Files
deepseek-harness/packages/session-persistence/session-persistence-jsonl

@deepseek-ai/dsh-session-persistence-jsonl

The JSONL durable session-persistence backend — a concrete SessionPersistence (the dsh-session-persistence seam). One append-only .jsonl event log per session.

On-disk layout

<root>/
  cwd-<sha256(cwd)[:12]>/        # per-project bucket (or _no-cwd/ when no cwd)
    <encoded-id>.jsonl           # header line + one SessionEvent per line (verbatim)
  • The first .jsonl line is the immutable SessionHeader tagged { type: 'session', version, id, cwd?, createdAt, parentSession?, seedLength?, delegationDepth }. delegationDepth is required on disk and is 0 for a top-level session; a missing or invalid value rejects the log. Every subsequent line is one SessionEvent JSON, verbatim including assistant/chunk so seq stays contiguous (events[i].seq === i).
  • Session ids are unvalidated branded strings, so they are percent-encoded to a single safe path segment before use (no traversal, no collision).

Config

Key Type Notes
root string (required) Root directory for all session files. No default — a process.cwd() default would scatter files as the process's cwd changes (bash calls, subprocesses).

locate(meta) returns { kind: 'jsonl', path } using the resolved absolute root and the same cwd-bucket/id encoding as materialization. It performs no filesystem I/O: the target can be returned before the file exists, and an existing file contains only the last flushed prefix.

Durability and crash semantics

  • Lazy materialization. create(meta) writes nothing; on the first append, the backend writes and fsyncs a temporary file, publishes it without overwrite via a hard link, then fsyncs the directory when the host supports it. A created-but-never-appended session leaves nothing on disk and is absent from list.
  • Append-only. Committed events (at or below a flushed turn/end) are never rewritten. Subsequent appends are line appends at EOF + fsync.
  • Crash recovery — preserve valid tail work. load keeps the contiguous valid prefix of an interrupted final turn. It truncates from the first unparsable or sequence-gapped uncommitted record, then appends the synthetic tool, step, and turn closers required by the shared persistence contract; the same defect at or before the last committed turn/end rejects.
  • Contiguous-seq. append rejects a batch whose first seq does not continue the stored log, and rejects non-JSON-serializable event.data naming the offending event type.

Write path

The plugin buffers frozen session events and drains them on flush or disposal. A per-session cursor prevents resumed sessions from re-appending stored events, and live sessions are seeded when the plugin loads. Operations for one session are serialized; disposal waits for initialization and the final drain so no write lands after teardown.

Model Experience

Resumed conversation history

What the model sees

JSONL storage contributes no live prompt or schema. Loading restores stored surface history and preserves prior request headers for reconstruction; the new loop composes its current envelope. Each unanswered call in an interrupted tail is balanced with the exact error text Tool call interrupted by a crash; no result was recorded. Raw assistant/chunk records do not duplicate messages.

Token effect

Zero live-request tokens. A resumed agent pays for retained history and its current envelope, plus the quoted repair result for each interrupted call.

KV Cache effect

JSONL storage does not mutate live request prefixes. A resumed loop can reuse provider cache only when its reconstructed history, current envelope, and model route match; crash-repair results append.

Known Limitations and Deferred Work

  • Only the current SESSION_FORMAT_VERSION (v0) loads — the on-disk format is pre-release/unstable: a breaking format change is absorbed at v0 and non-current logs are rejected; there is no migration.
  • Nothing deletes session files — logs accumulate under root until removed externally (the seam has no deletion surface).
  • Single-process assumption — per-session serialization and the write cursor live in this process; two processes appending to the same root are not coordinated.
  • Initial materialization requires hard-link support — first append uses link() so same-id races fail instead of overwriting a committed log; a filesystem that cannot create hard links cannot host this backend.
  • Windows cannot fsync directory handles through Node — the backend tolerates only Windows EPERM from directory fsync; file-content fsync remains mandatory, but a crash can lose a newly published directory entry on a host without an equivalent directory-sync primitive.