Commit Graph

129 Commits

Author SHA1 Message Date
wizardchen 30332cca99 fix(frontend): correct floating UI positioning under root zoom
The user font-size preference applies CSS `zoom` on `<html>`
(see `composables/useFont.ts`). This breaks every popover that
anchors itself with `getBoundingClientRect()` + `position: fixed/absolute`,
because the rect is in visual pixels while CSS lengths are then
multiplied by zoom again — shifting popovers toward the lower-right
and miscomputing maxHeight / width / viewport-edge clamping.

PR #1459 patched only `AgentSelector.vue` (and left its width/maxHeight
unfixed). This PR introduces a shared helper `frontend/src/utils/zoom.ts`
(`getRootZoom`, `rectToCssPx`, `cssViewportSize`) and applies it to every
affected popover:

- `AgentSelector.vue` — refactored to use the helper; also normalizes
  `width` and `maxHeight` (previously still in visual px).
- `Input-field.vue` — model dropdown, mention popup (typed @ and button-
  triggered), and agent-mode dropdown.
- `KnowledgeBaseSelector.vue` — primary anchor path and fallback path.
- `UserMenu.vue` — tenant and IM floating submenus + viewport clamp.
- `FAQTagTooltip.vue` — fixed tooltip positioning + edge clamp.
- `AgentEditorModal.vue` — placeholder popups for system_prompt,
  context_template, and rewrite/fallback prompts.
- `AgentStreamDisplay.vue` — `kb-float-popup` (absolute under body, also
  under the zoom containing block).

Verified with `npm --prefix frontend run build`.
2026-05-24 23:03:26 +08:00
Thinh Tran 3db5b0d126 fix(chat): adjust user message container to support pre-wrapped text 2026-05-21 16:11:22 +08:00
wizardchen 9f6148784a fix(frontend): improve offline and legacy browser support 2026-05-21 11:19:44 +08:00
wizardchen 8f4626158d fix(chat): improve history rendering stability 2026-05-21 11:19:44 +08:00
wizardchen 07afec1499 fix(chat): stabilize history pagination and keep message order 2026-05-20 21:03:39 +08:00
wizardchen f3c7281f47 refactor(agent): simplify grep_chunks tool to a single regex query
The grep_chunks tool previously accepted an array of regex queries (1-5)
and an optional knowledge_base_ids filter and limit. In practice the LLM
either fired multiple near-duplicate calls or split synonyms across
entries instead of using POSIX alternation, and KB scoping plus result
limit are server-side concerns the model should not control.

Reshape the contract to match `grep -E -i` semantics:

- Schema accepts a single required `query` string. Combine concepts with
  `|` alternation in one regex instead of multiple calls.
- Drop `knowledge_base_ids` and `limit` from the schema; the tool now
  always searches the full agent scope and uses a fixed internal cap.
- Legacy `pattern`, `queries`, `patterns`, `max_results` keys are still
  accepted and joined into a single alternation regex so older callers
  and in-flight model outputs keep working.
- Update the agent system prompt template to document the new single
  `query` field.
- Frontend tool title now reads `query`/`queries`/`pattern`/`patterns`
  in that order so the search text is shown again under the new schema.
- Add a dedicated `grepSearch` / `grepSearchFailed` tool status (zh-CN,
  en-US, ko-KR, ru-RU) and rename the zh-CN tool label to "搜索关键词"
  so the UI no longer prefixes the call with a generic "调用 ..." label.
2026-05-20 19:34:27 +08:00
wizardchen 7bb38f81b6 feat(session): persist last request state for UI restoration
Sessions now record the input-bar state used for the most recent QA
request (agent, model, KB scope, web search). The chat UI hydrates
those settings on session reopen so users see the same configuration
they used last time, instead of the global default.

The state is stored in the existing sessions.agent_config JSONB column
to avoid a new migration. Frontend snapshots the user's global defaults
on session enter and restores them on session leave, so opening an old
session does not pollute new-chat defaults.
2026-05-18 22:28:00 +08:00
wizardchen 4aedf5fd62 fix(chat): simplify enableMemoryOverride assignment in sendMsg function
Refactored the assignment of enableMemoryOverride in the sendMsg function to remove explicit type declaration, enhancing code clarity. This change maintains the existing functionality while streamlining the code structure.
2026-05-18 17:28:58 +08:00
wizardchen 5a91487322 feat(memory-management): implement server-side user preference for memory feature
Updated the memory management logic to utilize a server-side per-user preference for enabling memory. The `enable_memory` field is now conditionally set based on user preferences, allowing for better control in both normal and embedded contexts. Adjusted relevant API handlers and request structures to support this change, ensuring backward compatibility with existing clients.

