fix(opencode): a purge takes its child sessions' 1.x rows, the background service alone holds no session, XDG_DATA_HOME is followed (Issue #60, review)

- Review 614b6263 (codex, P2): `opencode session delete` removes the child
  sessions with their parent, but their 1.x rows stayed and the parent's
  residual was empty. The child sessions (session_v2 and a 1.x session
  table, any depth) are taken before the delete; the 1.x tables (message,
  part, todo, session_share, session) are cleaned for all of them, and the
  residual also reports a child still on record (a failed delete).
- The in-use check counted any process holding the shared opencode.db; the
  per-user 2.x background service (`serve --service`) holds it for every
  session, so every opencode purge was refused while it ran (it does on
  this Mac). It no longer counts; any other holder and a command line
  naming the session still do.
- The data dir follows the caller's XDG_DATA_HOME when ctx is the caller's
  own home (else <home>/.local/share), for debug paths, the fallback and the
  residual scan (review 614b6263 / f4cedbae N4).
- resident_children = ('opencode',): the --standalone server stays the TUI's
  idle child; what runs under it still counts (review 1abe0a90).
- Tests: child sessions on a migrated database, a failed delete, the service
  holder, XDG, resident children, drift C pinning the parent over a newer
  child session (review f4cedbae N2), and the real-binary test no longer
  depends on PATH (N1).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff

.agents/skills/lib_py/agents/adapters/opencode.py

@@ -1,8 +1,15 @@
 import os, sys, sqlite3, shutil, subprocess
+from urllib.parse import quote
 from typing import Optional, Any, List
-from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext, scan_names, db_rows_naming
+from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext, scan_names, db_rows_naming, conversation_in_use
 from lib_py.verify_session import workspace_key
 
+# Tables a 1.x opencode wrote and a migration to 2.x keeps but no longer
+# writes (`opencode session delete` leaves them), and their session column.
+_LEGACY_TABLES = (("message", "session_id"), ("messages", "session_id"), ("part", "session_id"),
+                  ("parts", "session_id"), ("todo", "session_id"), ("session_share", "session_id"),
+                  ("session", "id"), ("sessions", "id"))
+
 _PROVIDER_ENV_VARS = (
     'ANTHROPIC_API_KEY',
     'OPENAI_API_KEY',
@@ -59,6 +66,12 @@ class OpenCodeAgentAdapter(BaseAgentAdapter):
         # blanks after the ┃) or the `Build auto · <model>` status line.
         return r'^\s{20,}\S|^\s*(Build|Plan)\b.*·'
 
+    @property
+    def resident_children(self) -> tuple:
+        # --standalone keeps its server, `opencode serve --stdio --port 0`, as
+        # the TUI's child while idle (measured on 2.0.32, Issue #60).
+        return ('opencode',)
+
     def _bin(self, ctx: DiscoveryContext) -> Optional[str]:
         bin_path = shutil.which("opencode")
         if bin_path:
@@ -71,6 +84,15 @@ class OpenCodeAgentAdapter(BaseAgentAdapter):
                 return candidate_bin
         return None
 
+    def _data_home(self, ctx: DiscoveryContext) -> str:
+        """The XDG data dir opencode uses for ctx's home: the caller's
+        XDG_DATA_HOME when ctx is the caller's own home, else <home>/.local/share."""
+        ambient = os.environ.get("XDG_DATA_HOME")
+        own = os.path.realpath(ctx.home_dir or "") == os.path.realpath(os.path.expanduser("~"))
+        if ambient and (own or not ctx.home_dir):
+            return ambient
+        return os.path.join(ctx.home_dir, ".local/share")
+
     def _run(self, ctx: DiscoveryContext, args: list, timeout: int):
         """Run the opencode CLI against ctx's home (its data dir follows HOME and
         XDG_DATA_HOME); None when there is no binary."""
@@ -81,7 +103,7 @@ class OpenCodeAgentAdapter(BaseAgentAdapter):
         if ctx.home_dir:
             env["HOME"] = ctx.home_dir
             env["HOME_DIR"] = ctx.home_dir
-            env["XDG_DATA_HOME"] = os.path.join(ctx.home_dir, ".local/share")
+            env["XDG_DATA_HOME"] = self._data_home(ctx)
         cwd = ctx.workspace or ctx.cwd or os.getcwd()
         return subprocess.run([bin_path] + args, capture_output=True, text=True, timeout=timeout,
                               env=env, cwd=cwd if os.path.exists(cwd) else None)
@@ -98,7 +120,7 @@ class OpenCodeAgentAdapter(BaseAgentAdapter):
                         return parts[1].strip()
         except Exception:
             pass
-        return f"{ctx.home_dir}/.local/share/opencode/opencode.db"
+        return os.path.join(self._data_home(ctx), "opencode", "opencode.db")
 
