fix(agents): codex, grok and opencode report their residual (Issue #31)

Their purge is unchanged; what it leaves is now reported: codex names and
thread rows (state_*, thread_history_*; logs_* is not scanned), grok
memory-v2 observations, opencode event/todo rows. db_rows_naming opens the
DB read-only.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

.agents/skills/lib_py/agents/adapters/codex.py

@@ -1,6 +1,6 @@
 import os, json, glob, sqlite3, subprocess
 from typing import Optional, Any, List
-from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext
+from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext, scan_names, db_rows_naming
 from lib_py.verify_session import workspace_key
 
 class CodexAgentAdapter(BaseAgentAdapter):
@@ -158,6 +158,17 @@ class CodexAgentAdapter(BaseAgentAdapter):
                 pass
         return purged
 
+    def residual_artifacts(self, uuid: str, ctx: DiscoveryContext) -> List[str]:
+        # Issue #31: names under CODEX_HOME plus thread rows. logs_*.sqlite is
+        # not scanned (no thread index: a full scan of a large file).
+        root = self._codex_home(ctx)
+        found = scan_names(root, uuid)
+        for db in sorted(glob.glob(f"{root}/state_*.sqlite")):
+            found += db_rows_naming(db, uuid, ("thread_id",), id_tables=(("threads", "id"),))
+        for db in sorted(glob.glob(f"{root}/thread_history_*.sqlite")):
+            found += db_rows_naming(db, uuid, ("thread_id",))
+        return found
+
     def spawn_spec(self, binary: str, session_uuid: str = "", use_wrapper: bool = False) -> str:
         return f"{binary} --dangerously-bypass-approvals-and-sandbox"
 

.agents/skills/lib_py/agents/adapters/grok.py

@@ -1,7 +1,7 @@
 import os, json, glob, shutil
 from typing import Optional, Any
 from urllib.parse import quote
-from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext
+from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext, scan_names
 from lib_py.verify_session import workspace_key
 
 
@@ -108,6 +108,11 @@ class GrokAgentAdapter(BaseAgentAdapter):
             purged.append(self.artifact_path(uuid, ctx))
         return purged
 
+    def residual_artifacts(self, uuid: str, ctx: DiscoveryContext) -> list:
+        # Issue #31: reported, not removed - memory-v2 observations are the
+        # shared store of grok's memory pipeline.
+        return scan_names(f"{ctx.home_dir}/.grok", uuid)
+
     def spawn_spec(self, binary: str, session_uuid: str = "", use_wrapper: bool = False) -> str:
         if session_uuid:
             return f"{binary} --session-id {session_uuid} --permission-mode bypassPermissions"

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

@@ -1,6 +1,6 @@
 import os, sys, sqlite3, shutil
 from typing import Optional, Any, List
-from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext
+from lib_py.agents.base import BaseAgentAdapter, DiscoveryContext, scan_names, db_rows_naming
 from lib_py.verify_session import workspace_key
 
 _PROVIDER_ENV_VARS = (
@@ -194,6 +194,13 @@ class OpenCodeAgentAdapter(BaseAgentAdapter):
                 sys.stderr.write(f"WARN: purge opencode db records failed: {e}\n")
         return purged
 
+    def residual_artifacts(self, uuid: str, ctx: DiscoveryContext) -> list:
+        # Issue #31: the purge leaves event-sourced rows (event, todo, ...);
+        # deleting those is not known to be safe, so they are 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"),
+                                      id_tables=(("session", "id"),))
+
     def spawn_spec(self, binary: str, session_uuid: str = "", use_wrapper: bool = False) -> str:
         return f"{binary} --auto --agent build"
 

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

@@ -2,6 +2,7 @@
 
 import os, json, sqlite3, shutil, subprocess
 from typing import Optional, Dict, Any, List
+from urllib.parse import quote
 from lib_py.paths import resolve_home
 from lib_py.verify_session import verify_session_uuid, workspace_key
 
@@ -107,6 +108,40 @@ def scan_names(root: str, uuid: str, skip=()) -> list:
     return sorted(found)
 
 
+def db_rows_naming(db: str, uuid: str, columns=(), id_tables=()) -> list:
+    """"<db> (<table>.<col>: <n> rows)" for every table holding rows of this
+    conversation in one of `columns`, or in the id column of an `id_tables`
+    (table, column) pair (Issue #31). Read-only; unreadable tables are skipped."""
+    if not _plausible_id(uuid) or not db or not os.path.isfile(db):
+        return []
+    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'")]
+        for table in tables:
+            qt = table.replace('"', '""')
+            try:
+                cols = {r[1] for r in conn.execute(f'PRAGMA table_info("{qt}")')}
+            except Exception:
+                continue
+            wanted = [c for c in columns if c in cols]
+            wanted += [c for t, c in id_tables if t == table and c in cols and c not in wanted]
+            for col in wanted:
+                try:
+                    n = conn.execute(f'SELECT count(*) FROM "{qt}" WHERE "{col}"=?', (uuid,)).fetchone()[0]
+                except Exception:
+                    continue
+                if n:
+                    found.append(f"{db} ({table}.{col}: {n} rows)")
+    except Exception:
+        pass
+    finally:
+        conn.close()
+    return found
+
 class SpawnSpec:
     def __init__(self, agent_name: str, session_name: str, command: str, env: Optional[Dict[str, str]] = None):
         self.agent_name = agent_name