feat: chat UI overhaul — render pipeline, prompt profiles & UX fixes#20
Merged
Conversation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move skills_list adjacent to skills_guide and push memory/dataset blocks to the end for better logical grouping in the system prompt. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace generic <!-- rendered at runtime --> comments with representative sample content for user_profile, memory_section, memory_context, dataset, and skills_list blocks. Each sample retains the runtime comment to distinguish from static blocks. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move runtime back before base_agent_prompt and memory_guide before user_profile for correct layering precedence. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add monotonic display_order counter to PlutoDuckEventCallbackHandler that assigns unique ordering values in _canonicalize_event_metadata(). Extend ChatRepository to persist and retrieve display_order for both events and messages, with DB fallback via get_next_display_order(). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
… emit Make orchestrator emit() the single point of display_order assignment for all event paths. Events from ApprovalBroker and finally/except blocks now flow through emit() which auto-assigns display_order from the callback handler counter when missing. This eliminates duplicate display_order values in HITL flows. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add display_order field to timeline types, API interfaces, and the reducer. When present, display_order takes priority over run-based sequence ordering, enabling correct global sort across mixed message and event items from different runs. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
… profile editor - Make DEFAULT_PROFILE_ID a single source of truth in prompt_experiment.py - context.py now imports from prompt_experiment instead of hardcoding "v3" - Add "Set as Default" button in Streamlit profile editor sidebar Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Update DEFAULT_PROFILE_ID from "v3" to "v4" - Replace hardcoded "v3" assertions with DEFAULT_PROFILE_ID constant - Rename test to test_resolve_profile_id_defaults_to_configured_default Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Consolidate response formatting rules and remove redundant sections - Simplify file reading guidance into concise inline notes - Remove hardcoded "Prompt Profile: v3" from v4 memory_guide - Reorder sections for clearer prompt flow Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…chat-ui-overhaul # Conflicts: # backend/pluto_duck_backend/agent/core/deep/context.py # backend/pluto_duck_backend/agent/core/deep/event_mapper.py # backend/pluto_duck_backend/agent/core/deep/prompt_experiment.py # backend/tests/agent/test_prompt_experiment.py # backend/tests/agent/test_prompt_experiment_integration.py # backend/tests/services/test_llm_settings.py # frontend/pluto_duck_frontend/hooks/useMultiTabChat.ts # scripts/prompt_profile_editor.py
Collaborator
Author
|
@codex review |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: e61cdc6e8b
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Initialize PlutoDuckEventCallbackHandler with the next available display_order from the DB so that subsequent runs in an ongoing conversation do not restart numbering at 1, preventing duplicate display_order values in real-time SSE streams. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
1 participant
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.
Closes PLU-256
Closes PLU-308
Summary
Changes
채팅 렌더 파이프라인 구조화 (PLU-308)
chatTimelineReducer,chatTimelineAdapter,eventIntentRegistry등 타임라인 처리 모듈 신규 구축useMultiTabChat훅을 탭 상태/타임라인/복원 등 서브모듈로 분리display_order기반 이벤트 정렬을 백엔드(orchestrator, event_mapper, repository)와 프론트엔드 양쪽에 적용채팅 UI 버그 수정 및 UX 개선 (PLU-256)
mark_run_completed호출 방지프롬프트 실험 프로파일 시스템
base_agent_prompt,memory_guide,skills_guide블록 외부화기타
Test plan
chatTimelineReducer,chatTimelineAdapter,eventIntentRegistry,chatLoadingState등)useMultiTabChat탭/타임라인 테스트 통과 확인test_prompt_experiment,test_prompt_experiment_integration)🤖 Generated with Claude Code