Merge branch 'main' of github.com:NousResearch/hermes-agent into bb/gui

tests/gateway/conftest.py

@@ -313,19 +313,30 @@ def _scan_for_plugin_adapter_antipattern(source: str) -> list[str]:
     return offenses
 
 
-def pytest_configure(config):
-    """Reject plugin-adapter tests that use the sys.path anti-pattern.
+def _fingerprint_gateway_tests() -> str:
+    """Return a short fingerprint that changes when any gateway test file changes.
 
-    Runs once per pytest session on the controller, BEFORE any xdist
-    worker is spawned. If any file under ``tests/gateway/`` matches the
-    anti-pattern, we fail the whole session with a clear message —
-    before a polluted ``sys.path`` can cascade across workers.
+    Uses (mtime, size) pairs instead of content hashing — fast to compute
+    (stat-only, no reads) and sufficient for cache invalidation across
+    per-file subprocess runs.
     """
-    # Only run on the xdist controller (or in non-xdist runs). Skip on
-    # worker subprocesses so we don't scan the filesystem N times.
-    if hasattr(config, "workerinput"):
-        return
+    import hashlib
 
+    h = hashlib.sha256()
+    for path in sorted(_GATEWAY_DIR.rglob("test_*.py")):
+        try:
+            st = path.stat()
+            h.update(f"{path.name}:{st.st_mtime_ns}:{st.st_size}".encode())
+        except OSError:
+            h.update(f"{path.name}:missing".encode())
+    return h.hexdigest()[:16]
+
+
+def _run_adapter_antipattern_scan() -> list[str]:
+    """Scan gateway test files for the plugin-adapter anti-pattern.
+
+    Returns a list of violation strings (empty if clean).
+    """
     violations: list[str] = []
     for path in _GATEWAY_DIR.rglob("test_*.py"):
         if path.name in {"_plugin_adapter_loader.py", "conftest.py"}:
@@ -334,20 +345,108 @@ def pytest_configure(config):
             source = path.read_text(encoding="utf-8")
         except OSError:
             continue
+        # Fast string pre-filter: skip files that can't possibly violate.
+        # A violating file MUST contain both (a) an adapter/plugins/platforms
+        # reference AND (b) either sys.path manipulation or a bare adapter import.
         if "adapter" not in source and "plugins/platforms" not in source:
             continue
+        if not (
+            "sys.path" in source
+            or "import adapter" in source
+            or "from adapter import" in source
+        ):
+            continue
         offenses = _scan_for_plugin_adapter_antipattern(source)
         if offenses:
             violations.append(
                 f"  {path.relative_to(_GATEWAY_DIR.parent.parent)}:\n    "
                 + "\n    ".join(offenses)
             )
+    return violations
 
-    if violations:
-        raise pytest.UsageError(
-            "Plugin-adapter-import anti-pattern detected in gateway tests:\n"
-            + "\n".join(violations)
-            + "\n\n"
-            + _GUARD_HINT
-        )
+
+def pytest_configure(config):
+    """Reject plugin-adapter tests that use the sys.path anti-pattern.
+
+    Runs once per pytest session on the controller, BEFORE any xdist
+    worker is spawned. If any file under ``tests/gateway/`` matches the
+    anti-pattern, we fail the whole session with a clear message —
+    before a polluted ``sys.path`` can cascade across workers.
+
+    **Performance**: in the per-file subprocess isolation model (no xdist),
+    every subprocess is a "controller" — so the naive scan would run 257
+    times, each costing ~1s of AST walking.  We avoid this with two
+    strategies:
+
+    1. **Tight string pre-filter**: a file can only violate if it contains
+       *both* an adapter/plugins/platforms reference *and* a sys.path
+       manipulation or bare ``import adapter``.  This drops ~95% of files
+       from needing AST parsing.
+    2. **File-locked cache**: the scan result is cached in
+       ``.pytest-cache/gw-adapter-guard-<fingerprint>`` keyed on a
+       fingerprint of the gateway test file mtimes/sizes.  Concurrent
+       subprocesses acquire a lock; only the first performs the scan;
+       the rest wait and read the cached result.
+    """
+    # Only run on the xdist controller (or in non-xdist runs). Skip on
+    # worker subprocesses so we don't scan the filesystem N times.
+    if hasattr(config, "workerinput"):
+        return
+
+    fp = _fingerprint_gateway_tests()
+    cache_dir = Path.cwd() / ".pytest-cache"
+    cache_file = cache_dir / f"gw-adapter-guard-{fp}"
+    lock_file = cache_dir / f".gw-adapter-guard-{fp}.lock"
+
+    cache_dir.mkdir(parents=True, exist_ok=True)
+
+    # Evict stale cache entries from previous fingerprints (best-effort).
+    try:
+        for old in cache_dir.glob("gw-adapter-guard-*"):
+            if old.name != f"gw-adapter-guard-{fp}":
+                old.unlink(missing_ok=True)
+        for old in cache_dir.glob(".gw-adapter-guard-*.lock"):
+            if old.name != f".gw-adapter-guard-{fp}.lock":
+                old.unlink(missing_ok=True)
+    except OSError:
+        pass  # Non-critical; old files are harmless.
+
+    # Use filelock to ensure only one process scans at a time.
+    # Concurrent subprocesses all hit pytest_configure simultaneously;
+    # without a lock they'd all find no cache and all run the scan.
+    try:
+        from filelock import FileLock
+        lock = FileLock(str(lock_file), timeout=120)
+    except ImportError:
+        # Fallback: no locking (still correct, just slower under contention).
+        import contextlib
+
+        class _NoLock:
+            def __enter__(self):
+                return self
+            def __exit__(self, *a):
+                pass
+        lock = _NoLock()
+
+    with lock:
+        if cache_file.exists():
+            cached = cache_file.read_text(encoding="utf-8")
+            if cached == "clean":
+                return
+            raise pytest.UsageError(cached)
+
+        # Slow path: this process is the first to acquire the lock.
+        violations = _run_adapter_antipattern_scan()
+
+        if violations:
+            msg = (
+                "Plugin-adapter-import anti-pattern detected in gateway tests:\n"
+                + "\n".join(violations)
+                + "\n\n"
+                + _GUARD_HINT
+            )
+            cache_file.write_text(msg, encoding="utf-8")
+            raise pytest.UsageError(msg)
+        else:
+            cache_file.write_text("clean", encoding="utf-8")
 