Refs: #1303
2026-05-18 17:28:58 +08:00
wizardchen ec2b44494f fix(frontend): show reasoning_content in historical agent steps
Tool-calling rounds emit reasoning into the OpenAI-protocol
reasoning_content field rather than visible content, so AgentStep.Thought
is often empty in DB. The history reconstructor only read step.thought,
which made the historical step card silent for those rounds even though
the user saw the reasoning live.

Fall back to step.reasoning_content when step.thought is empty so
reload mirrors the live experience.
2026-05-13 13:36:51 +08:00
wizardchen 5510ea8f5a feat(agent): human-in-the-loop approval for MCP tool calls (#1173)
Add an opt-in human approval gate so Agent runs pause before executing
MCP tools that operators flag as dangerous, surface an approval card in
the chat UI, and only resume after the user approves (optionally with
edited args) or rejects.

Backend
- New mcp_tool_approvals table + repo/service to mark per-tool approval
  required (PG migration 000042 + sqlite init).
- approval.Gate coordinates RequestAndWait / Resolve with sync.Once
  delivery, configurable timeout, and Redis Pub/Sub fan-out so multi-
  replica deployments work without sticky sessions.
- MCPTool.Execute integrates the gate; uses a round-level ApprovalCtx
  (without the per-tool 60s timeout) for the wait, and re-derives a
  fresh 60s exec ctx after approval so CallTool keeps a full window.
- New SSE response types (tool_approval_required / _resolved) and
  EventBus events plumb approval state to AgentStreamDisplay.
- REST: list/set per-tool approval flag, resolve pending approval.
- Configurable via agent.tool_approval_timeout_seconds (yaml) or
  WEKNORA_AGENT_TOOL_APPROVAL_TIMEOUT env (accepts seconds or Go
  duration).

Frontend
- MCP settings: per-tool "require approval" switch on the test panel.
- Chat: ToolApprovalCard renders the pause point with editable JSON
  args, validation feedback, mm:ss countdown that turns warning/danger
  near deadline, and a resolved state that retains context.
- i18n strings added for zh-CN / en-US / ko-KR / ru-RU.

Docs
- docs/zh/mcp-approval.md covering behavior, config, API, deployment
  considerations (Redis cross-instance, restart limitations).
2026-05-10 22:57:12 +08:00
wizardchen 627e9e436d fix(frontend): render markdown tables in chat wiki drawer
The wiki page drawer opened from the chat view rendered tables without
borders or padding because the global `.wiki-graph-drawer .wiki-reader-body`
style block was missing GFM table rules. Add the same table styles already
used by `WikiBrowser.vue` so tables show consistent borders, header
background, and hover states across both entry points.
2026-05-07 18:29:36 +08:00
wizardchen 56058287dd fix(agent): drop whitespace-only thinking events from the steps tree
Some LLMs (e.g. qwen3 series) emit blank lines like "\n\n" before tool
calls. The backend faithfully forwards these as thought_chunk events
because streamThinkingToEventBus only filters chunk.Content == "" and
treats whitespace as content. The frontend then merges them into a
thinking event whose content is non-empty in JS truthiness terms but
visually empty, producing a "思考" card with a chevron and no text.

Filter such events out at the end of buildFullEventList so neither the
intermediate-steps tree nor the displayEvents fallback path renders
them.
2026-05-07 17:33:03 +08:00
wizardchen 921e4c015a fix(agent): hide trailing thinking event when it duplicates final answer
The natural-stop path on the backend (observe.go Case 1) emits the same
content twice: once as streaming thinking chunks (from
streamThinkingToEventBus's per-chunk callback) which the frontend merges
into a single thinking event, and once as one big EventAgentFinalAnswer.
The result is that the intermediate-steps tree contains a thinking card
whose content is identical to the answer card rendered below it.

Detect this duplication and hide the offending thinking event from the
tree:

- New utils `normaliseForComparison` and `thinkingEqualsAnswer` perform
  a tolerant comparison: strip <think>…</think> blocks (which leak into
  raw thinking chunks but not into the post-StripThinkBlocks answer),
  strip final-answer wrappers, collapse whitespace, then exact-equal or
  ±2% length with matching head/tail.
- `hiddenThinkingEventIds` (replacing the previous single-id
  `promotedThinkingEventId`) now collects two cases of duplicate
  thinking: the legacy promotion fallback (no answer event present) and
  the natural-stop content-match case.

