); the
sandbox fixture pins both. The tier suites that used to leak now leave the
real registry untouched (881 records before and after).

Tests: test_issue10_13_purge.py (13), test_issue15_registry_isolation.py (7);
T-O13 pins the corrected message; the R1 helper test and B-9 logs-dir test
now assert the workspace-anchored contract; publish_event snapshot updated.

Refs #10 #11 #13 #15

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff

.agents/skills/lib_py/agents/__main__.py

@@ -1,11 +1,48 @@
 # __main__.py — CLI bridge for lib_py.agents facts and resolution (N4)
 
-import sys, json, shlex
+import os, sys, json, shlex
 from lib_py.agents.registry import get_adapter, own_key, agent_of_row
 
+# `purge auto` probes adapters in this order; opencode last because its
+# artifact path is one shared DB that exists for every uuid.
+PURGE_PROBE_ORDER = ('agy', 'claude', 'hermes', 'grok', 'codex', 'opencode')
+
+
+def _resolve_purge_target(agent_hint: str, uuid: str, workspace: str):
+    """(agent, adapter, ctx) whose on-disk artifact carries `uuid`, else None.
+
+    An explicit agent is trusted as long as its artifact exists. `auto` tries
+    each adapter's own verification first (revalidate mode: an orchestrator
+    conversation is not in any workspace cache), then a plain path check for
+    adapters whose artifact path embeds the uuid.
+    """
+    from lib_py.agents.base import DiscoveryContext
+    names = [agent_hint] if agent_hint and agent_hint != 'auto' else list(PURGE_PROBE_ORDER)
+    probes = []
+    for name in names:
+        adapter = get_adapter(name)
+        if not adapter:
+            continue
+        probes.append((name, adapter, DiscoveryContext(workspace, name, mode="revalidate")))
+    for name, adapter, ctx in probes:
+        try:
+            if adapter.verify_artifact(uuid, ctx):
+                return name, adapter, ctx
+        except Exception:
+            pass
+    for name, adapter, ctx in probes:
+        try:
+            path = adapter.artifact_path(uuid, ctx)
+        except Exception:
+            continue
+        if uuid in path and os.path.exists(path):
+            return name, adapter, ctx
+    return None
+
+
 def main():
     if len(sys.argv) < 2:
-        print("Usage: python -m lib_py.agents <facts|resolve> [args...]", file=sys.stderr)
+        print("Usage: python -m lib_py.agents <facts|resolve|purge> [args...]", file=sys.stderr)
         sys.exit(1)
 
     cmd = sys.argv[1]
@@ -83,6 +120,31 @@ def main():
         print('/exit')
         sys.exit(0)
 
+    elif cmd == 'purge':
+        # purge <agent|auto> <uuid> [workspace]  (Issue #13)
+        # Deletes a conversation's on-disk artifacts through its adapter and
+        # prints one JSON object: {"agent", "purged", "residual", "in_use"}.
+        # Exit 0 purged; 4 refused, conversation still in use (nothing
+        # removed); 5 no adapter has an artifact for this uuid.
+        agent_hint = sys.argv[2] if len(sys.argv) > 2 else 'auto'
+        uuid = sys.argv[3] if len(sys.argv) > 3 else ''
+        workspace = sys.argv[4] if len(sys.argv) > 4 and sys.argv[4] else os.getcwd()
+        if not uuid:
+            print("ERROR: purge requires <agent|auto> <uuid>", file=sys.stderr)
+            sys.exit(1)
+        target = _resolve_purge_target(agent_hint, uuid, workspace)
+        if not target:
+            print(json.dumps({"agent": None, "purged": [], "residual": [], "in_use": False}))
+            sys.exit(5)
+        name, adapter, ctx = target
+        if adapter.conversation_in_use(uuid, ctx):
+            print(json.dumps({"agent": name, "purged": [], "residual": [], "in_use": True}))
+            sys.exit(4)
+        purged = adapter.purge_artifacts(uuid, ctx)
+        residual = adapter.residual_artifacts(uuid, ctx)
+        print(json.dumps({"agent": name, "purged": purged, "residual": residual, "in_use": False}))
+        sys.exit(0)
+
     else:
         print(f"ERROR: Unknown CLI command {cmd!r}", file=sys.stderr)
         sys.exit(1)

.agents/skills/lib_py/agents/adapters/agy.py

@@ -1,4 +1,4 @@
-import os, json, sqlite3, shutil
+import os, sys, json, sqlite3, shutil
 from typing import Optional, Any
 from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext
 
@@ -71,18 +71,55 @@ class AgyAgentAdapter(BaseAgentAdapter):
             return False
         return True
 