tests/gateway/platforms/test_yuanbao_recall_db_only.py

@@ -0,0 +1,88 @@
+"""Yuanbao recall: branch A1 (exact id) and A2 (content-match) against DB-only transcripts.
+
+state.db persists the platform-side ``message_id`` via the
+``platform_message_id`` column (added in the salvage of PR #29211) and
+``load_transcript`` surfaces it back on each message dict as ``message_id``
+— so the recall guard's exact-id match path stays canonical even with the
+JSONL file gone.  When a row has no platform id (e.g. agent-processed
+@bot messages whose adapter didn't carry a msg_id, or pre-column legacy
+rows), recall falls through to content-match.
+"""
+from gateway.session import SessionStore
+from gateway.config import GatewayConfig
+
+
+def _pin_db(monkeypatch, tmp_path):
+    """Force SessionDB() to write into tmp_path instead of the real ~/.hermes."""
+    import hermes_state
+    monkeypatch.setattr(hermes_state, "DEFAULT_DB_PATH", tmp_path / "state.db")
+
+
+def test_recall_branch_a1_exact_id_match_round_trips_through_db(tmp_path, monkeypatch):
+    """A user message persisted with ``message_id`` must round-trip through
+    state.db so recall can find and redact it by exact id (branch A1)."""
+    _pin_db(monkeypatch, tmp_path)
+
+    config = GatewayConfig()
+    store = SessionStore(sessions_dir=tmp_path, config=config)
+
+    sid = "test-yuanbao-recall-a1"
+    store._db.create_session(session_id=sid, source="yuanbao:group:G")
+    store.append_to_transcript(sid, {
+        "role": "user",
+        "content": "sensitive content",
+        "timestamp": 1.0,
+        "message_id": "platform-msg-abc",
+    })
+    store.append_to_transcript(sid, {
+        "role": "assistant",
+        "content": "ack",
+        "timestamp": 2.0,
+    })
+
+    history = store.load_transcript(sid)
+    # The user row must carry its platform id back so the recall guard can
+    # match by exact id; the assistant row had no platform id so it should
+    # not gain one spuriously.
+    user_msg = next(m for m in history if m["role"] == "user")
+    assistant_msg = next(m for m in history if m["role"] == "assistant")
+    assert user_msg.get("message_id") == "platform-msg-abc"
+    assert "message_id" not in assistant_msg
+
+    # Branch A1: locate the row by exact platform id — no content heuristics.
+    target = next(
+        (m for m in history if m.get("message_id") == "platform-msg-abc"),
+        None,
+    )
+    assert target is not None
+    assert target["content"] == "sensitive content"
+
+
+def test_recall_branch_a2_content_match_when_no_platform_id(tmp_path, monkeypatch):
+    """Rows that lack a platform_message_id (e.g. agent-processed @bot
+    messages) still match by content as a fallback."""
+    _pin_db(monkeypatch, tmp_path)
+
+    config = GatewayConfig()
+    store = SessionStore(sessions_dir=tmp_path, config=config)
+
+    sid = "test-yuanbao-recall-a2"
+    store._db.create_session(session_id=sid, source="yuanbao:group:G")
+    # No message_id on the dict — simulates an agent-processed message
+    # that did not carry the platform msg_id through.
+    store.append_to_transcript(sid, {
+        "role": "user",
+        "content": "sensitive content",
+        "timestamp": 1.0,
+    })
+
+    history = store.load_transcript(sid)
+    assert all("message_id" not in m for m in history)
+
+    # Branch A2: content match recovers the target.
+    target = next(
+        (m for m in history
+         if m.get("role") == "user" and m.get("content") == "sensitive content"),
+        None,
+    )
+    assert target is not None

tests/gateway/test_dm_topics.py

@@ -22,19 +22,26 @@ from gateway.config import PlatformConfig
 
 
 def _ensure_telegram_mock():
-    if "telegram" in sys.modules and hasattr(sys.modules["telegram"], "__file__"):
-        return
-
     telegram_mod = MagicMock()
     telegram_mod.ext.ContextTypes.DEFAULT_TYPE = type(None)
-    telegram_mod.constants.ParseMode.MARKDOWN_V2 = "MarkdownV2"
-    telegram_mod.constants.ChatType.GROUP = "group"
-    telegram_mod.constants.ChatType.SUPERGROUP = "supergroup"
-    telegram_mod.constants.ChatType.CHANNEL = "channel"
-    telegram_mod.constants.ChatType.PRIVATE = "private"
 
-    for name in ("telegram", "telegram.ext", "telegram.constants", "telegram.request"):
-        sys.modules.setdefault(name, telegram_mod)
+    # Register telegram.constants as a separate module mock so that
+    # ``from telegram.constants import ChatType`` resolves to our mock
+    # with string-valued members (not auto-generated MagicMocks).
+    constants_mod = MagicMock()
+    constants_mod.ParseMode.MARKDOWN_V2 = "MarkdownV2"
+    constants_mod.ChatType.GROUP = "group"
+    constants_mod.ChatType.SUPERGROUP = "supergroup"
+    constants_mod.ChatType.CHANNEL = "channel"
+    constants_mod.ChatType.PRIVATE = "private"
+
+    sys.modules["telegram"] = telegram_mod
+    sys.modules["telegram.ext"] = telegram_mod.ext
+    sys.modules["telegram.constants"] = constants_mod
+    sys.modules["telegram.request"] = telegram_mod.request
+
+    # Force reimport so the adapter picks up the mock ChatType.
+    sys.modules.pop("gateway.platforms.telegram", None)
 
 
 _ensure_telegram_mock()

tests/gateway/test_google_chat.py

@@ -22,6 +22,11 @@ import pytest
 
 from gateway.config import Platform, PlatformConfig, load_gateway_config
 
+# Platform uses _missing_() for dynamic members, so "google_chat" is
+# resolvable via Platform("google_chat") even without a static
+# GOOGLE_CHAT attribute on the enum class.
+_GC = Platform("google_chat")
+
 
 # ---------------------------------------------------------------------------
 # Mock the google-* packages if they are not installed
@@ -229,7 +234,7 @@ def _make_chat_envelope(text="hello", sender_email="u@example.com", sender_type=
 
 class TestPlatformRegistration:
     def test_enum_value(self):
-        assert Platform.GOOGLE_CHAT.value == "google_chat"
+        assert _GC.value == "google_chat"
 
     def test_requirements_check_returns_true_when_available(self):
         # The shim flag is True in this test module.
@@ -266,14 +271,14 @@ class TestEnvConfigLoading:
         monkeypatch.setenv("GOOGLE_CHAT_PROJECT_ID", "p")
         # No subscription.
         cfg = load_gateway_config()
-        assert Platform.GOOGLE_CHAT not in cfg.platforms
+        assert _GC not in cfg.platforms
 
     def test_missing_project_does_not_enable(self, monkeypatch):
         self._clean_env(monkeypatch)
         monkeypatch.setenv("GOOGLE_CHAT_SUBSCRIPTION_NAME",
                            "projects/p/subscriptions/s")
         cfg = load_gateway_config()
-        assert Platform.GOOGLE_CHAT not in cfg.platforms
+        assert _GC not in cfg.platforms
 
