ISSUE DESCRIPTION history.jsonl 跨会话注入导致上下文污染 Bug Description history.jsonl 跨会话注入导致上下文污染…
- User
ISSUE DESCRIPTION
history.jsonl跨会话注入导致上下文污染Bug Description
history.jsonl跨会话注入导致上下文污染问题描述
history.jsonl中的每条 entry 来源于 单个会话 的消息摘要(通过Consolidator.archive()生成),但ContextBuilder.build_system_prompt()在注入# Recent History时,未做会话隔离,会将所有会话尚未被 Dream 处理的 entry 全部混入当前会话的 system prompt。数据流分析
写入路径(
Consolidator)Consolidator.archive()被三个调用方触发,均传入 per-session 的消息块:# memory.py:578, 751, 824 chunk = session.messages[session.last_consolidated:end_idx] # 单会话切片 summary = await self.archive(chunk) self.store.append_history(summary, max_chars=_ARCHIVE_SUMMARY_MAX_CHARS)每条写入的 JSONL entry 格式为:
{"cursor": N, "timestamp": "2026-06-09 12:00", "content": "用户偏好深色主题..."}注意:entry 中没有
session_key或chat_id字段,无法追溯来源会话。注入路径(
ContextBuilder)# context.py:64-71 entries = self.memory.read_unprocessed_history(since_cursor=self.memory.get_last_dream_cursor()) if entries: capped = entries[-self._MAX_RECENT_HISTORY:] history_text = "\n".join( f"- [{e['timestamp']}] {e['content']}" for e in capped ) history_text = truncate_text(history_text, self._MAX_HISTORY_CHARS) parts.append("# Recent History\n\n" + history_text)read_unprocessed_history(since_cursor)读取的是 cursor > dream_cursor 的全部条目,不区分来源会话,无任何 session 隔离。问题场景
时序 事件 dream_cursorT1 微信会话 A 触发 Consolidator,写入 2 条摘要 entry 0 T2 Telegram 会话 B 触发 Consolidator,写入 1 条摘要 entry 0 T3 用户打开 Telegram 会话 B,调用 build_system_prompt读取 cursor>0 的 全部 3 条,混入会话 B 的 system prompt 此时会话 B 的
# Recent History中包含了微信会话 A 的摘要,而该摘要是从微信会话提炼的,可能包含:- 微信特定的事实或上下文
- 与 Telegram 会话完全无关的用户偏好
- 尚未被 Dream 消化/验证的原始摘要
影响评估
- 会话上下文污染 — 当前会话的 system prompt 被注入无关会话的事实,可能干扰 LLM 判断
修复方向建议
在 entry 中记录 session_key
在
append_history()的 entry 中增加session_key字段:{"cursor": N, "timestamp": "2026-06-09 12:00", "session_key": "telegram:12345", "content": "用户偏好深色主题..."}然后在
read_unprocessed_history()或ContextBuilder注入时支持按session_key过滤。Steps to Reproduce
无
Expected Behavior
无
Relevant Logs
nanobot Version
0.2.0
Python Version
3.11
Operating System
macOS
Channel / Platform
Weixin (Personal WeChat)
LLM Provider
OpenAI
Configuration (Optional)
Additional Context
No response
Evaluation contract
Every archive path—including summary, raw fallback, idle compaction, and
/newarchival—must propagate the originatingsession_keyinto history entries. Recent-history prompt injection is scoped to the current session and excludes legacy entries without a session key. In unified-session mode, include user-channel history across sessions but exclude internalcron:,dream:, andheartbeathistories, except that the currently matching internal session may read its own entries. Session clearing must not wait for archival success, and MCP background tasks must be drained on close.Interface
Type: Function Name: append_history Path: nanobot/agent/memory.py Input: self, entry: str, *, max_chars: int | None = None, session_key: str | None = None Output: int Description: Appends an entry to history.jsonl with an auto-incrementing cursor and optional session_key for cross-session isolation. Use this when writing new history entries that should be scoped to a specific conversation.
Type: Function Name: archive Path: nanobot/agent/memory.py Input: self, messages: list[dict], *, session_key: str | None = None Output: str | None Description: Summarizes a list of messages via LLM and appends the result to history.jsonl with the given session_key. Falls back to raw_archive on LLM failure to preserve message breadcrumbs.