The final_answer-tool path is unaffected because reasoning thinking
events ("我找到了…让我整理…") and the answer payload have different
content and don't match the equivalence check.
2026-05-07 17:33:03 +08:00
wizardchen 4677caba01 fix(agent): unify answer rendering when model skips final_answer tool
Many models (especially smaller or non-OpenAI-style ones) do not reliably
call the structured final_answer tool, even when the system prompt
explicitly requires it. Two visible symptoms in the agent UI:

1. The natural-stop path emits the answer as a final_answer event whose
   content is wrapped in <answer>...</answer>, <final_answer>...</final_answer>,
   or prefixed with "Final Answer:" / "最终答案:". These wrappers were
   rendered verbatim into the answer card.

2. When no answer event arrives at all, the trailing thinking event was
   surfaced via the legacy fallback but kept its collapsed "思考" card
   styling instead of rendering as a proper answer.

This change adds a small unwrap helper and wires it through the answer
rendering path:

- New util `unwrapFinalAnswerWrappers` strips conservative outer wrappers
  (XML-style answer tags, fenced ```final_answer code blocks, and leading
  "Final Answer:" / "最终答案:" prefixes) only when they cover the entire
  trimmed content, so user markdown that happens to contain similar text
  is left alone.
- `renderAnswerContent` and `getActualContent` apply the unwrap before the
  markdown renderer / clipboard copy, so users see and copy clean text.
- The legacy "promote trailing thinking to final answer" fallback now
  synthesizes a virtual answer event so it renders with the answer card
  UI (expanded markdown + copy/add toolbar) instead of the collapsed
  thinking card. The promoted thinking event is hidden from the
  intermediate-steps tree to avoid duplication.
2026-05-07 17:33:03 +08:00
bingxiang.cheng a3c3ba5acf fix(markdown): 修复小概率情况下公式加载失败问题 2026-05-07 16:34:20 +08:00
bingxiang.cheng a232b12ff0 fix(agent): 修复WeKnora对话完前端未显示结束标记问题
fix(agent): 修复流式回答think内容与answer混淆问题
2026-05-07 16:34:20 +08:00
Claude f140c12518 feat(frontend): unify font rendering and add font picker in settings
The UI used hardcoded "PingFang SC" in 50+ components, while the global
font stack in App.vue used a different fallback chain. Outside of mainland
China this caused visibly different fonts in the sidebar, breadcrumbs,
search and agent views compared to settings and document panes.

- Introduce --app-font-family / --app-font-family-mono CSS variables in
  theme.css and route TDesign's --td-font-family through them
- Add a useFont composable that persists the user's choice in localStorage
  and applies it via document.documentElement.style before mount
- Replace hardcoded font-family declarations across the app with the new
  variables (TencentSans logo and the SVG attribute list are preserved)
- Add UI font and monospace font selectors in General Settings with
  i18n strings for en-US, zh-CN, ko-KR and ru-RU

https://claude.ai/code/session_01S1FVPf4jRfWXkTSnpMmMp7
2026-05-05 00:48:40 +08:00
wizardchen 1fe1f853d5 fix(chat): keep input visible when conversation overflows viewport
The chat layout is a flex column (.chat) inside .platform-route-outlet,
with .chat_scroll_box {flex:1; overflow-y:auto} above .input-container.
Flex items default to min-height:auto, so when messages outgrew the
viewport the scroll box was stretched by its content instead of
scrolling internally. That pushed the input container out of view and
broke page-level scrolling because the parent clips overflow.