 
 
@@ -2583,7 +2588,7 @@ class TestAuthorizationEmailMatch:
         runner.pairing_store.is_approved = MagicMock(return_value=False)
 
         source = SessionSource(
-            platform=Platform.GOOGLE_CHAT,
+            platform=_GC,
             chat_id="spaces/S",
             chat_type="dm",
             user_id="alice@example.com",       # post-swap: email is canonical
@@ -2604,7 +2609,7 @@ class TestAuthorizationEmailMatch:
         runner.pairing_store.is_approved = MagicMock(return_value=False)
 
         source = SessionSource(
-            platform=Platform.GOOGLE_CHAT,
+            platform=_GC,
             chat_id="spaces/S",
             chat_type="dm",
             user_id="bob@example.com",
@@ -2630,7 +2635,7 @@ class TestAuthorizationEmailMatch:
         runner.pairing_store.is_approved = MagicMock(return_value=False)
 
         source = SessionSource(
-            platform=Platform.GOOGLE_CHAT,
+            platform=_GC,
             chat_id="spaces/S",
             chat_type="dm",
             user_id="users/77777",  # no email available — resource name wins

tests/gateway/test_load_transcript_db_only.py

@@ -0,0 +1,32 @@
+"""Verify load_transcript returns SQLite messages without any JSONL file."""
+from pathlib import Path
+
+import pytest
+
+from gateway.session import SessionStore
+from gateway.config import GatewayConfig
+
+
+def test_load_transcript_returns_db_messages_when_no_jsonl(tmp_path, monkeypatch):
+    """Reading a transcript must work from SQLite alone — no JSONL fallback needed.
+
+    Pin DEFAULT_DB_PATH to tmp_path so this test cannot write to the real
+    ~/.hermes/state.db. (DEFAULT_DB_PATH is a module-level constant computed
+    at hermes_state import time, before pytest's HERMES_HOME monkeypatch
+    fires — the autouse fixture's HERMES_HOME override doesn't help here.)
+    """
+    import hermes_state
+    monkeypatch.setattr(hermes_state, "DEFAULT_DB_PATH", tmp_path / "state.db")
+
+    config = GatewayConfig()
+    store = SessionStore(sessions_dir=tmp_path, config=config)
+
+    sid = "test-session-db-only"
+    store._db.create_session(session_id=sid, source="test")
+    store.append_to_transcript(sid, {"role": "user", "content": "hello", "timestamp": 1.0})
+    store.append_to_transcript(sid, {"role": "assistant", "content": "world", "timestamp": 2.0})
+
+    history = store.load_transcript(sid)
+    assert len(history) == 2
+    assert history[0]["content"] == "hello"
+    assert history[1]["content"] == "world"

tests/gateway/test_mirror.py

@@ -8,7 +8,6 @@ import gateway.mirror as mirror_mod
 from gateway.mirror import (
     mirror_to_session,
     _find_session_id,
-    _append_to_jsonl,
 )
 
 
@@ -152,33 +151,6 @@ class TestFindSessionId:
         assert result == "sess_1"
 
 
-class TestAppendToJsonl:
-    def test_appends_message(self, tmp_path):
-        sessions_dir = tmp_path / "sessions"
-        sessions_dir.mkdir()
-
-        with patch.object(mirror_mod, "_SESSIONS_DIR", sessions_dir):
-            _append_to_jsonl("sess_1", {"role": "assistant", "content": "Hello"})
-
-        transcript = sessions_dir / "sess_1.jsonl"
-        lines = transcript.read_text().strip().splitlines()
-        assert len(lines) == 1
-        msg = json.loads(lines[0])
-        assert msg["role"] == "assistant"
-        assert msg["content"] == "Hello"
-
-    def test_appends_multiple_messages(self, tmp_path):
-        sessions_dir = tmp_path / "sessions"
-        sessions_dir.mkdir()
-
-        with patch.object(mirror_mod, "_SESSIONS_DIR", sessions_dir):
-            _append_to_jsonl("sess_1", {"role": "assistant", "content": "msg1"})
-            _append_to_jsonl("sess_1", {"role": "assistant", "content": "msg2"})
-
-        transcript = sessions_dir / "sess_1.jsonl"
-        lines = transcript.read_text().strip().splitlines()
-        assert len(lines) == 2
-
 
 class TestMirrorToSession:
     def test_successful_mirror(self, tmp_path):
@@ -192,15 +164,16 @@ class TestMirrorToSession:
 
         with patch.object(mirror_mod, "_SESSIONS_DIR", sessions_dir), \
              patch.object(mirror_mod, "_SESSIONS_INDEX", index_file), \
-             patch("gateway.mirror._append_to_sqlite"):
+             patch("gateway.mirror._append_to_sqlite") as mock_sqlite:
             result = mirror_to_session("telegram", "12345", "Hello!", source_label="cli")
 
         assert result is True
 
-        # Check JSONL was written
-        transcript = sessions_dir / "sess_abc.jsonl"
-        assert transcript.exists()
-        msg = json.loads(transcript.read_text().strip())
+        # Check SQLite writer was called with the mirror message
+        mock_sqlite.assert_called_once()
+        call_args = mock_sqlite.call_args
+        assert call_args[0][0] == "sess_abc"
+        msg = call_args[0][1]
         assert msg["content"] == "Hello!"
         assert msg["role"] == "assistant"
         assert msg["mirror"] is True
@@ -222,12 +195,12 @@ class TestMirrorToSession:
 
         with patch.object(mirror_mod, "_SESSIONS_DIR", sessions_dir), \
              patch.object(mirror_mod, "_SESSIONS_INDEX", index_file), \
-             patch("gateway.mirror._append_to_sqlite"):
+             patch("gateway.mirror._append_to_sqlite") as mock_sqlite:
             result = mirror_to_session("telegram", "-1001", "Hello topic!", source_label="cron", thread_id="10")
 
         assert result is True
-        assert (sessions_dir / "sess_topic_a.jsonl").exists()
-        assert not (sessions_dir / "sess_topic_b.jsonl").exists()
+        mock_sqlite.assert_called_once()
+        assert mock_sqlite.call_args[0][0] == "sess_topic_a"
 
