Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(session): remove synthetic log-only turns

Browse Source
This commit is contained in:
_Kerman
2026-07-28 14:41:51 +08:00
parent 4c6fb8b957
commit cee0666a4d
83 changed files with 355 additions and 819 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/core-data-structures/persistence.md
View File

@@ -12,7 +12,7 @@ The seam is a textbook [capability seam](../../.agents/notes/implemented/archite
## Crash recovery preserves an interrupted turn
A backend that reloads a log crashed mid-turn finds an open `turn/start` with no `turn/end`. It does **not** truncate — a single turn can be huge in a long-horizon task (many steps, large tool output), and those events were durably appended before the crash. Instead it closes the orphaned turn with a synthetic `turn/end { reason: { kind: 'interrupted' } }`, keeping the log balanced and the turn-enclosure invariant intact. `interrupted` is the one `TurnEndReason` no loop emits (see [session.md](session.md#why-a-turn-ended-turnendreasonmap)).
A backend that reloads a log crashed mid-turn finds an open `turn/start` with no `turn/end`. It does **not** truncate — a single turn can be huge in a long-horizon task (many steps, large tool output), and those events were durably appended before the crash. Instead it closes the orphaned turn with a synthetic `turn/end { reason: { kind: 'interrupted' } }`, keeping the interrupted execution balanced without changing any standalone events before or after it. `interrupted` is the one `TurnEndReason` no loop emits (see [session.md](session.md#why-a-turn-ended-turnendreasonmap)).
Repair applies only to cold sessions. For a live id, `SessionPersistence.load(id)` snapshots the in-memory log, waits until that snapshot is durable, and returns it with the stored header only when balanced; an open live turn rejects rather than receiving synthetic interruption boundaries. A coordinator-backed cold load reserves the id across backend reads and repair writes, so concurrent publication of a same-id live session rejects and rolls back. HMR also adopts a live prefix without closing its active turn.