- .chat: add min-height:0 so its flex:1 child can shrink
- .chat_scroll_box: add min-height:0 to enable overflow-y scrolling
- .input-container: add flex-shrink:0 so a tall scroll box cannot
  squeeze it to zero height
2026-04-29 17:34:20 +08:00
wizardchen da90867dd4 feat(ui): refactor IM channels list layout and form\n\n- Change IM channel form from dialog to drawer for better UX\n- Convert channel list from vertical layout to responsive grid cards\n- Move edit/delete actions into a dropdown menu for cleaner card design\n- Replace platform radio group with a select dropdown in the add channel form 2026-04-29 17:34:20 +08:00
wizardchen c62ff4c906 fix(frontend): knowledge document list layout, batch bar, and selection
- Platform route outlet: flex min-height so document area is not collapsed
- Card grid: stable :key=item.id; clamp selection anchor after list reload
- DocumentListView: TDesign checkbox, sticky header, neutral file icons
- DocumentBatchBar: column-footer placement; toned style vs floating pill
- Clear selection i18n: less ambiguous wording (e.g. 取消选择)
- Batch delete: poll list refresh after async queue; getKnowled returns Promise
- files.ts: use file icon for text types; align chat/upload icon usage
2026-04-29 15:20:41 +08:00
wizardchen 4b87239929 fix: LaTeX formulas flash and disappear during streaming response (#1056)
Replace token-by-token rendering (marked.lexer + v-for + marked.parser)
with single-pass marked.parse() in botmsg.vue and AgentStreamDisplay.vue.
This prevents Vue's v-for keyed diffing from destroying KaTeX DOM nodes
on each streaming update.

Also adds a dev-only markdown test page (/platform/dev/markdown) with
LaTeX, code, tables, Mermaid, and streaming simulation for visual
regression testing.
2026-04-28 19:34:33 +08:00
wizardchen 623add89f1 fix: Improve inline code sanitization in AgentStreamDisplay component
- Enhanced the `sanitizeForDisplay` function to correctly remove empty inline code snippets (`` or ` `) while preserving triple-backtick fenced code blocks.
- This change ensures better rendering of code blocks in the chat interface, improving overall display accuracy.
2026-04-22 21:18:32 +08:00
wizardchen 3c2b29456a feat: Refactor wiki citation handling in chat bubbles for improved consistency
- Simplified the rendering of wiki citations in chat bubbles by removing truncation and inline pill styles, replacing them with a standard link format.
- Updated CSS styles to reflect the new inline link design, featuring a brand-blue dashed underline for better visual integration with surrounding text.
- Enhanced accessibility by maintaining the use of the `data-slug` attribute for interaction handling.

These changes streamline the presentation of wiki citations, improving user experience and visual consistency across the chat interface.
2026-04-22 21:18:30 +08:00
wizardchen b3eab5276c feat: Update agent system prompt and frontend citation handling for wiki sources
- Enhanced the agent system prompt to clarify citation formats for wiki and chunk sources, ensuring accurate inline citations.
- Introduced a new citation format section in the prompt, detailing the required syntax for both wiki pages and knowledge chunks.
- Updated the frontend to visually align wiki citations with knowledge base citations, improving user experience and consistency in citation presentation.
- Implemented truncation for long wiki labels in citations to maintain visual consistency in chat bubbles.

These changes improve the clarity and usability of citations in the agent system, enhancing the overall information retrieval process.
2026-04-22 21:18:21 +08:00
wizardchen 0429776e9f feat: Enhance knowledge base retrieval and runtime context handling
- Improved the `getKbIdForWiki` function to better handle multiple knowledge bases associated with a single slug, ensuring the most recent tool call's mapping is prioritized.
- Updated the `buildRuntimeContextBlock` function to include active knowledge bases and pinned documents, providing a clearer context for multi-turn interactions and preventing prompt injection.
- Added `registerLinkedSlugs` function to track outbound and inbound links for wiki pages, facilitating better resolution of slugs in the frontend without additional requests.

These enhancements significantly improve the accuracy and safety of knowledge base retrieval and context management in the agent system.
2026-04-22 21:18:11 +08:00
wizardchen 1d72a25e25 feat: Enhance chat UI and wiki page retrieval logic
- Updated the chat component to include a new class for handling sidebar collapse, improving layout responsiveness.
- Enhanced the wiki page retrieval logic to support multiple knowledge bases for the same slug, allowing for more comprehensive results.
- Introduced a mechanism to track ambiguous slugs across knowledge bases, improving clarity in search results.

These changes significantly improve the user experience in the chat interface and enhance the functionality of the wiki page retrieval system.
2026-04-22 21:18:11 +08:00
wizardchen bd5d70b5ae feat: Add wiki drawer functionality and localization support in AgentStreamDisplay
- Introduced a new wiki drawer component in AgentStreamDisplay for enhanced navigation to wiki pages, allowing users to view detailed content and related metadata.
- Implemented localization for the new "View in Graph" feature in both English and Chinese, improving accessibility for diverse user bases.
- Updated the WikiBrowser component to utilize the new drawer for displaying wiki content, streamlining the user experience when interacting with wiki links.

