_KermanandTianyi Cui
fb79a944f5
Give durable user context its producer-owned source kind instead of a generic plugin wrapper. The V3-to-V4 conversion preserves the frozen rename and collision rules, all own JSON metadata, event coordinates, and historical request-only kinds. Native catalog and JSONL admission retain source validation so unknown attribution can survive without its producer while malformed owned sources are refused. Use an explicit user-only RequestUserInput for auxiliary LLM prompts that do not own durable message identity. Auto Review and compaction remove their request-only source registrations while retaining prompt content and freezing; provider serializers and projections keep the same wire data, assistant replay isolation, image ordering, and tool correlation. Session writes, Agent delivery, and recorded title requests continue to require identified durable messages. Bind the saved compatibility policy only to user sources and qualify tmux location attribution without weakening fixed system, model, or tool semantics. Rebuild the current inventory and unpublished V4 acknowledgement on the actual tool-role parent, preserving its rationale and all accepted historical records. The catalog format version records tooling metadata; Session remains V4. Developer-role policy and activation belong to their own feature. The latest-master Messages adapter, serialization, request-input typing, EpochHeader reservation, and attribution checks pass 103 tests across five files. The retained V3 Messages input-history snapshot passes through the source profile; Host/Client typechecks and all 41 documentation gates pass. The generated comparison records four changed roots and 447 unchanged type fingerprints. Latest-master ARIA changes are retained, with producer source labels applied independently; new Messages fixtures retain their producer names as declared source kinds and use the fixed system-message helper; recorded Session generations are unchanged by this regrouping. Co-authored-by: Tianyi Cui <[email protected]>
Long-session browser benchmark
English | 中文
The required Chromium workflow in long-session.bench.ts measures opening a synthetic 240-turn Session, loading every older page, visiting Trajectory, and typing another draft during a paced reply. The shipped Web scaffold owns the isolated home, persistence, replay adapter, and loopback listener; Chromium loads the built Web artifacts, not a replacement development server.
Run
pnpm run test:bench builds libraries, workers, and Web artifacts before running the serial benchmark inventory. With artifacts already built, select this directory through pnpm exec vitest run --config vitest.bench.config.ts benchmarks/long-session-browser. Install Chromium through the benchmark workspace before the first run.
Measurements
Three fresh browser processes and scaffold worlds produce raw samples and median verdicts. Open and paging end after the expected transcript state and two animation frames; this includes a rendering opportunity, not a hardware presentation timestamp. Paging reports every page and gates the median of each sample’s slowest page. Stream reports first visible reply, trusted draft typing, complete reply wall time, and Chromium main-thread task duration. Enter submits from the focused composer; draft typing retains that focus without a mouse click. Reply-marker lookups and the input-event text witness read only the latest Assistant step, avoiding repeated whole-history text and accessibility scans. The input witness is installed before submission, and draft typing starts as soon as the first marker is visible, without an extra pre-input animation-frame wait. Reply markers are sampled on animation frames, with visible text required inside the latest step. The first observation captures marker state and focus in the browser; its diagnostics are retrieved after typing so they add no pre-input round trip. Diagnostics also include browser-clock timestamps and focus at the first input event. They do not pause replay; a delayed first observation or input can still fail overlap. The actual first input event must observe an unfinished reply; completion waits for the new rendered turn-tail after Host settlement. After measurement, a trusted keystroke after DONE must fail the same overlap assertion. Open, the slowest older page, and first Trajectory use standard-hosted expectations of 900/700/520 ms. Shared 1.25× headroom gives limits of 1125/875/650 ms respectively; stream endpoint overhead budgets are unchanged. Heap after forced GC and DOM counts are diagnostics, not leak budgets.
The fixture reserves an empty system head before the first user message, with each user message inside its step. It contains mixed-language prompts, prose, reasoning, 20 code fences, and 40 synthetic tool results. Every historical Assistant includes a compact stream built by the production accumulator from matching reasoning, text, tool arguments, usage, and finish chunks. No model, tool, external network, recorded Session, or private Harness home supplies its content. Streaming uses 120 text deltas at 16 ms replay pacing through the real composer, agent loop, transport, and persistence.
The decision record owns calibration, exclusions, and alternatives. The larger manual diagnostic remains separate.