Add the referenced_chat_context slice: models for the data shapes, a
fail-closed resolver that fetches mentioned threads and their visible
turns under the same access rules as thread search, and a transcript
renderer that emits a budgeted <referenced_chat_context> block. When a
chat exceeds the per-reference character budget, recent turns are kept
and any leftover budget is filled with the overflowing turn's tail, with
truncation markers signalling the cut.
Recursive pass over the agents module to make docstrings and inline
comments concise and intent-oriented: drop narration that just restates
the code, condense verbose module/function docstrings, and keep only the
non-obvious "why" notes. No functional code changed.
Move the lower-level runtime/infra modules out of multi_agent_chat/shared/
(they were never used by subagents, so they failed the shared-by-all-siblings
rule) and unify them with the already-relocated checkpointer:
agents/runtime/ -> agents/chat/runtime/
mac/shared/errors.py -> chat/runtime/errors.py
mac/shared/llm_config.py -> chat/runtime/llm_config.py
mac/shared/prompt_caching.py -> chat/runtime/prompt_caching.py
mac/shared/mention_resolver.py -> chat/runtime/mention_resolver.py
mac/shared/path_resolver.py -> chat/runtime/path_resolver.py
These sit below the agent packages: the boundary + agent factory + shared
middleware depend on them, and they import no agent code (acyclic).
