mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(gateway): always inject reply-to pointer, not just when quoted text is absent (#13676)

Browse source 
The [Replying to: "..."] prefix is disambiguation, not deduplication. When
a user explicitly replies to a prior message, the agent needs a pointer to
which specific message they're referencing — even when the quoted text
already exists somewhere in history. History can contain the same or
similar text multiple times; without an explicit pointer the agent has to
guess (or answer for both subjects), and the reply signal is silently
dropped.

Example: in a conversation comparing Japan and Italy, replying to the
"Japan is great for culture..." message and asking "What's the best time
to go?" — previously the found_in_history check suppressed the prefix
because the quoted text was already in history, leaving the agent to
guess which destination the user meant. Now the pointer is always present.

Drops the found_in_history guard added in #1594. Token overhead is
minimal (snippet capped at 500 chars on the new user turn; cached prefix
unaffected). Behavior becomes deterministic: reply sent ⇒ pointer present.

Thanks to smartyi for flagging this.
This commit is contained in:
Teknium 2026-04-21 13:33:02 -07:00 • committed by GitHub
parent 7ff7155cbd
commit e889332c99
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 166 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

14
gateway/run.py
View file

@ -3887,14 +3887,14 @@ class GatewayRunner:
message_text = f"{context_note}\n\n{message_text}"
if getattr(event, "reply_to_text", None) and event.reply_to_message_id:
# Always inject the reply-to pointer — even when the quoted text
# already appears in history. The prefix isn't deduplication, it's
# disambiguation: it tells the agent *which* prior message the user
# is referencing. History can contain the same or similar text
# multiple times, and without an explicit pointer the agent has to
# guess (or answer for both subjects). Token overhead is minimal.
reply_snippet = event.reply_to_text[:500]
found_in_history = any(
reply_snippet[:200] in (msg.get("content") or "")
for msg in history
if msg.get("role") in ("assistant", "user", "tool")
)
if not found_in_history:
message_text = f'[Replying to: "{reply_snippet}"]\n\n{message_text}'
message_text = f'[Replying to: "{reply_snippet}"]\n\n{message_text}'
if "@" in message_text:
try: