ling/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-28 06:51:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge PR #705: fix: detect, warn, and block file re-read/search loops after context compression

Browse Source 
Authored by 0xbyt4. Adds read/search loop detection, file history injection after compression, and todo filtering for active items only.
This commit is contained in:
teknium1
2026-03-10 16:17:03 -07:00
parent ad7a16dca6 912efe11b5
commit b53d5dad67
7 changed files with 523 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
run_agent.py
View File

@@ -2625,7 +2625,7 @@ class AIAgent:
if messages and messages[-1].get("_flush_sentinel") == _sentinel:
messages.pop()
def _compress_context(self, messages: list, system_message: str, *, approx_tokens: int = None) -> tuple:
def _compress_context(self, messages: list, system_message: str, *, approx_tokens: int = None, task_id: str = "default") -> tuple:
"""Compress conversation context and split the session in SQLite.
Returns:
@@ -2640,6 +2640,25 @@ class AIAgent:
if todo_snapshot:
compressed.append({"role": "user", "content": todo_snapshot})
# Preserve file-read history so the model doesn't re-read files
# it already examined before compression.
try:
from tools.file_tools import get_read_files_summary
read_files = get_read_files_summary(task_id)
if read_files:
file_list = "\n".join(
f" - {f['path']} ({', '.join(f['regions'])})"
for f in read_files
)
compressed.append({"role": "user", "content": (
"[Files already read in this session — do NOT re-read these]\n"
f"{file_list}\n"
"Use the information from the context summary above. "
"Proceed with writing, editing, or responding."
)})
except Exception:
pass # Don't break compression if file tracking fails
self._invalidate_system_prompt()
new_system_prompt = self._build_system_prompt(system_message)
self._cached_system_prompt = new_system_prompt
@@ -3225,7 +3244,8 @@ class AIAgent:
for _pass in range(3):
_orig_len = len(messages)
messages, active_system_prompt = self._compress_context(
messages, system_message, approx_tokens=_preflight_tokens
messages, system_message, approx_tokens=_preflight_tokens,
task_id=effective_task_id,
)
if len(messages) >= _orig_len:
break # Cannot compress further
@@ -3752,7 +3772,8 @@ class AIAgent:
original_len = len(messages)
messages, active_system_prompt = self._compress_context(
messages, system_message, approx_tokens=approx_tokens
messages, system_message, approx_tokens=approx_tokens,
task_id=effective_task_id,
)
if len(messages) < original_len:
@@ -3820,7 +3841,8 @@ class AIAgent:
original_len = len(messages)
messages, active_system_prompt = self._compress_context(
messages, system_message, approx_tokens=approx_tokens
messages, system_message, approx_tokens=approx_tokens,
task_id=effective_task_id,
)
if len(messages) < original_len or new_ctx and new_ctx < old_ctx:
@@ -4173,7 +4195,8 @@ class AIAgent:
if self.compression_enabled and self.context_compressor.should_compress():
messages, active_system_prompt = self._compress_context(
messages, system_message,
approx_tokens=self.context_compressor.last_prompt_tokens
approx_tokens=self.context_compressor.last_prompt_tokens,
task_id=effective_task_id,
)
# Save session log incrementally (so progress is visible even if interrupted)