     def test_successful_mirror_uses_user_id_for_group_session(self, tmp_path):
         sessions_dir, index_file = _setup_sessions(tmp_path, {
@@ -245,7 +218,7 @@ class TestMirrorToSession:
 
         with patch.object(mirror_mod, "_SESSIONS_DIR", sessions_dir), \
              patch.object(mirror_mod, "_SESSIONS_INDEX", index_file), \
-             patch("gateway.mirror._append_to_sqlite"):
+             patch("gateway.mirror._append_to_sqlite") as mock_sqlite:
             result = mirror_to_session(
                 "telegram",
                 "-1001",
@@ -255,8 +228,8 @@ class TestMirrorToSession:
             )
 
         assert result is True
-        assert (sessions_dir / "sess_alice.jsonl").exists()
-        assert not (sessions_dir / "sess_bob.jsonl").exists()
+        mock_sqlite.assert_called_once()
+        assert mock_sqlite.call_args[0][0] == "sess_alice"
 
     def test_no_matching_session(self, tmp_path):
         sessions_dir, index_file = _setup_sessions(tmp_path, {})

tests/gateway/test_retry_replacement.py

@@ -1,6 +1,6 @@
 """Regression tests for /retry replacement semantics."""
 
-from unittest.mock import AsyncMock, MagicMock, patch
+from unittest.mock import AsyncMock, MagicMock
 
 import pytest
 
@@ -11,14 +11,17 @@ from gateway.session import SessionStore
 
 
 @pytest.mark.asyncio
-async def test_gateway_retry_replaces_last_user_turn_in_transcript(tmp_path):
+async def test_gateway_retry_replaces_last_user_turn_in_transcript(tmp_path, monkeypatch):
+    # Pin DEFAULT_DB_PATH so SessionDB() doesn't write to the real ~/.hermes/state.db.
+    # (Module-level constant snapshot, see test_load_transcript_db_only.)
+    import hermes_state
+    monkeypatch.setattr(hermes_state, "DEFAULT_DB_PATH", tmp_path / "state.db")
+
     config = GatewayConfig()
-    with patch("gateway.session.SessionStore._ensure_loaded"):
-        store = SessionStore(sessions_dir=tmp_path, config=config)
-    store._db = None
-    store._loaded = True
+    store = SessionStore(sessions_dir=tmp_path, config=config)
 
     session_id = "retry_session"
+    store._db.create_session(session_id=session_id, source="test")
     for msg in [
         {"role": "session_meta", "tools": []},
         {"role": "user", "content": "first question"},

tests/gateway/test_session.py

@@ -1,6 +1,4 @@
 """Tests for gateway session management."""
-
-import builtins
 import json
 import pytest
 from pathlib import Path
@@ -503,19 +501,19 @@ class TestSenderPrefixWithBackfill:
 
 
 class TestSessionStoreRewriteTranscript:
-    """Regression: /retry and /undo must persist truncated history to disk."""
+    """Regression: /retry and /undo must persist truncated history to DB."""
 
     @pytest.fixture()
-    def store(self, tmp_path):
+    def store(self, tmp_path, monkeypatch):
+        import hermes_state
+        monkeypatch.setattr(hermes_state, "DEFAULT_DB_PATH", tmp_path / "state.db")
         config = GatewayConfig()
-        with patch("gateway.session.SessionStore._ensure_loaded"):
-            s = SessionStore(sessions_dir=tmp_path, config=config)
-        s._db = None  # no SQLite for these tests
-        s._loaded = True
+        s = SessionStore(sessions_dir=tmp_path, config=config)
         return s
 
-    def test_rewrite_replaces_jsonl(self, store, tmp_path):
+    def test_rewrite_replaces_transcript(self, store, tmp_path):
         session_id = "test_session_1"
+        store._db.create_session(session_id=session_id, source="test")
         # Write initial transcript
         for msg in [
             {"role": "user", "content": "hello"},
@@ -538,6 +536,7 @@ class TestSessionStoreRewriteTranscript:
 
     def test_rewrite_with_empty_list(self, store):
         session_id = "test_session_2"
+        store._db.create_session(session_id=session_id, source="test")
         store.append_to_transcript(session_id, {"role": "user", "content": "hi"})
 
         store.rewrite_transcript(session_id, [])
@@ -546,171 +545,28 @@ class TestSessionStoreRewriteTranscript:
         assert reloaded == []
 
 
-class TestLoadTranscriptCorruptLines:
-    """Regression: corrupt JSONL lines (e.g. from mid-write crash) must be
-    skipped instead of crashing the entire transcript load.  GH-1193."""
+class TestLoadTranscriptDBOnly:
+    """After spec 002, load_transcript reads only from state.db."""
 
