review(dream): harden line-age annotation per review feedback

Follow-up to #3212, fully backward compatible:

- Extract the 14-day staleness threshold as `_STALE_THRESHOLD_DAYS` module
  constant and pass it into the Phase 1 prompt template as
  `{{ stale_threshold_days }}`. The number lived in three places before
  (code threshold, prompt instruction, docstring); now there is one.
- Add `DreamConfig.annotate_line_ages` (default True = current behavior)
  and propagate it through `Dream.__init__` and the gateway wiring in
  cli/commands.py. Gives users a knob to disable the feature without a
  code patch if an LLM reacts poorly to the `← Nd` suffix.
- Harden `_annotate_with_ages` against dirty working trees: when HEAD
  blob line count disagrees with the working-tree content length, skip
  annotation entirely instead of assigning ages to the wrong lines. The
  previous `i >= len(ages)` guard only handled one direction of the
  mismatch.
- Inline-comment the `max_iterations` 10→15 bump with a pointer to
  exp002 so future blame has context.
- Add 4 regression tests: end-to-end `← 30d` reaches prompt, 14/15
  threshold boundary, `annotate_line_ages=False` bypasses git entirely
  (verified via `assert_not_called`), length-mismatch defense, and
  template-var rendering.

Made-with: Cursor

tests/agent/test_dream.py

@@ -2,11 +2,12 @@
 
 import pytest
 
-from unittest.mock import AsyncMock, MagicMock
+from unittest.mock import AsyncMock, MagicMock, patch
 
 from nanobot.agent.memory import Dream, MemoryStore
 from nanobot.agent.runner import AgentRunResult
 from nanobot.agent.skills import BUILTIN_SKILLS_DIR
+from nanobot.utils.gitstore import LineAge
 
 
 @pytest.fixture
@@ -175,3 +176,83 @@ class TestDreamRun:
         user_msg = call_args.kwargs.get("messages", call_args[1].get("messages"))[1]["content"]
         assert "## Current MEMORY.md" in user_msg
 
+    async def test_phase1_prompt_carries_age_suffix_for_stale_lines(
+        self, dream, mock_provider, mock_runner, store,
+    ):
+        """End-to-end: ages >14d must appear verbatim in the LLM prompt, ages ≤14d must not."""
+        # MEMORY.md fixture has 2 non-blank lines ("# Memory" and "- Project X active").
+        # Inject four ages to cover threshold boundaries: >14 suffix, ==14 no suffix, <14 no suffix.
+        store.write_memory("# Memory\n- Project X active\n- fresh item\n- edge case line")
+        store.append_history("some event")
+        mock_provider.chat_with_retry.return_value = MagicMock(content="[SKIP]")
+        mock_runner.run = AsyncMock(return_value=_make_run_result())
+
+        fake_ages = [
+            LineAge(age_days=30),   # "# Memory"        → should get ← 30d
+            LineAge(age_days=20),   # "- Project X..."  → should get ← 20d
+            LineAge(age_days=14),   # "- fresh item"    → ==14, threshold is strictly >14, no suffix
+            LineAge(age_days=5),    # "- edge case..."  → no suffix
+        ]
+        with patch.object(store.git, "line_ages", return_value=fake_ages):
+            await dream.run()
+
+        call_args = mock_provider.chat_with_retry.call_args
+        user_msg = call_args.kwargs.get("messages", call_args[1].get("messages"))[1]["content"]
+        memory_section = user_msg.split("## Current MEMORY.md")[1].split("## Current SOUL.md")[0]
+        assert "\u2190 30d" in memory_section
+        assert "\u2190 20d" in memory_section
+        assert "\u2190 14d" not in memory_section
+        assert "\u2190 5d" not in memory_section
+
+    async def test_phase1_skips_annotation_when_disabled(
+        self, dream, mock_provider, mock_runner, store,
+    ):
+        """`annotate_line_ages=False` must bypass the git lookup entirely and keep MEMORY.md raw."""
+        store.append_history("some event")
+        mock_provider.chat_with_retry.return_value = MagicMock(content="[SKIP]")
+        mock_runner.run = AsyncMock(return_value=_make_run_result())
+
+        dream.annotate_line_ages = False
+        # line_ages must be bypassed entirely — verify with a spy rather than a
+        # raising side_effect, because _annotate_with_ages catches Exception
+        # (which swallows AssertionError) and would hide an accidental call.
+        with patch.object(store.git, "line_ages") as mock_line_ages:
+            await dream.run()
+            mock_line_ages.assert_not_called()
+
+        call_args = mock_provider.chat_with_retry.call_args
+        user_msg = call_args.kwargs.get("messages", call_args[1].get("messages"))[1]["content"]
+        assert "\u2190" not in user_msg
+
+    async def test_phase1_skips_annotation_on_line_ages_length_mismatch(
+        self, dream, mock_provider, mock_runner, store,
+    ):
+        """If ages length != lines length (dirty working tree), skip annotation instead of mis-tagging."""
+        # MEMORY.md has 2 non-blank lines but we hand back only 1 age → mismatch.
+        store.append_history("some event")
+        mock_provider.chat_with_retry.return_value = MagicMock(content="[SKIP]")
+        mock_runner.run = AsyncMock(return_value=_make_run_result())
+
+        with patch.object(store.git, "line_ages", return_value=[LineAge(age_days=999)]):
+            await dream.run()
+
+        call_args = mock_provider.chat_with_retry.call_args
+        user_msg = call_args.kwargs.get("messages", call_args[1].get("messages"))[1]["content"]
+        memory_section = user_msg.split("## Current MEMORY.md")[1].split("## Current SOUL.md")[0]
+        # No age arrow at all — we refused to annotate rather than tag the wrong line.
+        assert "\u2190" not in memory_section
+
+    async def test_phase1_prompt_uses_threshold_from_template_var(
+        self, dream, mock_provider, mock_runner, store,
+    ):
+        """System prompt should reference the stale-threshold constant, not a hardcoded 14."""
+        store.append_history("some event")
+        mock_provider.chat_with_retry.return_value = MagicMock(content="[SKIP]")
+        mock_runner.run = AsyncMock(return_value=_make_run_result())
+
+        await dream.run()
+
+        system_msg = mock_provider.chat_with_retry.call_args.kwargs["messages"][0]["content"]
+        # The template renders with stale_threshold_days=14 → LLM must see "N>14"
+        assert "N>14" in system_msg
+