+    def _cli_root(self, ctx: DiscoveryContext) -> str:
+        return f"{ctx.home_dir}/.gemini/antigravity-cli"
+
     def purge_artifacts(self, uuid: str, ctx: DiscoveryContext) -> list:
+        # Issue #10: a purge must leave nothing resumable behind. Besides the
+        # conversation DB and the brain dir, agy keeps SQLite sidecars (-wal /
+        # -shm / -journal, created whenever the DB is opened - the stop path
+        # itself does so while capturing the id, and an unflushed WAL can still
+        # hold conversation content), the title annotation and a presence lock.
         purged = []
         db = self.artifact_path(uuid, ctx)
-        if os.path.exists(db):
-            os.remove(db)
-            purged.append(db)
-        brain = f"{ctx.home_dir}/.gemini/antigravity-cli/brain/{uuid}"
+        for path in [db] + [f"{db}{suffix}" for suffix in ("-wal", "-shm", "-journal")]:
+            if os.path.exists(path):
+                os.remove(path)
+                purged.append(path)
+        root = self._cli_root(ctx)
+        brain = f"{root}/brain/{uuid}"
         if os.path.isdir(brain):
             shutil.rmtree(brain, ignore_errors=True)
             purged.append(brain)
+        annotation = f"{root}/annotations/{uuid}.pbtxt"
+        if os.path.exists(annotation):
+            os.remove(annotation)
+            purged.append(annotation)
+        # The presence lock marks a conversation some process has open; only
+        # remove it once nothing references the conversation any more.
+        lock = f"{root}/presence/{uuid}.lock"
+        if os.path.exists(lock):
+            if self.conversation_in_use(uuid, ctx):
+                print(f"WARN: presence lock kept, conversation {uuid} is still in use: {lock}", file=sys.stderr)
+            else:
+                os.remove(lock)
+                purged.append(lock)
         return purged
 
+    def residual_artifacts(self, uuid: str, ctx: DiscoveryContext) -> list:
+        """Anything under the agy CLI tree still carrying this conversation id."""
+        root = self._cli_root(ctx)
+        if not os.path.isdir(root):
+            return []
+        found = []
+        for dirpath, dirnames, filenames in os.walk(root):
+            for name in dirnames + filenames:
+                if uuid in name:
+                    found.append(os.path.join(dirpath, name))
+            # Do not descend into a matched directory; it is reported as a whole.
+            dirnames[:] = [d for d in dirnames if uuid not in d]
+        return sorted(found)
+
     def spawn_spec(self, binary: str, session_uuid: str = "", use_wrapper: bool = False) -> str:
         return f"{binary} --dangerously-skip-permissions"
 

.agents/skills/lib_py/agents/base.py

@@ -1,10 +1,53 @@
 # base.py — BaseAgentAdapter abstract base class, SpawnSpec, and DiscoveryContext
 
-import os, json, sqlite3
+import os, json, sqlite3, shutil, subprocess
 from typing import Optional, Dict, Any, List
 from lib_py.paths import resolve_home
 from lib_py.verify_session import verify_session_uuid, workspace_key
 
+
+def conversation_in_use(uuid: str, paths=()) -> bool:
+    """A live process still references the conversation (Issues #10, #13).
+
+    Either its id is on a command line other than this process's own lineage
+    (`claude -r <uuid>`, `agy --conversation <uuid>`, ... - the purge command
+    itself names the uuid, so its ancestors are excluded), or one of `paths`
+    is held open (lsof, where available). A purge must not touch a
+    conversation that is in use.
+    """
+    try:
+        out = subprocess.run(["ps", "-axo", "pid=,ppid=,command="],
+                             capture_output=True, text=True, timeout=10).stdout
+    except Exception:
+        out = ""
+    parents: Dict[int, int] = {}
+    holders: List[int] = []
+    for line in out.splitlines():
+        parts = line.split(None, 2)
+        if len(parts) < 2 or not (parts[0].isdigit() and parts[1].isdigit()):
+            continue
+        pid, ppid = int(parts[0]), int(parts[1])
+        parents[pid] = ppid
+        if len(parts) > 2 and uuid in parts[2]:
+            holders.append(pid)
+    if holders:
+        lineage = set()
+        p = os.getpid()
+        while p and p not in lineage:
+            lineage.add(p)
+            p = parents.get(p, 0)
+        if any(h not in lineage for h in holders):
+            return True
+    existing = [p for p in paths if p and os.path.exists(p)]
+    if existing and shutil.which("lsof"):
+        try:
+            r = subprocess.run(["lsof", "-t"] + existing, capture_output=True, text=True, timeout=10)
+            if r.stdout.strip():
+                return True
+        except Exception:
+            pass
+    return False
+
 class SpawnSpec:
     def __init__(self, agent_name: str, session_name: str, command: str, env: Optional[Dict[str, str]] = None):
         self.agent_name = agent_name
@@ -107,6 +150,15 @@ class BaseAgentAdapter:
     def purge_artifacts(self, uuid: str, ctx: DiscoveryContext) -> list:
         raise NotImplementedError
 
+    def residual_artifacts(self, uuid: str, ctx: DiscoveryContext) -> list:
+        """Paths still carrying `uuid` after a purge. Adapters that know their
+        on-disk tree override this; the default has nothing to scan."""
+        return []
+
+    def conversation_in_use(self, uuid: str, ctx: DiscoveryContext) -> bool:
+        """True while a live process still references the conversation."""
+        return conversation_in_use(uuid, [self.artifact_path(uuid, ctx)])
+
     def spawn_spec(self, binary: str, session_uuid: str = "", use_wrapper: bool = False) -> str:
         raise NotImplementedError