-    @pytest.fixture()
-    def store(self, tmp_path):
+    def test_db_only_returns_empty_for_nonexistent(self, tmp_path, monkeypatch):
+        import hermes_state
+        monkeypatch.setattr(hermes_state, "DEFAULT_DB_PATH", tmp_path / "state.db")
         config = GatewayConfig()
-        with patch("gateway.session.SessionStore._ensure_loaded"):
-            s = SessionStore(sessions_dir=tmp_path, config=config)
-        s._db = None
-        s._loaded = True
-        return s
-
-    def test_corrupt_line_skipped(self, store, tmp_path):
-        session_id = "corrupt_test"
-        transcript_path = store.get_transcript_path(session_id)
-        transcript_path.parent.mkdir(parents=True, exist_ok=True)
-        with open(transcript_path, "w") as f:
-            f.write('{"role": "user", "content": "hello"}\n')
-            f.write('{"role": "assistant", "content": "hi th')  # truncated
-            f.write("\n")
-            f.write('{"role": "user", "content": "goodbye"}\n')
-
-        messages = store.load_transcript(session_id)
-        assert len(messages) == 2
-        assert messages[0]["content"] == "hello"
-        assert messages[1]["content"] == "goodbye"
-
-    def test_all_lines_corrupt_returns_empty(self, store, tmp_path):
-        session_id = "all_corrupt"
-        transcript_path = store.get_transcript_path(session_id)
-        transcript_path.parent.mkdir(parents=True, exist_ok=True)
-        with open(transcript_path, "w") as f:
-            f.write("not json at all\n")
-            f.write("{truncated\n")
-
-        messages = store.load_transcript(session_id)
-        assert messages == []
-
-    def test_valid_transcript_unaffected(self, store, tmp_path):
-        session_id = "valid_test"
-        store.append_to_transcript(session_id, {"role": "user", "content": "a"})
-        store.append_to_transcript(session_id, {"role": "assistant", "content": "b"})
-
-        messages = store.load_transcript(session_id)
-        assert len(messages) == 2
-        assert messages[0]["content"] == "a"
-        assert messages[1]["content"] == "b"
-
-
-class TestLoadTranscriptPreferLongerSource:
-    """Regression: load_transcript must return whichever source (SQLite or JSONL)
-    has more messages to prevent silent truncation.  GH-3212."""
-
-    @pytest.fixture()
-    def store_with_db(self, tmp_path):
-        """SessionStore with both SQLite and JSONL active."""
-        from hermes_state import SessionDB
-
-        config = GatewayConfig()
-        with patch("gateway.session.SessionStore._ensure_loaded"):
-            s = SessionStore(sessions_dir=tmp_path, config=config)
-        s._db = SessionDB(db_path=tmp_path / "state.db")
-        s._loaded = True
-        return s
-
-    def test_jsonl_longer_than_sqlite_returns_jsonl(self, store_with_db):
-        """Legacy session: JSONL has full history, SQLite has only recent turn."""
-        sid = "legacy_session"
-        store_with_db._db.create_session(session_id=sid, source="gateway", model="m")
-        # JSONL has 10 messages (legacy history — written before SQLite existed)
-        for i in range(10):
-            role = "user" if i % 2 == 0 else "assistant"
-            store_with_db.append_to_transcript(
-                sid, {"role": role, "content": f"msg-{i}"}, skip_db=True,
-            )
-        # SQLite has only 2 messages (recent turn after migration)
-        store_with_db._db.append_message(session_id=sid, role="user", content="new-q")
-        store_with_db._db.append_message(session_id=sid, role="assistant", content="new-a")
-
-        result = store_with_db.load_transcript(sid)
-        assert len(result) == 10
-        assert result[0]["content"] == "msg-0"
-
-    def test_sqlite_longer_than_jsonl_returns_sqlite(self, store_with_db):
-        """Fully migrated session: SQLite has more (JSONL stopped growing)."""
-        sid = "migrated_session"
-        store_with_db._db.create_session(session_id=sid, source="gateway", model="m")
-        # JSONL has 2 old messages
-        store_with_db.append_to_transcript(
-            sid, {"role": "user", "content": "old-q"}, skip_db=True,
-        )
-        store_with_db.append_to_transcript(
-            sid, {"role": "assistant", "content": "old-a"}, skip_db=True,
-        )
-        # SQLite has 4 messages (superset after migration)
-        for i in range(4):
-            role = "user" if i % 2 == 0 else "assistant"
-            store_with_db._db.append_message(session_id=sid, role=role, content=f"db-{i}")
-
-        result = store_with_db.load_transcript(sid)
-        assert len(result) == 4
-        assert result[0]["content"] == "db-0"
-
-    def test_sqlite_empty_falls_back_to_jsonl(self, store_with_db):
-        """No SQLite rows — falls back to JSONL (original behavior preserved)."""
-        sid = "no_db_rows"
-        store_with_db.append_to_transcript(
-            sid, {"role": "user", "content": "hello"}, skip_db=True,
-        )
-        store_with_db.append_to_transcript(
-            sid, {"role": "assistant", "content": "hi"}, skip_db=True,
-        )
-
-        result = store_with_db.load_transcript(sid)
-        assert len(result) == 2
-        assert result[0]["content"] == "hello"
-
-    def test_both_empty_returns_empty(self, store_with_db):
-        """Neither source has data — returns empty list."""
-        result = store_with_db.load_transcript("nonexistent")
+        store = SessionStore(sessions_dir=tmp_path, config=config)
+        result = store.load_transcript("nonexistent")
         assert result == []
 
-    def test_equal_length_prefers_sqlite(self, store_with_db):
-        """When both have same count, SQLite wins (has richer fields like reasoning)."""
-        sid = "equal_session"
-        store_with_db._db.create_session(session_id=sid, source="gateway", model="m")
-        # Write 2 messages to JSONL only
-        store_with_db.append_to_transcript(
-            sid, {"role": "user", "content": "jsonl-q"}, skip_db=True,
-        )
-        store_with_db.append_to_transcript(
-            sid, {"role": "assistant", "content": "jsonl-a"}, skip_db=True,
-        )
-        # Write 2 different messages to SQLite only
-        store_with_db._db.append_message(session_id=sid, role="user", content="db-q")
-        store_with_db._db.append_message(session_id=sid, role="assistant", content="db-a")
+    def test_db_only_returns_messages(self, tmp_path, monkeypatch):
+        import hermes_state
+        monkeypatch.setattr(hermes_state, "DEFAULT_DB_PATH", tmp_path / "state.db")
+        config = GatewayConfig()
+        store = SessionStore(sessions_dir=tmp_path, config=config)
+        sid = "db_only_session"
+        store._db.create_session(session_id=sid, source="gateway", model="m")
+        store._db.append_message(session_id=sid, role="user", content="db-q")
+        store._db.append_message(session_id=sid, role="assistant", content="db-a")
 
-        result = store_with_db.load_transcript(sid)
-        assert len(result) == 2
-        # Should be the SQLite version (equal count → prefers SQLite)
-        assert result[0]["content"] == "db-q"
-
-    def test_unreadable_jsonl_returns_sqlite(self, store_with_db, monkeypatch):
-        """Unreadable legacy JSONL must not hide valid SQLite history."""
-        sid = "unreadable_jsonl"
-        store_with_db._db.create_session(session_id=sid, source="gateway", model="m")
-        store_with_db._db.append_message(session_id=sid, role="user", content="db-q")
-        store_with_db._db.append_message(session_id=sid, role="assistant", content="db-a")
-
-        transcript_path = store_with_db.get_transcript_path(sid)
-        transcript_path.parent.mkdir(parents=True, exist_ok=True)
-        transcript_path.write_text('{"role": "user", "content": "jsonl-q"}\n', encoding="utf-8")
-
-        real_open = builtins.open
-
-        def raise_for_transcript(path, *args, **kwargs):
-            mode = args[0] if args else kwargs.get("mode", "r")
-            if Path(path) == transcript_path and "r" in mode:
-                raise OSError("simulated unreadable transcript")
-            return real_open(path, *args, **kwargs)
-
-        monkeypatch.setattr(builtins, "open", raise_for_transcript)
-
-        result = store_with_db.load_transcript(sid)
+        result = store.load_transcript(sid)
         assert len(result) == 2
         assert result[0]["content"] == "db-q"
         assert result[1]["content"] == "db-a"

tests/gateway/test_session_dm_thread_seeding.py

@@ -22,13 +22,18 @@ from gateway.session import SessionSource, SessionStore, build_session_key
 
