Commit graph

6 commits

Author SHA1 Message Date
Teknium
6ea5699e3f
fix(compression): notify users when configured aux model fails even if main-model fallback recovers (#16775)
A misconfigured auxiliary.compression.model is a user-fixable problem that silent recovery would hide. The previous retry-on-main logic transparently swallowed aux-model failures whenever the fallback succeeded, leaving the user's broken config in place and racking up future failures.

Track the aux-model failure on the compressor alongside the existing fallback-placeholder fields:
- _last_aux_model_failure_model: str | None
- _last_aux_model_failure_error: str | None

Both are set at the moment the aux model errors (captured before summary_model is cleared for retry), regardless of whether the retry succeeds. Cleared at compress() start and on on_session_reset() so a clean run doesn't leak stale warnings.

Surface at three places:
- gateway hygiene auto-compress: ℹ note to the platform adapter (thread_id preserved)
- gateway /compress command: ℹ line appended to the reply
- CLI via _emit_warning: deduped on (model, error) so repeat compactions don't spam

Distinct from the existing ⚠️ dropped-turns warning — different severity, different emoji, explicit 'context is intact' reassurance.
2026-04-27 20:08:23 -07:00
iamagenius00
f2fcc087f7 test(gateway): cover /compress summary-failure warning path
PR #16333 added a warning to the manual /compress reply when the
auxiliary summariser fails and the static fallback placeholder is
used, but only the gateway-hygiene path had a test
(test_session_hygiene_warns_user_when_summary_generation_fails).
The /compress branch in _handle_compress_command was uncovered.

New test test_compress_command_appends_warning_when_summary_generation_fails
mocks the compressor's _last_summary_fallback_used /
_last_summary_dropped_count / _last_summary_error fields and
verifies the /compress reply contains the ⚠️ marker, the underlying
error string, the dropped message count, and the 'historical
message(s) were removed' wording — i.e. the same contract the
hygiene-path test enforces.
2026-04-27 19:18:13 -07:00
Teknium
a9a4416c7c
fix(compress): don't reach into ContextCompressor privates from /compress (#15039)
Manual /compress crashed with 'LCMEngine' object has no attribute
'_align_boundary_forward' when any context-engine plugin was active.
The gateway handler reached into _align_boundary_forward and
_find_tail_cut_by_tokens on tmp_agent.context_compressor, but those
are ContextCompressor-specific — not part of the generic ContextEngine
ABC — so every plugin engine (LCM, etc.) raised AttributeError.

- Add optional has_content_to_compress(messages) to ContextEngine ABC
  with a safe default of True (always attempt).
- Override it in the built-in ContextCompressor using the existing
  private helpers — preserves exact prior behavior for 'compressor'.
- Rewrite gateway /compress preflight to call the ABC method, deleting
  the private-helper reach-in.
- Add focus_topic to the ABC compress() signature. Make _compress_context
  retry without focus_topic on TypeError so older strict-sig plugins
  don't crash on manual /compress <focus>.
- Regression test with a fake ContextEngine subclass that only
  implements the ABC (mirrors LCM's surface).

Reported by @selfhostedsoul (Discord, Apr 22).
2026-04-24 02:55:43 -07:00
LeonSGP43
465193b7eb fix(gateway): close temporary agents after one-off tasks
Add shared _cleanup_agent_resources() for temporary gateway AIAgent
instances. Apply cleanup to memory flush, background tasks, /btw,
manual /compress, and session-hygiene auto-compression. Prevents
unclosed aiohttp client session leaks.

Cherry-picked from #10899 by @LeonSGP43. Consolidates #10945 by @Lubrsy706.
Fixes #10865.

Co-authored-by: Lubrsy706 <Lubrsy706@users.noreply.github.com>
2026-04-16 06:31:23 -07:00
Kenny Xie
1ffd92cc94 fix(gateway): make manual compression feedback truthful 2026-04-10 21:16:53 -07:00
Kenny Xie
d6c2ad7e41 fix(gateway): make compress responses truthful 2026-04-10 21:16:53 -07:00