These enhancements significantly improve the usability and functionality of the wiki navigation system, providing users with a more intuitive experience when accessing and citing wiki content.
2026-04-22 21:18:10 +08:00
wizardchen e9ed8d1961 feat: Enhance wiki navigation and citation handling in AgentStreamDisplay and WikiBrowser
- Updated the agent system prompt to require wiki-links in citations, improving user navigation to source pages.
- Implemented logic in AgentStreamDisplay to handle wiki link clicks and keyboard interactions, facilitating seamless navigation to knowledge base wiki pages.
- Enhanced WikiBrowser to auto-select pages based on query parameters, improving user experience when accessing specific wiki content.
- Added localization support for new error messages related to knowledge base identification, ensuring clarity in user interactions.

These changes significantly improve the usability and functionality of the wiki navigation system, providing users with a more intuitive experience when accessing and citing wiki content.
2026-04-22 21:18:10 +08:00
wizardchen 84edfa5439 feat: Implement wiki editing functionalities and UI components
- Added new tools for wiki page editing, including writing, replacing text, renaming, and deleting pages, with corresponding data structures for each action.
- Enhanced the frontend with a new `WikiEditResult` component to display results of wiki edits, supporting multiple languages for improved accessibility.
- Updated localization files for English and Chinese to include new strings related to wiki actions.
- Modified existing tools to return structured data for wiki actions, improving the clarity and usability of the output messages.

These changes significantly enhance the wiki editing capabilities, providing users with a more robust and user-friendly experience when managing wiki content.
2026-04-22 21:18:08 +08:00
wizardchen 995e2157cd feat: Enhance Wiki Fixer agent with improved issue handling and UI updates
- Updated the agent system prompt to refine the workflow for fixing issues, emphasizing the need to verify if issues still exist before making edits.
- Introduced a new `embeddedMode` prop in the frontend components to manage UI behavior based on the context of use.
- Simplified issue fix prompts in multiple languages for clarity, ensuring users receive concise instructions for resolving issues.
- Enhanced the WikiBrowser component to improve the display of issues and actions, including updated icons and streamlined interaction elements.

These changes significantly improve the user experience and functionality of the Wiki Fixer agent, fostering more efficient issue resolution and content management.
2026-04-22 21:18:08 +08:00
wizardchen bd096454e1 feat: Introduce Wiki Fixer agent and related functionalities
- Added a new built-in agent, "Wiki Fixer," designed to repair and optimize Wiki pages based on linter issues, with multilingual support for enhanced accessibility.
- Implemented a corresponding system prompt detailing the agent's role, mission, and workflow for effective issue resolution.
- Introduced new API functions for listing and updating wiki issues, allowing for better management of content conflicts and errors.
- Enhanced the frontend with new UI elements to display pending issues and facilitate auto-fixing, improving user interaction with the Wiki content.