     def artifact_path(self, uuid: str, ctx: DiscoveryContext) -> str:
         db = self._resolve_db(ctx)
@@ -133,10 +155,15 @@ class OpenCodeAgentAdapter(BaseAgentAdapter):
     def purge_artifacts(self, uuid: str, ctx: DiscoveryContext) -> list:
         purged = []
         db = self._resolve_db(ctx)
-        if db and os.path.exists(db) and self._has_session(db, uuid):
+        if not db or not os.path.exists(db):
+            return purged
+        # The child sessions are taken before opencode deletes them with
+        # their parent: their 1.x rows are this purge's to remove too.
+        ids = [uuid] + self._descendants(db, uuid)
+        if self._has_session(db, uuid):
             # opencode deletes a 2.x session with its child sessions and every
-            # row it keeps for them; --standalone so no background service is
-            # started for it.
+            # 2.x row it keeps for them; --standalone so no background service
+            # is started for it.
             try:
                 res = self._run(ctx, ["session", "delete", "--standalone", "--", uuid], timeout=60)
                 if res is None:
@@ -148,33 +175,47 @@ class OpenCodeAgentAdapter(BaseAgentAdapter):
                                      f"{(res.stderr or res.stdout).strip()}\n")
             except Exception as e:
                 sys.stderr.write(f"WARN: purge opencode: session delete {uuid} failed: {e}\n")
-        if db and os.path.exists(db):
-            # Rows a 1.x opencode left in the tables a migration keeps.
+        # The rows a 1.x opencode left (a migration keeps those tables).
         try:
             conn = sqlite3.connect(db)
-                cursor = conn.cursor()
-                cursor.execute("SELECT name FROM sqlite_master WHERE type='table'")
-                tables = {row[0] for row in cursor.fetchall()}
-                if "message" in tables:
-                    conn.execute("DELETE FROM message WHERE session_id=?", (uuid,))
-                if "messages" in tables:
-                    conn.execute("DELETE FROM messages WHERE session_id=?", (uuid,))
-                if "part" in tables:
-                    conn.execute("DELETE FROM part WHERE session_id=?", (uuid,))
-                if "parts" in tables:
-                    conn.execute("DELETE FROM parts WHERE session_id=?", (uuid,))
-                if "session" in tables:
-                    conn.execute("DELETE FROM session WHERE id=?", (uuid,))
-                if "sessions" in tables:
-                    conn.execute("DELETE FROM sessions WHERE id=?", (uuid,))
+            tables = {row[0] for row in conn.execute("SELECT name FROM sqlite_master WHERE type='table'")}
+            legacy = [(t, c) for t, c in _LEGACY_TABLES if t in tables]
+            for t, c in legacy:
+                for i in ids:
+                    conn.execute(f'DELETE FROM "{t}" WHERE "{c}"=?', (i,))
             conn.commit()
             conn.close()
-                if tables & {"message", "messages", "part", "parts", "session", "sessions"}:
-                    purged.append(f"sqlite rows for session: {uuid}")
+            if legacy:
+                kids = f" and {len(ids) - 1} child session(s)" if len(ids) > 1 else ""
+                purged.append(f"sqlite rows for session: {uuid}{kids}")
         except Exception as e:
             sys.stderr.write(f"WARN: purge opencode db records failed: {e}\n")
         return purged
 
+    def _descendants(self, db: str, uuid: str) -> list:
+        """Child sessions (any depth) of uuid in session_v2 and a 1.x session table."""
+        found, todo = [], [uuid]
+        try:
+            conn = sqlite3.connect(f"file:{quote(os.path.abspath(db))}?mode=ro", uri=True)
+        except Exception:
+            return found
+        try:
+            tables = {r[0] for r in conn.execute("SELECT name FROM sqlite_master WHERE type='table'")}
+            sources = [t for t in ("session_v2", "session") if t in tables
+                       and "parent_id" in {r[1] for r in conn.execute(f'PRAGMA table_info("{t}")')}]
+            while todo:
+                cur = todo.pop()
+                for t in sources:
+                    for (cid,) in conn.execute(f'SELECT id FROM "{t}" WHERE parent_id=?', (cur,)):
+                        if cid and cid != uuid and cid not in found:
+                            found.append(cid)
+                            todo.append(cid)
+        except Exception:
+            pass
+        finally:
+            conn.close()
+        return found
+
     def _has_session(self, db: str, uuid: str) -> bool:
         try:
             conn = sqlite3.connect(db)
@@ -186,11 +227,43 @@ class OpenCodeAgentAdapter(BaseAgentAdapter):
             return False
 
