fix(memory): keep failed Dream batches retryable

nanobot/agent/memory.py

@@ -43,6 +43,26 @@ if TYPE_CHECKING:
 # MemoryStore — pure file I/O layer
 # ---------------------------------------------------------------------------
 
+
+class DreamRunProgress:
+    """Track tool failures that make a nominally completed Dream run unsafe to advance."""
+
+    def __init__(self) -> None:
+        self.had_tool_errors = False
+
+    async def __call__(
+        self,
+        *_args: Any,
+        tool_events: list[dict[str, Any]] | None = None,
+        **_kwargs: Any,
+    ) -> None:
+        if any(
+            isinstance(event, dict) and event.get("phase") == "error"
+            for event in tool_events or ()
+        ):
+            self.had_tool_errors = True
+
+
 class MemoryStore:
     """Pure file I/O for memory files: MEMORY.md, history.jsonl, SOUL.md, USER.md."""
 
@@ -635,10 +655,18 @@ class MemoryStore:
         return tools
 
     @staticmethod
-    def dream_run_completed(resp: object | None) -> bool:
+    def dream_run_completed(
-        """Return True only when an ephemeral Dream agent turn completed cleanly."""
+        resp: object | None,
+        *,
+        had_tool_errors: bool = False,
+    ) -> bool:
+        """Return True only when a Dream turn completed without tool failures."""
         metadata = getattr(resp, "metadata", None)
-        return isinstance(metadata, dict) and metadata.get("_stop_reason") == "completed"
+        return (
+            not had_tool_errors
+            and isinstance(metadata, dict)
+            and metadata.get("_stop_reason") == "completed"
+        )
 
     # -- message formatting utility ------------------------------------------
 

nanobot/cli/commands.py

@@ -1824,12 +1824,13 @@ def _run_gateway(
 
         # Dream is an internal job — run directly, not through the agent loop.
         if job.name == "dream":
-            from nanobot.agent.memory import MemoryStore
+            from nanobot.agent.memory import DreamRunProgress, MemoryStore
 
             dream_session_key = MemoryStore.dream_session_key
             prune_dream_sessions = MemoryStore.prune_dream_sessions
 
             store = agent.context.memory
+            progress = DreamRunProgress()
             resp = None
             diff_body = ""
             try:
@@ -1844,12 +1845,15 @@ def _run_gateway(
                     session_key=key,
                     ephemeral=True,
                     tools=store.build_dream_tools(),
-                    on_progress=_silent,
+                    on_progress=progress,
                 )
                 # The real file delta grounds the audit record; clean completion
                 # decides whether this history batch has finished processing.
                 diff_body = store.dream_content_diff()
-                completed = MemoryStore.dream_run_completed(resp)
+                completed = MemoryStore.dream_run_completed(
+                    resp,
+                    had_tool_errors=progress.had_tool_errors,
+                )
                 if completed:
                     store.set_last_dream_cursor(last_cursor)
                     if diff_body:

nanobot/command/builtin.py

@@ -404,16 +404,14 @@ async def cmd_dream(ctx: CommandContext) -> OutboundMessage:
     msg = ctx.msg
 
     async def _run_dream():
-        async def _silent(*_args, **_kwargs):
+        from nanobot.agent.memory import DreamRunProgress, MemoryStore
-            pass
-
-        from nanobot.agent.memory import MemoryStore
 
         dream_session_key = MemoryStore.dream_session_key
         build_dream_commit_message = MemoryStore.build_dream_commit_message
         prune_dream_sessions = MemoryStore.prune_dream_sessions
 
         store = loop.context.memory
+        progress = DreamRunProgress()
         content = ""
         resp = None
         diff_body = ""
@@ -434,13 +432,16 @@ async def cmd_dream(ctx: CommandContext) -> OutboundMessage:
                 session_key=key,
                 ephemeral=True,
                 tools=store.build_dream_tools(),
-                on_progress=_silent,
+                on_progress=progress,
             )
             elapsed = time.monotonic() - t0
             # The real file delta grounds the audit record; clean completion
             # decides whether this history batch has finished processing.
             diff_body = store.dream_content_diff()
-            completed = MemoryStore.dream_run_completed(resp)
+            completed = MemoryStore.dream_run_completed(
+                resp,
+                had_tool_errors=progress.had_tool_errors,
+            )
             if completed:
                 store.set_last_dream_cursor(last_cursor)
                 if diff_body:

tests/command/test_builtin_dream.py

@@ -192,6 +192,7 @@ def _build_runnable_dream(
     initialized: bool,
     content_diff: str,
     stop_reason: str = "completed",
+    tool_error: bool = False,
 ) -> tuple[CommandContext, _FakeStore]:
     """Build a /dream ctx whose run is driven by a canned stop reason + diff."""
     msg = InboundMessage(channel="cli", sender_id="u1", chat_id="direct", content="/dream")
@@ -203,6 +204,15 @@ def _build_runnable_dream(
     )
 
     async def process_direct(*args, **kwargs):
+        if tool_error:
+            await kwargs["on_progress"](
+                "",
+                tool_events=[{
+                    "phase": "error",
+                    "name": "edit_file",
+                    "error": "edit failed",
+                }],
+            )
         return OutboundMessage(
             channel="cli",
             chat_id="direct",
@@ -257,6 +267,21 @@ async def test_dream_keeps_cursor_when_incomplete_with_diff(tmp_path) -> None:
     assert "did not complete" in ctx.loop.bus.outbound[0].content
 
 
+@pytest.mark.asyncio
+async def test_dream_keeps_cursor_when_completed_after_tool_error(tmp_path) -> None:
+    """A soft tool failure must not masquerade as a verified no-op."""
+    ctx, store = _build_runnable_dream(
+        tmp_path,
+        initialized=True,
+        content_diff="",
+        tool_error=True,
+    )
+    await cmd_dream(ctx)
+    await asyncio.sleep(0)
+    assert store._last_dream_cursor == 5
+    assert "did not complete" in ctx.loop.bus.outbound[0].content
+
+
 @pytest.mark.asyncio
 async def test_dream_noop_batch_unlocks_following_history(tmp_path) -> None:
     """A no-op first batch must not starve later history entries."""