 
 @pytest.fixture()
-def store(tmp_path):
-    """SessionStore with no SQLite, for fast unit tests."""
+def store(tmp_path, monkeypatch):
+    """SessionStore with SQLite — load_transcript reads from DB only.
+
+    Pin DEFAULT_DB_PATH to tmp_path so SessionDB() can't write to the real
+    ~/.hermes/state.db. (DEFAULT_DB_PATH is a module-level constant computed
+    at hermes_state import time, before pytest's HERMES_HOME monkeypatch
+    fires — the autouse fixture's HERMES_HOME override doesn't help here.)
+    """
+    import hermes_state
+    monkeypatch.setattr(hermes_state, "DEFAULT_DB_PATH", tmp_path / "state.db")
     config = GatewayConfig()
-    with patch("gateway.session.SessionStore._ensure_loaded"):
-        s = SessionStore(sessions_dir=tmp_path, config=config)
-    s._db = None
-    s._loaded = True
+    s = SessionStore(sessions_dir=tmp_path, config=config)
     return s
 
 

tests/gateway/test_telegram_group_gating.py

@@ -1,8 +1,11 @@
+import asyncio
 import json
 from types import SimpleNamespace
 from unittest.mock import AsyncMock
 
 from gateway.config import Platform, PlatformConfig, load_gateway_config
+from gateway.platforms.base import MessageType
+from gateway.session import SessionSource
 
 
 def _make_adapter(
@@ -15,7 +18,9 @@ def _make_adapter(
     allow_from=None,
     group_allow_from=None,
     allowed_chats=None,
+    group_allowed_chats=None,
     guest_mode=None,
+    observe_unmentioned_group_messages=None,
     bot_username="hermes_bot",
 ):
     from gateway.platforms.telegram import TelegramAdapter
@@ -49,8 +54,14 @@ def _make_adapter(
         # environment; production adapters without this explicit key still fall
         # back to the env var.
         extra["allowed_chats"] = []
+    if group_allowed_chats is not None:
+        extra["group_allowed_chats"] = group_allowed_chats
+    else:
+        extra["group_allowed_chats"] = []
     if guest_mode is not None:
         extra["guest_mode"] = guest_mode
+    if observe_unmentioned_group_messages is not None:
+        extra["observe_unmentioned_group_messages"] = observe_unmentioned_group_messages
 
     adapter = object.__new__(TelegramAdapter)
     adapter.platform = Platform.TELEGRAM
@@ -60,7 +71,12 @@ def _make_adapter(
     adapter._pending_text_batches = {}
     adapter._pending_text_batch_tasks = {}
     adapter._text_batch_delay_seconds = 0.01
+    adapter._text_batch_split_delay_seconds = 0.01
     adapter._mention_patterns = adapter._compile_mention_patterns()
+    adapter._forum_lock = asyncio.Lock()
+    adapter._forum_command_registered = set()
+    adapter._active_sessions = {}
+    adapter._pending_messages = {}
     # Trigger-gating tests don't exercise the allowlist gate (added by
     # #23795 + #24468).  Force-authorize all senders so the trigger logic
     # under test runs.  Without this, every fake message hits the new
@@ -74,6 +90,7 @@ def _group_message(
     *,
     chat_id=-100,
     from_user_id=111,
+    from_user_name="Alice Example",
     thread_id=None,
     reply_to_bot=False,
     entities=None,
@@ -82,29 +99,34 @@ def _group_message(
 ):
     reply_to_message = None
     if reply_to_bot:
-        reply_to_message = SimpleNamespace(from_user=SimpleNamespace(id=999))
+        reply_to_message = SimpleNamespace(from_user=SimpleNamespace(id=999), message_id=10, text="previous bot reply", caption=None)
     return SimpleNamespace(
+        message_id=42,
         text=text,
         caption=caption,
         entities=entities or [],
         caption_entities=caption_entities or [],
         message_thread_id=thread_id,
-        chat=SimpleNamespace(id=chat_id, type="group"),
-        from_user=SimpleNamespace(id=from_user_id),
+        is_topic_message=thread_id is not None,
+        chat=SimpleNamespace(id=chat_id, type="group", title="Test Group", is_forum=thread_id is not None),
+        from_user=SimpleNamespace(id=from_user_id, full_name=from_user_name, first_name=from_user_name.split()[0]),
         reply_to_message=reply_to_message,
+        date=None,
     )
 
 
 def _dm_message(text="hello", *, from_user_id=111):
     return SimpleNamespace(
+        message_id=43,
         text=text,
         caption=None,
         entities=[],
         caption_entities=[],
         message_thread_id=None,
-        chat=SimpleNamespace(id=from_user_id, type="private"),
-        from_user=SimpleNamespace(id=from_user_id),
+        chat=SimpleNamespace(id=from_user_id, type="private", full_name="Alice Example", title=None, is_forum=False),
+        from_user=SimpleNamespace(id=from_user_id, full_name="Alice Example", first_name="Alice"),
         reply_to_message=None,
+        date=None,
     )
 
 
@@ -134,6 +156,157 @@ def test_group_messages_can_be_opened_via_config():
     assert adapter._should_process_message(_group_message("hello everyone")) is True
 
