Conversation
tt-a1i
left a comment
There was a problem hiding this comment.
Reviewed at ad0fc65.
This preserves bounded, sanitized provider failure diagnostics across live events and reload while keeping canonical runtime state, model-visible context, and operator-facing UI projections distinct. Failed and aborted outcomes remain separate, and retry completion clears stale diagnostic state.
Local validation: bun run check passed; 94 focused protocol/pi-runtime/web-host Node tests and 146 focused UI tests passed. Hosted CI is green.
Non-blocking follow-up: add a real fixture that streams partial assistant text and then fails, asserting the live SSE state before snapshot polling and the retained incomplete/failure state after reload.
tt-a1i
left a comment
There was a problem hiding this comment.
审查提交:ad0fc6519ffde97266649bb713c7f1a8c082570f。
本轮未发现新的阻断问题。以下结论仅覆盖所列验证范围,不是合并批准。
验证范围
Full production/test diff reviewed. Frozen head 94 Node and 146 UI/store tests passed. Projection retains bounded/sanitized failure diagnostics, snapshot persistence and UI partial-output/error rendering tested separately.
限制与后续
Did not rerun provider/browser E2E. Its fixture fails before streaming and polls the final snapshot, so it does not independently prove mid-stream partial-output failure rendering before refresh. Needs integration with current main.
Problem
Closes #469.
The Web message projection drops an assistant response's
stopReasonanderrorMessage. A provider failure with empty content can therefore look like no response, and the reason disappears from SSE and snapshot views. Retry completion also leaves stale retry state visible.Value
Users can see why a response failed, distinguish failure from cancellation or uncertain settlement, and recover the diagnostic when reopening the Session.
Approach
Preserve bounded, plain-text assistant diagnostics through projection, SSE, and snapshots. Render the outcome and reason for failed or aborted responses, including partial content. Include the outcome in transcript deduplication so empty failures do not collapse together. Project retry completion and clear its live state, display failed/uncertain turn settlement in Composer, and rebuild committed Web assets.
Validation
bun run check,bun run typecheck, andgit diff --check: passed.bun run teston Windows / Node 24.14.0: 1,516 passed, 2 failed, 10 skipped. The failures were the existinggit-info/process.test.ts1-second process timeout andworkflows/execute.e2e.test.tsdetached-workflow settlement timeout, also seen on the audit baseline. The runner stopped before its later Windows serial and Vitest partitions. Full local suite success is not claimed.Impact