     def residual_artifacts(self, uuid: str, ctx: DiscoveryContext) -> list:
-        # Issue #31: whatever still names the session (event-sourced rows a
-        # 1.x opencode left, a failed `session delete`) is reported.
-        found = scan_names(f"{ctx.home_dir}/.local/share/opencode", uuid)
-        return found + db_rows_naming(self._resolve_db(ctx), uuid, ("session_id", "aggregate_id"),
+        # Issue #31: whatever still names the session or a child session still
+        # on record (a failed `session delete`) is reported.
+        db = self._resolve_db(ctx)
+        found = scan_names(os.path.join(self._data_home(ctx), "opencode"), uuid)
+        for i in [uuid] + (self._descendants(db, uuid) if db and os.path.isfile(db) else []):
+            rows = db_rows_naming(db, i, ("session_id", "aggregate_id"),
                                   id_tables=(("session", "id"), ("session_v2", "id")))
+            found += rows if i == uuid else [f"{r} [child session {i}]" for r in rows]
+        return found
+
+    def conversation_in_use(self, uuid: str, ctx: DiscoveryContext) -> bool:
+        """A process naming the session, or an opencode process holding the
+        shared database. The per-user background service (`serve --service`)
+        holds it for every session and runs none of MAM's (MAM spawns
+        --standalone), so it alone does not make a session in use."""
+        if conversation_in_use(uuid, []):
+            return True
+        db = self._resolve_db(ctx)
+        if not db or not os.path.exists(db) or not shutil.which("lsof"):
+            return False
+        try:
+            pids = subprocess.run(["lsof", "-t", db], capture_output=True, text=True, timeout=10).stdout.split()
+        except Exception:
+            return True
+        for pid in pids:
+            try:
+                cmd = subprocess.run(["ps", "-o", "command=", "-p", pid], capture_output=True, text=True,
+                                     timeout=10).stdout
+            except Exception:
+                return True
+            if cmd.strip() and "serve --service" not in cmd:
+                return True
+        return False
+
+    def in_use_hints(self, uuid: str, ctx: DiscoveryContext) -> list:
+        return super().in_use_hints(uuid, ctx) + [
+            f"another opencode session holding {self._resolve_db(ctx)}: lsof {self._resolve_db(ctx)}"]
 
     # opencode 2.x: the default agent is build (`--agent` is gone from the
     # TUI), and --standalone keeps the server a child of the pane's TUI

tests/test_issue31_purge_residual.py

@@ -896,10 +896,10 @@ def _db(path: Path, ddl: list, rows: list):
     conn.close()
 
 
-def test_opencode_residual_reports_event_rows(home, tmp_path, monkeypatch):
+def test_opencode_purge_leaves_no_rows(home, tmp_path, monkeypatch):
     # A database migrated from 1.x (Issue #60): `opencode session delete`
-    # (the fake, as measured on 2.0.32) removes the 2.x rows, the purge
-    # deletes the 1.x session/message/part rows, and todo is reported.
+    # (the fake, as measured on 2.0.32) removes the 2.x rows and the purge
+    # deletes the rows of the 1.x tables 2.x no longer writes.
     u, o = f"ses_{uuidlib.uuid4().hex}", f"ses_{uuidlib.uuid4().hex}"
     db = home / ".local" / "share" / "opencode" / "opencode.db"
     ddl = ["CREATE TABLE session (id TEXT PRIMARY KEY)",
@@ -931,7 +931,7 @@ def test_opencode_residual_reports_event_rows(home, tmp_path, monkeypatch):
     assert adapter.purge_artifacts(u, ctx) == [f"opencode session (with its child sessions): {u}",
                                                f"sqlite rows for session: {u}"]
 
-    assert adapter.residual_artifacts(u, ctx) == [f"{db} (todo.session_id: 1 rows)"]
+    assert adapter.residual_artifacts(u, ctx) == []
     assert len(adapter.residual_artifacts(o, ctx)) == 8  # the other session is untouched: one entry per table
 
 

tests/test_issue60_opencode_v2.py

@@ -18,6 +18,7 @@ import shutil
 import sqlite3
 import subprocess
 import sys
+import time
 from pathlib import Path
 
 import pytest
@@ -145,6 +146,122 @@ def test_a_failed_delete_is_warned_and_reported(oc, monkeypatch, capsys, broken)
     assert f"{adapter._resolve_db(ctx)} (session_v2.id: 1 rows)" in adapter.residual_artifacts("ses_main", ctx)
 