 
+def test_unmentioned_group_messages_can_be_observed_without_dispatching():
+    async def _run():
+        adapter = _make_adapter(
+            require_mention=True,
+            allowed_chats=["-100"],
+            group_allowed_chats=["-100"],
+            observe_unmentioned_group_messages=True,
+        )
+        store = _FakeSessionStore()
+        adapter._session_store = store
+        update = SimpleNamespace(
+            update_id=1001,
+            message=_group_message("side chatter"),
+            effective_message=None,
+        )
+
+        await adapter._handle_text_message(update, SimpleNamespace())
+
+        adapter._message_handler.assert_not_awaited()
+        assert len(store.messages) == 1
+        session_id, message, skip_db = store.messages[0]
+        assert session_id == "telegram-group-session"
+        assert skip_db is False
+        assert message["role"] == "user"
+        assert message["content"] == "[Alice Example|111]\nside chatter"
+        assert message["observed"] is True
+        assert message["message_id"] == "42"
+        assert store.sources[0].chat_id == "-100"
+        assert store.sources[0].chat_type == "group"
+        assert store.sources[0].user_id is None
+        assert store.sources[0].user_name is None
+
+    asyncio.run(_run())
+
+
+def test_observed_group_context_uses_shared_source_and_prompt_for_later_mentions():
+    async def _run():
+        adapter = _make_adapter(
+            require_mention=True,
+            allowed_chats=["-100"],
+            group_allowed_chats=["-100"],
+            observe_unmentioned_group_messages=True,
+        )
+        adapter._session_store = _FakeSessionStore()
+        text = "@hermes_bot what did Alice say?"
+        msg = _group_message(
+            text,
+            from_user_id=222,
+            from_user_name="Bob Example",
+            entities=[_mention_entity(text)],
+        )
+        event = adapter._build_message_event(msg, MessageType.TEXT, update_id=1003)
+        event.text = adapter._clean_bot_trigger_text(event.text)
+        event.channel_prompt = "Existing topic prompt"
+
+        event = adapter._apply_telegram_group_observe_attribution(event)
+
+        assert event.source.chat_id == "-100"
+        assert event.source.chat_type == "group"
+        assert event.source.user_id is None
+        assert event.source.user_name is None
+        assert event.text == "[Bob Example|222]\nwhat did Alice say?"
+        assert "Existing topic prompt" in event.channel_prompt
+        assert "observed Telegram group context" in event.channel_prompt
+        assert "current new message" in event.channel_prompt
+
+    asyncio.run(_run())
+
+
+def test_unmentioned_group_observe_requires_chat_allowlist_for_shared_context():
+    async def _run():
+        adapter = _make_adapter(
+            require_mention=True,
+            allowed_chats=["-100"],
+            observe_unmentioned_group_messages=True,
+        )
+        store = _FakeSessionStore()
+        adapter._session_store = store
+        update = SimpleNamespace(
+            update_id=1004,
+            message=_group_message("side chatter"),
+            effective_message=None,
+        )
+
+        await adapter._handle_text_message(update, SimpleNamespace())
+
+        adapter._message_handler.assert_not_awaited()
+        assert store.messages == []
+
+    asyncio.run(_run())
+
+
+def test_shared_group_observe_source_is_authorized_by_group_allowed_chats(monkeypatch):
+    from gateway.run import GatewayRunner
+
+    runner = object.__new__(GatewayRunner)
+    source = SessionSource(
+        platform=Platform.TELEGRAM,
+        chat_id="-100",
+        chat_type="group",
+        user_id=None,
+        user_name=None,
+    )
+
+    monkeypatch.setenv("TELEGRAM_GROUP_ALLOWED_CHATS", "-100")
+    monkeypatch.delenv("TELEGRAM_ALLOWED_CHATS", raising=False)
+
+    assert runner._is_user_authorized(source) is True
+
+
+def test_unmentioned_group_observe_respects_chat_allowlist():
+    async def _run():
+        adapter = _make_adapter(
+            require_mention=True,
+            allowed_chats=["-200"],
+            group_allowed_chats=["-200"],
+            observe_unmentioned_group_messages=True,
+        )
+        store = _FakeSessionStore()
+        adapter._session_store = store
+        update = SimpleNamespace(
+            update_id=1002,
+            message=_group_message("side chatter", chat_id=-201),
+            effective_message=None,
+        )
+
+        await adapter._handle_text_message(update, SimpleNamespace())
+
+        adapter._message_handler.assert_not_awaited()
+        assert store.messages == []
+
+    asyncio.run(_run())
+
+
+class _FakeSessionEntry:
+    session_id = "telegram-group-session"
+
+
+class _FakeSessionStore:
+    def __init__(self):
+        self.sources = []
+        self.messages = []
+
+    def get_or_create_session(self, source):
+        self.sources.append(source)
+        return _FakeSessionEntry()
+
+    def append_to_transcript(self, session_id, message, skip_db=False):
+        self.messages.append((session_id, message, skip_db))
+
+
 def test_group_messages_can_require_direct_trigger_via_config():
     adapter = _make_adapter(require_mention=True)
 
@@ -349,12 +522,15 @@ def test_config_bridges_telegram_group_settings(monkeypatch, tmp_path):
         "  require_mention: true\n"
         "  guest_mode: true\n"
         "  exclusive_bot_mentions: true\n"
+        "  observe_unmentioned_group_messages: true\n"
         "  mention_patterns:\n"
         "    - \"^\\\\s*chompy\\\\b\"\n"
         "  free_response_chats:\n"
         "    - \"-123\"\n"
         "  allowed_chats:\n"
         "    - \"-100\"\n"
+        "  group_allowed_chats:\n"
+        "    - \"-100\"\n"
         "  allowed_topics:\n"
         "    - 8\n",
         encoding="utf-8",
@@ -365,8 +541,10 @@ def test_config_bridges_telegram_group_settings(monkeypatch, tmp_path):
     monkeypatch.delenv("TELEGRAM_MENTION_PATTERNS", raising=False)
     monkeypatch.delenv("TELEGRAM_EXCLUSIVE_BOT_MENTIONS", raising=False)
     monkeypatch.delenv("TELEGRAM_GUEST_MODE", raising=False)
+    monkeypatch.delenv("TELEGRAM_OBSERVE_UNMENTIONED_GROUP_MESSAGES", raising=False)
     monkeypatch.delenv("TELEGRAM_FREE_RESPONSE_CHATS", raising=False)
     monkeypatch.delenv("TELEGRAM_ALLOWED_CHATS", raising=False)
+    monkeypatch.delenv("TELEGRAM_GROUP_ALLOWED_CHATS", raising=False)
     monkeypatch.delenv("TELEGRAM_ALLOWED_TOPICS", raising=False)
 
     config = load_gateway_config()
@@ -374,17 +552,21 @@ def test_config_bridges_telegram_group_settings(monkeypatch, tmp_path):
     assert config is not None
     assert __import__("os").environ["TELEGRAM_REQUIRE_MENTION"] == "true"
     assert __import__("os").environ["TELEGRAM_GUEST_MODE"] == "true"
+    assert __import__("os").environ["TELEGRAM_OBSERVE_UNMENTIONED_GROUP_MESSAGES"] == "true"
     assert __import__("os").environ["TELEGRAM_EXCLUSIVE_BOT_MENTIONS"] == "true"
     assert json.loads(__import__("os").environ["TELEGRAM_MENTION_PATTERNS"]) == [r"^\s*chompy\b"]
     assert __import__("os").environ["TELEGRAM_FREE_RESPONSE_CHATS"] == "-123"
     assert __import__("os").environ["TELEGRAM_ALLOWED_CHATS"] == "-100"
+    assert __import__("os").environ["TELEGRAM_GROUP_ALLOWED_CHATS"] == "-100"
     assert __import__("os").environ["TELEGRAM_ALLOWED_TOPICS"] == "8"
     tg_cfg = config.platforms.get(Platform.TELEGRAM)
     assert tg_cfg is not None
     assert tg_cfg.extra.get("guest_mode") is True
     assert tg_cfg.extra.get("allowed_chats") == ["-100"]
+    assert tg_cfg.extra.get("group_allowed_chats") == ["-100"]
     assert tg_cfg.extra.get("allowed_topics") == [8]
     assert tg_cfg.extra.get("exclusive_bot_mentions") is True
+    assert tg_cfg.extra.get("observe_unmentioned_group_messages") is True
 
