fix(context_compressor): prevent consecutive same-role messages after compression (#1743)

compress() checks both the head and tail neighbors when choosing the
summary message role.  When only the tail collides, the role is flipped.
When BOTH roles would create consecutive same-role messages (e.g.
head=assistant, tail=user), the summary is merged into the first tail
message instead of inserting a standalone message that breaks role
alternation and causes API 400 errors.

The previous code handled head-side collision but left the tail-side
uncovered — long conversations would crash mid-reply with no useful
error, forcing the user to /reset and lose session history.

Based on PR #1186 by @alireza78a, with improved double-collision
handling (merge into tail instead of unconditional 'user' fallback).

Co-authored-by: alireza78a <alireza78.crypto@gmail.com>
This commit is contained in:
Teknium 2026-03-17 05:18:52 -07:00 committed by GitHub
parent 702191049f
commit 548cedb869
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 160 additions and 3 deletions

View file

@ -311,6 +311,7 @@ Write only the summary body. Do not include any preamble or prefix; the system w
)
compressed.append(msg)
_merge_summary_into_tail = False
if summary:
last_head_role = messages[compress_start - 1].get("role", "user") if compress_start > 0 else "user"
first_tail_role = messages[compress_end].get("role", "user") if compress_end < n_messages else "user"
@ -326,13 +327,25 @@ Write only the summary body. Do not include any preamble or prefix; the system w
flipped = "assistant" if summary_role == "user" else "user"
if flipped != last_head_role:
summary_role = flipped
compressed.append({"role": summary_role, "content": summary})
else:
# Both roles would create consecutive same-role messages
# (e.g. head=assistant, tail=user — neither role works).
# Merge the summary into the first tail message instead
# of inserting a standalone message that breaks alternation.
_merge_summary_into_tail = True
if not _merge_summary_into_tail:
compressed.append({"role": summary_role, "content": summary})
else:
if not self.quiet_mode:
print(" ⚠️ No summary model available — middle turns dropped without summary")
for i in range(compress_end, n_messages):
compressed.append(messages[i].copy())
msg = messages[i].copy()
if _merge_summary_into_tail and i == compress_end:
original = msg.get("content") or ""
msg["content"] = summary + "\n\n" + original
_merge_summary_into_tail = False
compressed.append(msg)
self.compression_count += 1