AutoCompact.prepare_session runs on the turn hot path
(AgentLoop._compact_session) and read the persisted _last_summary metadata
with an unguarded meta['text'] and datetime.fromisoformat(meta['last_active']).
A _last_summary dict that was hand-edited or written by another version
(missing text/last_active, or a non-ISO last_active) raised KeyError/ValueError
out of the turn.
Sibling readers already tolerate the same data: estimate_session_prompt_tokens
uses .get('text') and _archive parses inside try/except. Mirror that tolerance:
skip when text is unusable, and fall back to the session's own updated_at (the
value the writer persists) when last_active is missing or unparseable, so the
archived summary is preserved instead of crashing the turn.
_load() treated any OSError like corruption and returned an empty store. When pairing.json was transiently unreadable, an unapproved DM could deny the sender, generate a pairing code from the empty view, and overwrite the store without its approved senders.
Keep the existing JSONDecodeError reset behavior, but propagate OSError so mutations cannot persist unreadable state. Read-only checks fail closed without writing; mutating /pairing subcommands report temporary unavailability; and the DM pairing path skips one reply instead of crashing the handler.
This mirrors the refuse-to-overwrite strategy used by the cron and trigger stores.
normalize_token_usage_state only length-checked persisted day keys, so a
hand-edited or foreign 10-char key (e.g. "not-a-dat3" or "2026-13-01") in
token-usage.json survived reads and atomic rewrites. token_usage_payload
then parsed every day key with an unguarded datetime.fromisoformat, so one
such key failed every /api/settings and /api/settings/usage request until
the file was repaired by hand.
Validate day keys in normalize_token_usage_state, the shared boundary that
every read, record, and rewrite already funnels through. Malformed keys are
dropped like other malformed rows and scrubbed from the file on the next
write; valid state is unchanged.
Bind SessionManager saves to the existing raw archive path so SDK imports and other bypass saves cannot persist more than the file cap without archiving unconsolidated overflow.
Add an SDK regression test that exercises the real ingest path.
Refs #4787
Keep only 128 recently used sessions strongly cached while retaining weak references to evicted sessions still owned by active callers. This bounds idle memory growth without allowing duplicate live Session objects or skipping shutdown flushes.
Add LRU, lifecycle, SDK, and flush regression coverage.
Refs #4786
KDBandXubin Ren