 
 def test_config_bridges_telegram_user_allowlists(monkeypatch, tmp_path):
@@ -518,3 +700,186 @@ def test_config_bridges_telegram_ignored_threads(monkeypatch, tmp_path):
 
     assert config is not None
     assert __import__("os").environ["TELEGRAM_IGNORED_THREADS"] == "31,42"
+
+
+# ---------------------------------------------------------------------------
+# Helpers for location / media observe+attribution tests
+# ---------------------------------------------------------------------------
+
+def _group_location_message(
+    *,
+    chat_id=-100,
+    from_user_id=111,
+    from_user_name="Alice Example",
+    lat=37.7749,
+    lon=-122.4194,
+):
+    return SimpleNamespace(
+        message_id=50,
+        text=None,
+        caption=None,
+        entities=[],
+        caption_entities=[],
+        message_thread_id=None,
+        is_topic_message=False,
+        chat=SimpleNamespace(id=chat_id, type="group", title="Test Group", is_forum=False),
+        from_user=SimpleNamespace(
+            id=from_user_id, full_name=from_user_name,
+            first_name=from_user_name.split()[0],
+        ),
+        reply_to_message=None,
+        date=None,
+        location=SimpleNamespace(latitude=lat, longitude=lon),
+        venue=None,
+        sticker=None,
+        photo=None,
+        video=None,
+        audio=None,
+        voice=None,
+        document=None,
+    )
+
+
+def _group_voice_message(
+    *,
+    chat_id=-100,
+    from_user_id=111,
+    from_user_name="Alice Example",
+    caption=None,
+):
+    return SimpleNamespace(
+        message_id=51,
+        text=None,
+        caption=caption,
+        entities=[],
+        caption_entities=[],
+        message_thread_id=None,
+        is_topic_message=False,
+        chat=SimpleNamespace(id=chat_id, type="group", title="Test Group", is_forum=False),
+        from_user=SimpleNamespace(
+            id=from_user_id, full_name=from_user_name,
+            first_name=from_user_name.split()[0],
+        ),
+        reply_to_message=None,
+        date=None,
+        location=None,
+        venue=None,
+        sticker=None,
+        photo=None,
+        video=None,
+        audio=None,
+        voice=SimpleNamespace(
+            get_file=AsyncMock(side_effect=Exception("simulated download failure"))
+        ),
+        document=None,
+    )
+
+
+# ---------------------------------------------------------------------------
+# Observe + attribution parity: location messages
+# ---------------------------------------------------------------------------
+
+def test_unmentioned_location_message_observed_in_group():
+    async def _run():
+        adapter = _make_adapter(
+            require_mention=True,
+            allowed_chats=["-100"],
+            group_allowed_chats=["-100"],
+            observe_unmentioned_group_messages=True,
+        )
+        store = _FakeSessionStore()
+        adapter._session_store = store
+        update = SimpleNamespace(
+            update_id=2001,
+            message=_group_location_message(),
+            effective_message=None,
+        )
+
+        await adapter._handle_location_message(update, SimpleNamespace())
+
+        adapter._message_handler.assert_not_awaited()
+        assert len(store.messages) == 1
+        _, message, _ = store.messages[0]
+        assert message["observed"] is True
+        assert store.sources[0].user_id is None
+
+    asyncio.run(_run())
+
+
+def test_triggered_location_message_uses_shared_session_in_observe_mode():
+    async def _run():
+        adapter = _make_adapter(
+            require_mention=False,
+            group_allowed_chats=["-100"],
+            observe_unmentioned_group_messages=True,
+        )
+        adapter.handle_message = AsyncMock()
+        update = SimpleNamespace(
+            update_id=2002,
+            message=_group_location_message(),
+            effective_message=None,
+        )
+
+        await adapter._handle_location_message(update, SimpleNamespace())
+
+        adapter.handle_message.assert_awaited_once()
+        event = adapter.handle_message.call_args[0][0]
+        assert event.source.user_id is None
+        assert "[Alice Example|111]" in event.text
+
+    asyncio.run(_run())
+
+
+# ---------------------------------------------------------------------------
+# Observe + attribution parity: media messages (voice as representative)
+# ---------------------------------------------------------------------------
+
+def test_unmentioned_voice_message_observed_in_group():
+    async def _run():
+        adapter = _make_adapter(
+            require_mention=True,
+            allowed_chats=["-100"],
+            group_allowed_chats=["-100"],
+            observe_unmentioned_group_messages=True,
+        )
+        store = _FakeSessionStore()
+        adapter._session_store = store
+        update = SimpleNamespace(
+            update_id=3001,
+            message=_group_voice_message(),
+            effective_message=None,
+        )
+
+        await adapter._handle_media_message(update, SimpleNamespace())
+
+        adapter._message_handler.assert_not_awaited()
+        assert len(store.messages) == 1
+        _, message, _ = store.messages[0]
+        assert message["observed"] is True
+        assert store.sources[0].user_id is None
+
+    asyncio.run(_run())
+
+
+def test_triggered_voice_message_uses_shared_session_in_observe_mode():
+    async def _run():
+        adapter = _make_adapter(
+            require_mention=False,
+            group_allowed_chats=["-100"],
+            observe_unmentioned_group_messages=True,
+        )
+        adapter.handle_message = AsyncMock()
+        update = SimpleNamespace(
+            update_id=3002,
+            message=_group_voice_message(caption="check this audio"),
+            effective_message=None,
+        )
+
+        await adapter._handle_media_message(update, SimpleNamespace())
+
+        adapter.handle_message.assert_awaited_once()
+        event = adapter.handle_message.call_args[0][0]
+        assert event.source.user_id is None
+        assert "[Alice Example|111]" in event.text
+
+    asyncio.run(_run())