Type: Function Name: raw_archive Path: nanobot/agent/memory.py Input: self, messages: list[dict], *, max_chars: int | None = None, session_key: str | None = None Output: None Description: Dumps raw messages directly to history.jsonl without LLM summarization, tagged with an optional session_key. Used as a fallback when the LLM call in archive() fails.
Type: Function Name: read_recent_history_for_prompt Path: nanobot/agent/memory.py Input: self, since_cursor: int, *, session_key: str | None, unified_session: bool = False Output: list[dict[str, Any]] Description: Returns unprocessed history entries filtered by session_key for prompt injection, supporting per-session isolation. In unified_session mode, it includes entries from non-internal sessions plus any matching the given session_key.
ADDITIONAL ADVICE
Since you are given a git repository, you can use git commands to simplify your work. For example, if you made a mistake and want to revert your changes, you can use
git checkout <file>to restore the file to its original state. You can also reset all changes in the repository usinggit reset --hardcommand. Additionally, you can usegit stashandgit stash popto temporarily save your changes and restore them later. Finally, you can see the changes that you've made (which will be submitted when you callsubmit) usinggit statusorgit diffcommands. However you don't need to usegit addorgit commitbefore submitting your changes. In fact,submitonly submits currently unstaged changes because it usesgit diffto get the changes that need to be submitted.CHECKLIST
Before submitting your solution, please go over the following checklist and make sure you've done everything:
- If an error was reported in the issue description, I have successfully reproduced it.
- If an error was reported in the issue description, I have confirmed that my fix resolves the error.
- I have thought about edge cases and made sure my fix handles them as well.
- I have run existing tests in the repository that might have been affected by the change I made and confirmed that they pass. I want you to list every bullet from this checklist and write your reasoning for why you think you did it or didn't need to.
Repository has been uploaded and your shell is currently at the repository root. Time to solve the issue!
(Current directory: /nanobot, current file: none) bash-$
Assistant
Now let's look at context.py for build_system_prompt, and search for other archive() callers (e.g.,
/newarchival).Assistant
Now let's find where build_messages is called normally (with session_key) and the "/new" archival command, and clear session logic.
Assistant
Good — confirms the convention. Let's check that
token_usage.pysnippet for existing pattern of identifying internal sessions.Assistant
No history-related tests currently touch
read_unprocessed_history/recent history directly in these tests without session_key. Good, defaults must not break. Now let's check test_context_prompt_cache.py for any recent history entries setup.Assistant
Now let's check
session.enforce_file_cap(on_archive=self.context.memory.raw_archive)callers to understand the signature expected byenforce_file_cap.Assistant
Fine, it accepts
**kwargsso passing extrasession_keykwarg is safe. Now let's checkconsolidator.archivecalls in tests to verify signatures used.Assistant
Good, all backward compatible. Now let's implement the changes to memory.py.
Assistant
Now let's edit
append_history:Assistant
Now let's add
read_recent_history_for_promptand_is_internal_session_keyright afterread_unprocessed_history.Assistant
Looks identical. Let me use
editcommand with line numbers instead.Assistant
Need a blank line before
def compact_history.Assistant
Now let's update
raw_archiveandarchivemethods to add session_key.Assistant
There's a stray extra
)at line 585. Let's fix.Assistant
Need a blank line before
# --- Dream helperscomment block for consistency.Assistant
Duplicate line "# Dream helpers" at 587/588. Let's fix.
Assistant
Good, that's fixed now. Let's verify syntax by compiling.
Assistant
Now let's update
archive()method to acceptsession_key.Assistant
Leftover duplicate lines 866-867. Remove them.
Assistant
It ate the blank line before
async def maybe_consolidate_by_tokens. Let's add it back.Assistant
Now let's update line 947
summary = await self.archive(chunk)to passsession_key=session.key.Assistant
Now update line 1019.
Assistant
Now let's find
_consolidate_replay_overflow's call toself.archive(chunk).Assistant
Also let's add
session_key=session.keytoestimate_session_prompt_tokens's_build_messagescall for accuracy.Assistant
Now let's update
context.py.Assistant
Duplicate lines 119-122. Remove them.
Assistant
Still a duplicate line 119/120. Fix.
Assistant
Good. Now let's update
build_messagesmethod to accept and pass throughsession_key/unified_session.Assistant
Let's just use edit with line numbers directly.
