Co-authored-by: Graham King <grahamk@nvidia.com>

…oder reuse, doc fixes

Low-risk cleanup batch from the independent review (no decision-path change):

- ai-dynamo#4 chain_augment: add ``predicted_kv_hit_rate`` to ``_PREDICTION_FIELDS``
  so it participates in first-writer-wins partial merge like the other three
  predicted_* fields (was silently dropped in any 2+ plugin PREDICT chain,
  contradicting the proto/Pydantic contract). +2 chain_augment tests.
- #10 engine_adapter: add ``scale_down_capped_by_throughput`` to
  ``_aggregate_disagg_load_reason`` priority (PSM disagg emits it; placed
  between scale_up and scale_down to mirror PSM's _PRIORITY).
- ai-dynamo#11 dead code: drop ``contributing_plugin_ids`` (built, never read) in
  pipeline._run_fanout_stage; drop ``_set_enabled`` + ``_plugin_ids``
  (no caller in PR #1; would KeyError if reached).
- ai-dynamo#18 _encode_fpm: use the canonical
  ``dynamo.common.forward_pass_metrics.encode`` (shared module-level encoder)
  instead of allocating a fresh ``msgspec.msgpack.Encoder`` per tick and
  re-implementing the encoding. Byte-identical wire format; keeps FPM
  serialization in lock-step with the rest of dynamo.
- ai-dynamo#17 transport ABC docstring: timeout is enforced by the transport
  (``call()`` wraps ``asyncio.wait_for``), not the orchestrator — the
  pipeline uses a bare gather to avoid double-counting the deadline.
- ai-dynamo#20 scheduler docstring: note the heartbeat-eviction monitor is not wired
  in this PR (last_heartbeat_at is recorded but unread; monitor is follow-up).
- ai-dynamo#21 transport contract test: 7 inputs (not 8) → 14 cases (multi_pool fixture
  was removed with component_name; comments were stale).
- ai-dynamo#22 metrics test: remove the dead no-op ``pass`` loop in _sample_value.

828 planner tests pass (was 825; +3 chain-augment / merge tests).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>