Repository navigation
Add prompt-based Turns and expandable timelines - #12
Merged
Merged
Conversation
Replace Responses with prompt-based `Turns` and lazy, bounded model/tool waterfalls. Show distinct model/provider pairs once in each turn header, preserve overlap and unknown timing, support legacy Pi prompt boundaries, and retain full-timeline drill-down. Attribute work using unique native identities, capture-scoped prompt flows and ancestry, then unambiguous containment. Preserve ambiguous requests unless request-ID correlation is one-to-one. Make failed setup retryable without stale async results. Keep setup metadata lightweight, use indexed flow and parent lookups, defer tool payloads until expansion, and release temporary tables. Wire native browser retry and large-WASM regressions into the UI smoke suite. Tests: `npm run check`; `npm test`; `npm run check:example`; UI typecheck and WASM build; integrated `tools/perfetto smoke-ui --existing-server` across all four harnesses, setup-failure recovery, desktop/mobile layouts and timeline navigation. WASM stress: 100,000 operations and 1,000,000 unrelated indexed flow rows; setup about 2.4 seconds. Perfetto ESLint passes.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Replace Responses with prompt-based
Turnsand lazy, bounded model/tool waterfalls. Show distinct model/provider pairs once in each turn header, preserve overlap and unknown timing, support legacy Pi prompt boundaries, and retain full-timeline drill-down.Attribute work using unique native identities, capture-scoped prompt flows and ancestry, then unambiguous containment. Preserve ambiguous requests unless request-ID correlation is one-to-one. Make failed setup retryable without stale async results.
Keep setup metadata lightweight, use indexed flow and parent lookups, defer tool payloads until expansion, and release temporary tables. Wire native browser retry and large-WASM regressions into the UI smoke suite.
Tests:
npm run check;npm test;npm run check:example; UI typecheck and WASM build; integratedtools/perfetto smoke-ui --existing-serveracross all four harnesses, setup-failure recovery, desktop/mobile layouts and timeline navigation.WASM stress: 100,000 operations and 1,000,000 unrelated indexed flow rows; setup about 2.4 seconds. Perfetto ESLint passes.