Files
ragflow/web/src/components/message-item/index.module.less

84 lines
1.5 KiB
Plaintext
Raw Normal View History

.messageItem {
padding: 24px 0;
.messageItemSection {
display: inline-block;
}
.messageItemSectionLeft {
width: 80%;
}
.messageItemContent {
display: inline-flex;
gap: 20px;
width: 100%;
min-width: 0;
}
.messageItemContentReverse {
flex-direction: row-reverse;
}
.messageTextBase() {
padding: 6px 10px;
border-radius: 8px;
& > p {
margin: 0;
}
}
.messageText {
.chunkText();
.messageTextBase();
// background-color: #e6f4ff;
word-break: break-word;
}
.messageTextDark {
.chunkText();
.messageTextBase();
padding: 0;
word-break: break-word;
Fix: collapsible thinking display and separate deep research retrieval tag (#14613) ## Summary - **Collapsible thinking**: Replace `<section>` with `<details>` for `<think>` content, so model thinking output is collapsed by default (click to expand). Works for all models that output `<think>` tags (Qwen3, DeepSeek, Gemini, Claude, etc.). - **Fix double thinking tags**: When reasoning/deep research mode is enabled in knowledge base chat, both the retrieval progress and model thinking were wrapped in `<think>` tags, producing two "Thinking..." blocks. Now retrieval progress uses a dedicated `<retrieving>` tag rendered as a separate "Retrieving..." collapsible with a distinct green accent. ### Before - Thinking content displayed as flat gray-bordered `<section>`, occupying significant screen space - Deep research + model thinking both use `<think>` → two identical "Thinking..." blocks ### After - Thinking content collapsed by default in a `<details>` element, click "Thinking..." to expand - Deep research shows "Retrieving..." (green border), model thinking shows "Thinking..." (gray border) ## Changes **Backend (`api/db/services/dialog_service.py`)** - Deep research callback: replace `start_to_think`/`end_to_think` marker flags with direct `<retrieving>`/`</retrieving>` answer text **Frontend** - `web/src/utils/chat.ts`: `replaceThinkToSection()` now uses `<details>` instead of `<section>`; add new `replaceRetrievingToSection()` - 4 tsx files: import and pipe `replaceRetrievingToSection`, whitelist `details`, `summary`, `retrieving` in DOMPurify `ADD_TAGS` - 4 less files: `section.think` → `details.think` with `<summary>` styles; add `details.retrieving` with green accent; dark mode and RTL variants ## Test plan - [ ] Open a chat WITHOUT knowledge base, ask a question to a model with thinking (e.g. Qwen3) → thinking content should be collapsed by default, click "Thinking..." to expand - [ ] Open a chat WITH knowledge base and reasoning enabled, ask a question → "Retrieving..." (green) shows retrieval progress, "Thinking..." (gray) shows model thinking, each independently collapsible - [ ] Verify dark mode renders correctly for both collapsible blocks - [ ] Verify RTL layout renders correctly 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: wanghualoong <wanghualoong@gmail.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-05-08 14:40:00 +08:00
:global(details.think) {
color: rgb(166, 166, 166);
border-inline-start-color: rgb(78, 78, 86);
Fix: collapsible thinking display and separate deep research retrieval tag (#14613) ## Summary - **Collapsible thinking**: Replace `<section>` with `<details>` for `<think>` content, so model thinking output is collapsed by default (click to expand). Works for all models that output `<think>` tags (Qwen3, DeepSeek, Gemini, Claude, etc.). - **Fix double thinking tags**: When reasoning/deep research mode is enabled in knowledge base chat, both the retrieval progress and model thinking were wrapped in `<think>` tags, producing two "Thinking..." blocks. Now retrieval progress uses a dedicated `<retrieving>` tag rendered as a separate "Retrieving..." collapsible with a distinct green accent. ### Before - Thinking content displayed as flat gray-bordered `<section>`, occupying significant screen space - Deep research + model thinking both use `<think>` → two identical "Thinking..." blocks ### After - Thinking content collapsed by default in a `<details>` element, click "Thinking..." to expand - Deep research shows "Retrieving..." (green border), model thinking shows "Thinking..." (gray border) ## Changes **Backend (`api/db/services/dialog_service.py`)** - Deep research callback: replace `start_to_think`/`end_to_think` marker flags with direct `<retrieving>`/`</retrieving>` answer text **Frontend** - `web/src/utils/chat.ts`: `replaceThinkToSection()` now uses `<details>` instead of `<section>`; add new `replaceRetrievingToSection()` - 4 tsx files: import and pipe `replaceRetrievingToSection`, whitelist `details`, `summary`, `retrieving` in DOMPurify `ADD_TAGS` - 4 less files: `section.think` → `details.think` with `<summary>` styles; add `details.retrieving` with green accent; dark mode and RTL variants ## Test plan - [ ] Open a chat WITHOUT knowledge base, ask a question to a model with thinking (e.g. Qwen3) → thinking content should be collapsed by default, click "Thinking..." to expand - [ ] Open a chat WITH knowledge base and reasoning enabled, ask a question → "Retrieving..." (green) shows retrieval progress, "Thinking..." (gray) shows model thinking, each independently collapsible - [ ] Verify dark mode renders correctly for both collapsible blocks - [ ] Verify RTL layout renders correctly 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: wanghualoong <wanghualoong@gmail.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-05-08 14:40:00 +08:00
summary {
color: rgb(140, 140, 140);
&:hover {
color: rgb(180, 180, 180);
}
}
}
:global(details.retrieving) {
color: rgb(166, 166, 166);
border-inline-start-color: rgb(60, 100, 90);
summary {
color: rgb(120, 170, 155);
&:hover {
color: rgb(150, 200, 185);
}
}
}
}
.messageUserText {
.chunkText();
.messageTextBase();
background-color: rgba(255, 255, 255, 0.3);
word-break: break-word;
text-align: justify;
}
.messageEmpty {
width: 300px;
}
.thumbnailImg {
max-width: 20px;
}
}
.messageItemLeft {
text-align: start;
}
.messageItemRight {
text-align: end;
}