 
+def test_purge_takes_the_1x_rows_of_the_child_sessions_too(oc):
+    """A migrated database: the child sessions opencode deletes with their
+    parent keep 1.x rows that only the purge removes (review 614b6263)."""
+    adapter, ctx, db, ws, calls = oc
+    conn = sqlite3.connect(str(db))
+    conn.execute("CREATE TABLE session (id TEXT PRIMARY KEY, parent_id TEXT)")
+    conn.execute("CREATE TABLE message (id TEXT PRIMARY KEY, session_id TEXT)")
+    conn.execute("CREATE TABLE todo (id TEXT, session_id TEXT)")
+    conn.commit()
+    conn.close()
+    tree = [("ses_main", None), ("ses_child", "ses_main"), ("ses_grand", "ses_child"), ("ses_other", None)]
+    for sid, parent in tree:
+        _add(db, sid, ws, 2_000_000, parent=parent)
+        conn = sqlite3.connect(str(db))
+        conn.execute("INSERT INTO session VALUES (?, ?)", (sid, parent))
+        conn.execute("INSERT INTO message VALUES (?, ?)", (f"m-{sid}", sid))
+        conn.execute("INSERT INTO todo VALUES ('t', ?)", (sid,))
+        conn.commit()
+        conn.close()
+
+    assert any(r.endswith("[child session ses_grand]") for r in adapter.residual_artifacts("ses_main", ctx))
+    purged = adapter.purge_artifacts("ses_main", ctx)
+    assert purged == ["opencode session (with its child sessions): ses_main",
+                      "sqlite rows for session: ses_main and 2 child session(s)"]
+    for sid in ("ses_main", "ses_child", "ses_grand"):
+        assert adapter.residual_artifacts(sid, ctx) == [], sid
+    # the unrelated session is untouched: session_v2, session_message, event_sequence, session, message, todo
+    assert len(adapter.residual_artifacts("ses_other", ctx)) == 6
+
+
+def test_a_failed_delete_reports_the_child_sessions_left(oc, monkeypatch):
+    adapter, ctx, db, ws, calls = oc
+    _add(db, "ses_main", ws, 2_000_000)
+    _add(db, "ses_child", ws, 2_000_000, parent="ses_main")
+    monkeypatch.setattr(adapter, "_bin", lambda ctx: None)
+    adapter.purge_artifacts("ses_main", ctx)
+    residual = adapter.residual_artifacts("ses_main", ctx)
+    assert f"{db} (session_v2.id: 1 rows) [child session ses_child]" in residual
+    assert f"{db} (session_v2.id: 1 rows)" in residual
+
+
+def _holder(tmp_path, db, *argv):
+    """A live process holding `db` open, with `argv` on its command line."""
+    ready = tmp_path / f"ready-{len(argv)}"
+    code = ("import sys, time; f = open(sys.argv[1]); open(sys.argv[2], 'w').close(); time.sleep(60)")
+    p = subprocess.Popen([sys.executable, "-c", code, str(db), str(ready), *argv])
+    for _ in range(100):
+        if ready.exists():
+            break
+        time.sleep(0.05)
+    return p
+
+
+@pytest.mark.skipif(shutil.which("lsof") is None, reason="no lsof")
+def test_the_background_service_alone_does_not_hold_a_session(oc, tmp_path):
+    """The per-user service keeps the shared database open for every session
+    (2.x); MAM runs none of its sessions there."""
+    adapter, ctx, db, ws, calls = oc
+    _add(db, "ses_main", ws, 2_000_000)
+    assert adapter.conversation_in_use("ses_main", ctx) is False
+    service = _holder(tmp_path, db, "serve", "--service")
+    try:
+        assert adapter.conversation_in_use("ses_main", ctx) is False
+        other = _holder(tmp_path, db, "--auto", "--standalone")   # another session's TUI or its server
+        try:
+            assert adapter.conversation_in_use("ses_main", ctx) is True
+        finally:
+            other.kill()
+            other.wait()
+    finally:
+        service.kill()
+        service.wait()
+    named = subprocess.Popen([sys.executable, "-c", "import time; time.sleep(60)", "--session", "ses_main"])
+    try:
+        time.sleep(0.2)
+        assert adapter.conversation_in_use("ses_main", ctx) is True
+    finally:
+        named.kill()
+        named.wait()
+
+
+def test_the_data_dir_follows_the_callers_xdg_data_home_only_for_its_own_home(tmp_path, monkeypatch):
+    adapter = get_adapter("opencode")
+    monkeypatch.setattr(adapter, "_bin", lambda ctx: None)
+    own, other, xdg = tmp_path / "own", tmp_path / "other", tmp_path / "xdg"
+    monkeypatch.setenv("HOME", str(own))
+    monkeypatch.setenv("XDG_DATA_HOME", str(xdg))
+    ws = str(tmp_path)
+    assert adapter._resolve_db(DiscoveryContext(workspace=ws, agent_name="opencode", home_dir=str(own))) \
+        == f"{xdg}/opencode/opencode.db"
+    assert adapter._resolve_db(DiscoveryContext(workspace=ws, agent_name="opencode", home_dir=str(other))) \
+        == f"{other}/.local/share/opencode/opencode.db"
+    monkeypatch.delenv("XDG_DATA_HOME")
+    assert adapter._resolve_db(DiscoveryContext(workspace=ws, agent_name="opencode", home_dir=str(own))) \
+        == f"{own}/.local/share/opencode/opencode.db"
+
+
+def test_the_standalone_server_is_a_resident_child_but_its_tools_are_work():
+    """--standalone keeps `opencode serve --stdio` under the TUI while idle;
+    the stall watcher skips it but still sees what runs under it."""
+    from lib_py.stall_watch import background_children
+    resident = get_adapter("opencode").resident_children
+    tui = subprocess.Popen(["bash", "-c", "(exec -a opencode sleep 300) & exec sleep 300"], start_new_session=True)
+    busy = subprocess.Popen(["bash", "-c", "(exec -a opencode bash -c 'sleep 300; :') & exec sleep 300"],
+                            start_new_session=True)
+    try:
+        time.sleep(0.5)
+        assert background_children(tui.pid, ()) != []
+        assert background_children(tui.pid, resident) == []
+        assert background_children(busy.pid, resident) != []
+    finally:
+        for p in (tui, busy):
+            os.killpg(p.pid, 9)   # the whole group: children and grandchildren
+            p.wait()
+
+
 def test_spawn_and_resume_never_pass_agent_and_run_standalone():
     """The shell copies of the opencode command line match the adapter."""
     adapter = get_adapter("opencode")
@@ -214,6 +331,9 @@ def test_real_opencode_2x_contract(tmp_path, monkeypatch):
                            json.dumps({"title": "mam child", "parentID": parent})).stdout)["data"]["id"]
 
