Commit graph

5 commits

Author SHA1 Message Date
kshitijk4poor
7bd1a3a4b1 test(compression): cover real init feasibility override 2026-04-19 10:40:26 -07:00
kshitijk4poor
045b28733e fix(compression): resolve missing config attribute in feasibility check
Commit 4a9c3565 added a reference to `self.config` in
`_check_compression_model_feasibility()` to pass the user-configured
`auxiliary.compression.context_length` to `get_model_context_length()`.
However, `AIAgent` never stores the loaded config dict as an instance
attribute — the config is loaded into a local variable `_agent_cfg` in
`__init__()` and discarded after init.

This causes an `AttributeError: 'AIAgent' object has no attribute
'config'` on every session start when compression is enabled, caught by
the try/except and logged as a non-fatal DEBUG message.

Fix: store the loaded config as `self._config` in `__init__()` and
update the reference in the feasibility check to use `self._config`.
2026-04-19 10:40:26 -07:00
Teknium
bc4e2744c3 test: add tests for compression config_context_length passthrough
- Test that auxiliary.compression.context_length from config is forwarded
  to get_model_context_length (positive case)
- Test that invalid/non-integer config values are silently ignored
- Fix _make_agent() to set config=None (cherry-picked code reads self.config)
2026-04-12 17:52:34 -07:00
Harish Kukreja
b1f13a8c5f fix(agent): route compression aux through live session runtime 2026-04-12 01:34:52 -07:00
Teknium
dafe443beb
feat: warn at session start when compression model context is too small (#7894)
Two-phase design so the warning fires before the user's first message
on every platform:

Phase 1 (__init__):
  _check_compression_model_feasibility() runs during agent construction.
  Resolves the auxiliary compression model (same chain as call_llm with
  task='compression'), compares its context length to the main model's
  compression threshold. If too small, emits via _emit_status() (prints
  for CLI) and stores the warning in _compression_warning.

Phase 2 (run_conversation, first call):
  _replay_compression_warning() re-sends the stored warning through
  status_callback — which the gateway wires AFTER construction. The
  warning is then cleared so it only fires once.

This ensures:
- CLI users see the warning immediately at startup (right after the
  context limit line)
- Gateway users (Telegram, Discord, Slack, WhatsApp, Signal, Matrix,
  Mattermost, Home Assistant, DingTalk, etc.) receive it via
  status_callback('lifecycle', ...) on their first message
- logger.warning() always hits agent.log regardless of platform

Also warns when no auxiliary LLM provider is configured at all.
Entire check wrapped in try/except — never blocks startup.

11 tests covering: core warning logic, boundary conditions, exception
safety, two-phase store+replay, gateway callback wiring, and
single-delivery guarantee.
2026-04-11 12:01:30 -07:00