fix(agent): bound remaining memory/history pollution paths from #3412

#3412 stopped the headline raw_archive bloat but left four adjacent leaks
on the same pollution chain:

- archive() success path appended uncapped LLM summaries to history.jsonl,
  so a misbehaving LLM could re-open the #3412 bug from the happy path.
- maybe_consolidate_by_tokens did not advance last_consolidated when
  archive() fell back to raw_archive, causing duplicate [RAW] dumps of
  the same chunk on every subsequent call.
- Dream's Phase 1/2 prompt injected MEMORY.md / SOUL.md / USER.md and
  each history entry without caps, so any legacy oversized record (or an
  unbounded user edit) would blow past the context window every dream.
- append_history itself had no default cap, leaving future new callers
  one forgotten-cap-away from the same vector.

Changes:

- Cap LLM-produced summaries at 8K chars (_ARCHIVE_SUMMARY_MAX_CHARS)
  before writing to history.jsonl.
- Advance session.last_consolidated after archive() regardless of whether
  it summarized or raw-archived — both outcomes materialize the chunk;
  still break the round loop on fallback so a degraded LLM isn't hammered.
- Truncate MEMORY.md / SOUL.md / USER.md and each history entry in Dream's
  Phase 1 prompt preview (Phase 2 still reaches full files via read_file).
- Add _HISTORY_ENTRY_HARD_CAP (64K) as belt-and-suspenders default in
  append_history with a once-per-store warning, so any new caller that
  forgets its own tighter cap gets caught and observable.

Layer the caps by scope: raw_archive=16K, archive summary=8K,
append_history default=64K. Tight per-caller values cover expected
payloads; the wide default only catches regressions.

Tests: +9 regression tests covering each fix. Full suite: 2372 passed.
Made-with: Cursor
This commit is contained in:
Xubin Ren
2026-04-24 04:17:19 +08:00
committed by Xubin Ren
parent 81a5af2352
commit 4531167c12
4 changed files with 222 additions and 13 deletions
+51
View File
@@ -1,5 +1,7 @@
"""Tests for the Dream class — two-phase memory consolidation via AgentRunner."""
import json
import pytest
from unittest.mock import AsyncMock, MagicMock, patch
@@ -256,3 +258,52 @@ class TestDreamRun:
# The template renders with stale_threshold_days=14 → LLM must see "N>14"
assert "N>14" in system_msg
class TestDreamPromptCaps:
"""Dream's Phase 1/2 prompt must not be poisoned by a legacy oversized
history entry or a runaway MEMORY.md. Without caps, a single pre-#3412
raw_archive dump in history.jsonl would make every subsequent Dream run
exceed the context window and silently advance the cursor past real work.
"""
async def test_phase1_caps_huge_memory_file(
self, dream, mock_provider, mock_runner, store,
):
"""A MEMORY.md much larger than _MEMORY_FILE_MAX_CHARS must be truncated
in the prompt preview (full content is still reachable via read_file)."""
store.write_memory("M" * (dream._MEMORY_FILE_MAX_CHARS * 5))
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()
user_msg = mock_provider.chat_with_retry.call_args.kwargs["messages"][1]["content"]
memory_section = user_msg.split("## Current MEMORY.md")[1].split("## Current SOUL.md")[0]
assert len(memory_section) < dream._MEMORY_FILE_MAX_CHARS + 500
async def test_phase1_caps_huge_history_entry(
self, dream, mock_provider, mock_runner, store,
):
"""A legacy oversized history entry (e.g. pre-#3412 raw_archive dump)
must not explode the Phase 1 prompt — each entry is capped in the
preview, even though the JSONL record itself stays full-size."""
# Bypass the append_history cap by writing directly, simulating a
# record that was written by an older nanobot build before any caps.
store.history_file.write_text(
json.dumps({
"cursor": 1,
"timestamp": "2026-04-01 10:00",
"content": "H" * (dream._HISTORY_ENTRY_PREVIEW_MAX_CHARS * 8),
}) + "\n",
encoding="utf-8",
)
mock_provider.chat_with_retry.return_value = MagicMock(content="[SKIP]")
mock_runner.run = AsyncMock(return_value=_make_run_result())
await dream.run()
user_msg = mock_provider.chat_with_retry.call_args.kwargs["messages"][1]["content"]
history_section = user_msg.split("## Conversation History\n")[1].split("\n\n## Current Date")[0]
assert len(history_section) < dream._HISTORY_ENTRY_PREVIEW_MAX_CHARS + 500