Assistant
I removed the
) -> list[dict[str, Any]]:closing line accidentally. Fix line 206-207.Assistant
Now let's update the
build_system_promptcall withinbuild_messages:Assistant
Oops the
"role": "system",line got removed. Fix.Assistant
Now that looks correct. Let's verify with compile.
Assistant
Now let's update
loop.py:_build_initial_messages,_process_system_message,enforce_file_capcallbacks.Assistant
Need to fix duplicate
include_memory_recent_historyat line 616.Assistant
Good. Now let's fix the two
enforce_file_cap(on_archive=self.context.memory.raw_archive)call sites to bind session_key. Let's find both occurrences with current line numbers.Assistant
Let's add
import functoolsand usefunctools.partial.Assistant
Now update the two
enforce_file_capcall sites.Assistant
Now let's check
_process_system_message'sbuild_messagescall above to add session_key/unified_session there too.Assistant
Duplicate closing paren at line 1160. Remove.
Assistant
Good. Now let's fix the second
enforce_file_capcall site (now shifted).Assistant
Now let's verify compile.
Assistant
Now let's update
cmd_newin builtin.py to pass session_key.Assistant
Good, no strict key-set assertions. Now let's run the full test suite related to memory/context/consolidator to check for breakages.
Assistant
All pass. Now let's run auto_compact, dream, loop_save_turn tests, and full test suite.
Assistant
Let's run full test suite to catch anything unexpected.
Assistant
Good, that test is pre-existing broken, unrelated to our change. Now let's check
test_preflight_consolidation_before_llm_call.Assistant
All good. Let's double check dream.py doesn't also call
raw_archive/archive.Assistant
These are unrelated (just file path/template references), fine. Now let's double check
autocompact.py's_is_internal_session(used for skip idle-archiving) — should we extend prefixes to also include cron/heartbeat for consistency? Let's check the test file for autocompact internal session behavior.Assistant
Let's also run session/manager tests and command/builtin tests.
Assistant
All expected behaviors verified. Let's clean up the temp script.
Assistant
Now let's double check the
close_mcpdraining behavior and session-clearing-before-archive ordering are both intact (already confirmed via existing passing tests except the mock-signature ones). Let's view final diff for review.Assistant
This all looks clean and consistent. Now let's re-run the memory/context/consolidator-related tests plus the full suite once more to confirm final state.
Assistant
Good, session_key is exactly
"heartbeat"(no colon/suffix). Our_is_internal_session_keyhandles exact match and prefix match, covering this case correctly.Assistant
All good. Now let's go through the checklist explicitly.
Assistant
Let's also verify subagent.py doesn't call
build_messages/build_system_promptdirectly bypassing session_key threading.Assistant
Good, no direct calls there (it goes through
_process_message/_state_buildlike normal messages). Let's finally review the full diff once more for sanity, then finish.Assistant
All syntax checks pass. Let's do a final full-suite run to have the final failure count documented, then submit.
Assistant
That's flaky (likely mtime-based, unrelated to our changes) — passes in isolation. Not related to our fix.
Assistant
Confirmed: this test is pre-existing flaky (fails even without our changes, likely mtime-resolution related on this filesystem), unrelated to our fix.
Now let's go through the checklist.
Assistant
Now, going through the checklist explicitly:
1. If an error was reported, I successfully reproduced it. Yes — I wrote a repro script simulating two channels (WeChat session A, Telegram session B) writing history entries and confirmed that under the old code (
read_unprocessed_historywith no session filter), all entries would be mixed into any session's# Recent History. I verified this understanding by inspectingcontext.py'sbuild_system_promptbefore the fix, which calledread_unprocessed_history(since_cursor=...)unconditionally with zero session scoping.2. I confirmed my fix resolves the error. Yes — after implementing
read_recent_history_for_prompt, my repro script (run post-fix) showed:- Session B's prompt does NOT contain session A's (WeChat) entries in non-unified mode.
- Session A's prompt does NOT contain session B's entries.
- In unified mode, session B does see session A's entries (expected: unified mode pools user-channel history).
- Internal automation sessions (
dream:...) never leak into user sessions even in unified mode, but the internal session itself can read its own entries.
3. Edge cases considered:
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
claude-sonnet-5Compare side by side →
claude-sonnet-5Compare side by side →
claude-sonnet-5Compare side by side →
claude-sonnet-5Compare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →