Commit Graph

4 Commits

Author SHA1 Message Date
Aleix Conchillo Flaqué
480eca42f5 Split user-turn-stop into inference-triggered and finalized events
Fixes a real bug: with `filter_incomplete_user_turns` enabled, the
smart-turn detector's tentative stop was firing `on_user_turn_stopped`
before the LLM had a chance to veto it. Observers, transcript
appenders and UI indicators received an early — and sometimes
duplicated — signal.

Decomposes the single stop concern into two events:
- `on_user_turn_inference_triggered` fires when a stop strategy has
  enough signal to start LLM inference. The aggregator pushes the
  context here, kicking off the LLM call.
- `on_user_turn_stopped` fires only when the user turn is semantically
  final. Built-in strategies fire both events at the same call site,
  preserving today's behavior for the common case.

Adds `LLMTurnCompletionUserTurnStopStrategy`, which gates
finalization on a `UserTurnCompletedFrame` (a fieldless system frame
emitted by any component judging turn completeness — currently the
`UserTurnCompletionLLMServiceMixin` on `✓`).

Adds `deferred(strategy)` / `DeferredUserTurnStopStrategy`, a thin
wrapper that forwards an inner strategy's events except
`on_user_turn_stopped`. Use this to install a stop strategy as an
inference trigger only, leaving finalization to a peer (e.g. the LLM
completion strategy).

Adds `llm_completion_user_turn_stop_strategies()` for the common
case:

    UserTurnStrategies(
        stop=llm_completion_user_turn_stop_strategies(),
    )

Deprecates `LLMUserAggregatorParams.filter_incomplete_user_turns`.
The aggregator emits a `DeprecationWarning`, wraps existing stop
strategies with `deferred(...)`, and appends
`LLMTurnCompletionUserTurnStopStrategy` automatically.
2026-05-07 17:46:09 -07:00
Mark Backman
efda57de5c Move turn completion instructions to system_instruction
Turn completion instructions were being injected as a system message in
the LLM context, which caused warning spam when system_instruction was
also set, did not persist across full context updates, and broke LLMs
that do not support consecutive system messages.

Instead, compose the turn completion instructions into the LLM service
system_instruction field. This is managed via _base_system_instruction
which stores the original value for restoration when turn completion is
disabled.
2026-03-08 10:41:40 -04:00
radhikagpt1208
b14c8e0e94 Fix turn completion mixin not resetting state after each LLM response 2026-03-08 08:46:45 -04:00
Mark Backman
63a23246d5 Add UserTurnCompletionLLMServiceMixin (#3518)
* Added UserTurnCompletionLLMServiceMixin class

* Added 22-filter-incomplete-turns.py foundational example

* Removed old 22 natural conversation foundational examples

* Added test_user_turn_completion_mixin.py
2026-01-30 14:57:15 -05:00