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

feat: improve memory prioritization + aggressive skill updates (inspired by OpenAI Codex)

Browse Source 
* feat: improve memory prioritization — user preferences over procedural knowledge

Inspired by OpenAI Codex's memory prompt improvements (openai/codex#14493)
which focus memory writes on user preferences and recurring patterns
rather than procedural task details.

Key insight: 'Optimize for reducing future user steering — the most
valuable memory prevents the user from having to repeat themselves.'

Changes:
- MEMORY_GUIDANCE (prompt_builder.py): added prioritization hierarchy
  and the core principle about reducing user steering
- MEMORY_SCHEMA (memory_tool.py): reordered WHEN TO SAVE list to put
  corrections first, added explicit PRIORITY guidance
- Memory nudge (run_agent.py): now asks specifically about preferences,
  corrections, and workflow patterns instead of generic 'anything'
- Memory flush (run_agent.py): now instructs to prioritize user
  preferences and corrections over task-specific details

* feat: more aggressive skill creation and update prompting

Press harder on skill updates — the agent should proactively patch
skills when it encounters issues during use, not wait to be asked.

Changes:
- SKILLS_GUIDANCE: 'consider saving' → 'save'; added explicit instruction
  to patch skills immediately when found outdated/wrong
- Skills header: added instruction to update loaded skills before finishing
  if they had missing steps or wrong commands
- Skill nudge: more assertive ('save the approach' not 'consider saving'),
  now also prompts for updating existing skills used in the task
- Skill nudge interval: lowered default from 15 to 10 iterations
- skill_manage schema: added 'patch it immediately' to update triggers
This commit is contained in:
Teknium
2026-03-16 06:52:32 -07:00
committed by GitHub
parent 447594be28
commit 1ecfe68675
4 changed files with 31 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
agent/prompt_builder.py
View File

@@ -73,9 +73,15 @@ DEFAULT_AGENT_IDENTITY = (
MEMORY_GUIDANCE = (
"You have persistent memory across sessions. Save durable facts using the memory "
"tool: user preferences, environment details, tool quirks, and stable conventions. "
"Memory is injected into every turn, so keep it compact. Do NOT save task progress, "
"session outcomes, or completed-work logs to memory; use session_search to recall "
"those from past transcripts."
"Memory is injected into every turn, so keep it compact and focused on facts that "
"will still matter later.\n"
"Prioritize what reduces future user steering — the most valuable memory is one "
"that prevents the user from having to correct or remind you again. "
"User preferences and recurring corrections matter more than procedural task details.\n"
"Do NOT save task progress, session outcomes, completed-work logs, or temporary TODO "
"state to memory; use session_search to recall those from past transcripts. "
"If you've discovered a new way to do something, solved a problem that could be "
"necessary later, save it as a skill with the skill tool."
)
SESSION_SEARCH_GUIDANCE = (
@@ -86,8 +92,11 @@ SESSION_SEARCH_GUIDANCE = (
SKILLS_GUIDANCE = (
"After completing a complex task (5+ tool calls), fixing a tricky error, "
"or discovering a non-trivial workflow, consider saving the approach as a "
"skill with skill_manage so you can reuse it next time."
"or discovering a non-trivial workflow, save the approach as a "
"skill with skill_manage so you can reuse it next time.\n"
"When using a skill and finding it outdated, incomplete, or wrong, "
"patch it immediately with skill_manage(action='patch') — don't wait to be asked. "
"Skills that aren't maintained become liabilities."
)
PLATFORM_HINTS = {
@@ -326,6 +335,9 @@ def build_skills_system_prompt(
"Before replying, scan the skills below. If one clearly matches your task, "
"load it with skill_view(name) and follow its instructions. "
"If a skill has issues, fix it with skill_manage(action='patch').\n"
"After difficult/iterative tasks, offer to save as a skill. "
"If a skill you loaded was missing steps, had wrong commands, or needed "
"pitfalls you discovered, update it before finishing.\n"
"\n"
"<available_skills>\n"
+ "\n".join(index_lines) + "\n"

15
run_agent.py
View File

@@ -812,7 +812,7 @@ class AIAgent:
logger.debug("peer %s memory_mode=honcho: local USER.md writes disabled", _hcfg.peer_name or "user")
# Skills config: nudge interval for skill creation reminders
self._skill_nudge_interval = 15
self._skill_nudge_interval = 10
try:
from hermes_cli.config import load_config as _load_skills_config
skills_config = _load_skills_config().get("skills", {})
@@ -3542,7 +3542,8 @@ class AIAgent:
flush_content = (
"[System: The session is being compressed. "
"Please save anything worth remembering to your memories.]"
"Save anything worth remembering — prioritize user preferences, "
"corrections, and recurring patterns over task-specific details.]"
)
_sentinel = f"__flush_{id(self)}_{time.monotonic()}"
flush_msg = {"role": "user", "content": flush_content, "_flush_sentinel": _sentinel}
@@ -4541,8 +4542,9 @@ class AIAgent:
self._turns_since_memory += 1
if self._turns_since_memory >= self._memory_nudge_interval:
user_message += (
"\n\n[System: You've had several exchanges in this session. "
"Consider whether there's anything worth saving to your memories.]"
"\n\n[System: You've had several exchanges. Consider: "
"has the user shared preferences, corrected you, or revealed "
"something about their workflow worth remembering for future sessions?]"
)
self._turns_since_memory = 0
@@ -4552,8 +4554,9 @@ class AIAgent:
and self._iters_since_skill >= self._skill_nudge_interval
and "skill_manage" in self.valid_tool_names):
user_message += (
"\n\n[System: The previous task involved many steps. "
"If you discovered a reusable workflow, consider saving it as a skill.]"
"\n\n[System: The previous task involved many tool calls. "
"Save the approach as a skill if it's reusable, or update "
"any existing skill you used if it was wrong or incomplete.]"
)
self._iters_since_skill = 0

4
tools/memory_tool.py
View File

@@ -439,11 +439,13 @@ MEMORY_SCHEMA = {
"Memory is injected into future turns, so keep it compact and focused on facts "
"that will still matter later.\n\n"
"WHEN TO SAVE (do this proactively, don't wait to be asked):\n"
"- User corrects you or says 'remember this' / 'don't do that again'\n"
"- User shares a preference, habit, or personal detail (name, role, timezone, coding style)\n"
"- You discover something about the environment (OS, installed tools, project structure)\n"
"- User corrects you or says 'remember this' / 'don't do that again'\n"
"- You learn a convention, API quirk, or workflow specific to this user's setup\n"
"- You identify a stable fact that will be useful again in future sessions\n\n"
"PRIORITY: User preferences and corrections > environment facts > procedural knowledge. "
"The most valuable memory prevents the user from having to repeat themselves.\n\n"
"Do NOT save task progress, session outcomes, completed-work logs, or temporary TODO "
"state to memory; use session_search to recall those from past transcripts.\n"
"If you've discovered a new way to do something, solved a problem that could be "

3
tools/skill_manager_tool.py
View File

@@ -561,7 +561,8 @@ SKILL_MANAGE_SCHEMA = {
"user-corrected approach worked, non-trivial workflow discovered, "
"or user asks you to remember a procedure.\n"
"Update when: instructions stale/wrong, OS-specific failures, "
"missing steps or pitfalls found during use.\n\n"
"missing steps or pitfalls found during use. "
"If you used a skill and hit issues not covered by it, patch it immediately.\n\n"
"After difficult/iterative tasks, offer to save as a skill. "
"Skip for simple one-offs. Confirm with user before creating/deleting.\n\n"
"Good skills: trigger conditions, numbered steps with exact commands, "