mirror of https://github.com/deepseek-ai/deepseek-harness.git synced 2026-08-29 04:26:38 +00:00

Files

T

Tianyi Cui 7e445c3a67 refactor(session): fold the session family into packages/session/

git mv the 12 packages from session-persistence/, session-projection/,
session-title/, and telemetry/ into one session/ group per the
regrouping RFC; merge the four group READMEs into one bilingual
triplet; rewrite the group segment in tsconfig references (intra-group
references shorten to ../<pkg>), tsconfig.base.json paths/globs,
knip.json keys, vitest include, gate scripts, and authored doc/note
citations; regenerate module graph, doc graphs, catalogs, and the
lockfile importer keys. No npm names change.

Full unit suite: 8779 passed; the 18 reported failures reproduce as
env flakes (ambient-proxy IPv6 tunneling, watched-dir inotify
timeouts under parallel load) — each passes in isolation with
NO_PROXY set, matching their known pre-existing behavior on master.

2026-08-09 01:21:11 +08:00

3.8 KiB

Raw Blame History

Agent Note: Persist assembled assistant messages, not stream chunks

Status: rejected — high-fidelity chunk replay, partial failed streams, and snapshot replay currently depend on persisted assistant/chunk events. Dropping chunks is only viable with a no-information-loss replay/artifact replacement.

English | 中文

Problem

The canonical session log currently persists every assistant/chunk exactly as streamed by the model. The session persistence Agent Note chose this for token-level replay fidelity and contiguous seq, but the cost has grown: JSONL fixtures are dominated by tiny delta records, snapshot scenarios replay the model by grouping chunk events, ACP load reconstructs prior assistant output from chunks, and any future log reader must distinguish durable message history from token-level trace.

For successful steps that assemble completed content, the loop already appends an assistant/message. That is the event deriveMessages() uses for the next model request. In other words, the normal resumable conversation state is already present without the chunks; chunks are a live rendering and deterministic-test artifact, not required conversation history. Failed or aborted streams are different: partial assistant output may exist only as chunks, and empty max-token steps may produce no assistant/message at all.

Proposal

Stop storing assistant/chunk in the canonical session log. The durable log keeps assistant/message, tool/call, tool/result, usage if retained, and turn boundaries. Live UIs can still receive token deltas through a deliberately transient stream event. Snapshot replay should move its model script into an explicit fixture sidecar or derive it from a recorded adapter artifact, rather than treating the canonical user session as a token tape. Scenarios that need partial failed-stream output must record that output in the replay fixture.

ACP session/load can replay prior assistant messages as complete content blocks instead of simulating the original token stream. A loaded transcript need not reproduce every historical delta; it must show the same completed assistant content and resume with a valid provider history.

Acceptance criteria

SessionEventMap drops assistant/chunk, or marks it as non-persisted if a transitional live event is needed.
Session persistence docs no longer require every stream chunk to be stored verbatim.
llm-replay and ACP snapshots use an explicit replay fixture format or sidecar for model chunks.
session/load renders completed assistant messages from assistant/message.
Stored logs get much smaller and remain seq-contiguous without chunk holes.
The session format version and recorded fixtures are refreshed; non-current stored logs are rejected per the pre-release format policy.

What we give up

The canonical user session no longer reconstructs the exact token stream of an old turn. It also loses partial assistant output from failed or aborted streams unless another event or fixture records it. That is too much information loss for the current resume, load, and snapshot contracts. Tests that need exact deterministic streams should own that fixture directly only if the production session log keeps enough fidelity for user-visible recovery.

This supersedes the chunk-persistence choice in session persistence and affects ACP snapshot tests, whose current replay plugin derives its script from assistant/chunk events.

3.8 KiB Raw Blame History