     adapter = get_adapter("opencode")
+    # The binary was found with the real HOME; under the test's HOME only a
+    # PATH entry would find it (review f4cedbae N1).
+    monkeypatch.setattr(adapter, "_bin", lambda ctx: REAL)
     ctx = DiscoveryContext(workspace=ws_real, agent_name="opencode", home_dir=str(home))
     db = adapter._resolve_db(ctx)
     assert db == str(home / ".local" / "share" / "opencode" / "opencode.db")

tests/test_tier2_component.py

@@ -1249,6 +1249,17 @@ def test_comp_opencode_create_and_reconcile_and_stop(mam_sandbox, mock_herdr, mo
     assert s["opencode_session_id_own"] is None
     assert s["session_id_source"] == "pending-discovery"
 
+    # A subagent's session in the same directory, newer than the TUI's own
+    # (opencode 2.x, Issue #60): drift C must pin the top-level session.
+    import sqlite3
+    odb = os.path.join(os.environ["HOME"], ".local", "share", "opencode", "opencode.db")
+    conn = sqlite3.connect(odb)
+    (parent, directory, created), = conn.execute("SELECT id, directory, time_created FROM session_v2").fetchall()
+    conn.execute("INSERT INTO session_v2 (id, parent_id, directory, time_created) VALUES (?, ?, ?, ?)",
+                 (f"{parent}-child", parent, directory, created + 1000))
+    conn.commit()
+    conn.close()
+
     # Run reconcile.sh to trigger drift-C materialization
     reconcile_script = mam_sandbox / ".agents" / "skills" / "multi-agent-mux-monitor" / "scripts" / "reconcile.sh"
     res_rec = subprocess.run(["bash", str(reconcile_script), "--once", "--emit-diff"], capture_output=True, text=True, cwd=str(mam_sandbox), env={**os.environ, "WORKSPACE_ROOT": str(mam_sandbox)})
@@ -1259,7 +1270,7 @@ def test_comp_opencode_create_and_reconcile_and_stop(mam_sandbox, mock_herdr, mo
     with open(yaml_path) as f:
         data_after = yaml.safe_load(f)
     s_after = [x for x in data_after.get("herdr_sessions", []) if x.get("name") == session_name][0]
-    assert s_after.get("opencode_session_id_own") is not None
+    assert s_after.get("opencode_session_id_own") == parent
     assert s_after.get("last_visible_status") in ("pinned", "resume_verified")
 
     # Stop session