These changes significantly enhance the agent's capabilities for maintaining the accuracy and quality of Wiki pages, fostering a more reliable knowledge base.
2026-04-22 21:18:08 +08:00
jw_mac a121a5d636 fix(frontend): 修复公式输出展示问题并引入 KaTeX 支持 (#912) 2026-04-22 16:38:24 +08:00
wizardchen fb714ea883 feat(document-preview): enhance security by sanitizing HTML and Markdown content
- Integrated sanitizeHTML and safeMarkdownToHTML functions to ensure that rendered HTML and Markdown content is safe from XSS vulnerabilities.
- Updated the rendering logic for Excel and Markdown to sanitize the output, improving overall security in document previews.
2026-04-16 18:13:20 +08:00
Mao Meng 78e36d4ade Merge upstream main and resolve conflicts 2026-04-14 14:13:00 +08:00
Mao Meng 41aa35e346 refactor: change icon 2026-04-14 13:31:44 +08:00
wizardchen 6d8b47e57c feat: implement theme synchronization and loading skeletons across various components, enhancing user experience during content loading 2026-04-11 18:51:16 +08:00
wizardchen 98ff0761ed feat: implement Lite edition support by filtering menu items and adjusting UI elements, enhancing user experience for Lite users 2026-04-11 18:51:16 +08:00
wizardchen 9a2b54536d fix: update environment configuration for debugging and logging, enhance SQLite FTS5 table management, and improve API base URL handling 2026-04-11 18:51:16 +08:00
wizardchen 091fe59560 feat: enhance chat UI with improved hover effects and update database schema for chat history and retrieval configurations 2026-04-11 18:51:16 +08:00
MaoMengww aaee5f044a feat: attachment_support 2026-04-10 12:49:20 +08:00
Manx98 b6fd4ba133 fix(frontend): resolve mermaid not rendering on page refresh 2026-03-30 10:46:50 +08:00
Manx98 5c0b265ea7 fix: marked usage errors 2026-03-27 14:57:54 +08:00
wizardchen 72dfb9ce75 feat(prompt): enhance context and intent classification in templates
- Updated context template to include runtime metadata such as current time and week, improving contextual awareness in user queries.
- Enhanced rewrite template with critical instructions for intent classification, ensuring that rewritten questions preserve essential entities and keywords.
- Refined intent classification logic to prioritize user intents more effectively, improving the accuracy of responses based on user queries.
- Added examples to clarify expected input and output formats for intent classification, enhancing usability for developers.
2026-03-26 18:57:12 +08:00
wizardchen 1960fc2d90 feat(suggested-questions): implement suggested questions feature for chat interface
- Added a new API endpoint to fetch suggested questions based on the agent's associated knowledge bases.
- Implemented frontend components to display suggested questions in both chat and create chat views, enhancing user interaction.
- Updated localization files to include translations for suggested questions in English, Korean, Russian, and Chinese.
- Introduced debounce logic for fetching suggestions to optimize performance during knowledge base changes.
- Enhanced backend services to support fetching and returning suggested questions, improving the overall chat experience.
2026-03-25 22:08:29 +08:00
wizardchen 5245475e0f feat(knowledge): add channel support to knowledge entries and related components
- Introduced a new `channel` field in the Knowledge struct and associated request types to track the source channel (e.g., "web", "api", "browser_extension").
- Updated various frontend components to display channel information and enhance user experience with channel labels.
- Enhanced localization files to support channel labels in English and Chinese.
- Modified backend services and database migrations to accommodate the new channel feature, ensuring consistent tracking across knowledge entries.
- Refactored related functions to integrate channel handling, improving overall knowledge management and context.
2026-03-25 22:08:29 +08:00
wizardchen 5b2ebd1f44 feat(channel): add channel support across various components and locales
- Introduced a new `channel` field in multiple request and message structures to track the source channel (e.g., "web", "api", "im").
- Updated frontend API calls and chat components to include the `channel` parameter, ensuring consistent channel tracking in user messages.
- Enhanced localization files to support channel labels in English, Korean, Russian, and Chinese.
- Added database migration scripts to incorporate the `channel` column in the messages table, facilitating the storage of channel information.
- Refactored related functions and components to accommodate the new channel feature, improving overall message context and tracking.
2026-03-25 22:08:29 +08:00
wizardchen 052be53c42 feat(prompts): update assistant descriptions and add intent-specific templates
- Updated the assistant descriptions in various prompt templates to specify that they are developed by Tencent.
- Added new intent-specific system prompt templates for greeting, chitchat, follow-up, image analysis, summarization, and web search unavailability scenarios.
- Enhanced citation rules in the system prompts to ensure proper inline citation formatting.
- Refactored the rewrite prompt to classify user intent more accurately and output structured JSON responses.
2026-03-25 22:08:29 +08:00
wizardchen e138e0c81a refactor(agent): remove query display from DatabaseQuery component and update tool result structure
- Removed the query display section from the DatabaseQuery component to streamline the UI.
- Updated the DatabaseQueryData interface to eliminate the query field, reflecting changes in tool result handling.
- Enhanced the DatabaseQuery tool execution to focus on returning structured results without exposing raw SQL queries.
- Added a new utility to strip <think> blocks from LLM outputs, improving content clarity and user experience.
2026-03-25 22:08:29 +08:00
lyingbug 03fda55261 fix(frontend): replace v-html with text interpolation in deepThink
Replace v-html + DOMPurify sanitization with plain Vue text
interpolation ({{ }}) and CSS white-space: pre-wrap for the
thinking content display.

The thinking content is raw model output that should never be
interpreted as HTML. Using v-html here created an unnecessary XSS
attack surface — even with DOMPurify, the \n→<br/> replacement
happened before sanitization, and future changes to sanitizer config
could introduce vulnerabilities.

Plain text rendering with pre-wrap:
- Eliminates XSS risk entirely (no HTML parsing)
- Preserves line breaks natively via CSS
- Removes the sanitizeHTML import and safeProcessThinkContent function
- Simpler code with identical visual output
2026-03-25 22:08:29 +08:00