Simplify UI and improve footer display (v0.3.14)#2
Merged
Conversation
- Fix welcome banner generating a fake session ID (random UUID that
didn't match the actual session); now shows tips and omits the
misleading session line
- Fix footer redundancy: mode and model were shown in both the header
and footer; footer now shows session ID, token count, and help hint
- Fix STATUS_SUCCESS and STATUS_WARNING being the same color
(both DEEPSEEK_SKY), making success/warning states indistinguishable;
success is now green, warning is amber
- Remove unprofessional thinking tagline ("You're absolutely right!
... maybe."); replaced with professional labels
- Fix README mode cycle documentation (said Normal->Plan->Agent->YOLO
but code actually cycles Plan->Agent->YOLO->Plan)
- Fix README tool miscategorization: web.run, web_search,
request_user_input, and multi_tool_use.parallel were listed under
"File Operations" instead of their own categories
- Rewrite README with numbered getting-started steps, keyboard
shortcuts table, cleaner tool categories, environment variable table,
and compact troubleshooting table
- Remove unused imports (chrono::Local, uuid::Uuid, Color, Modifier)
and dead code (mode_color, mode_badge_style)
https://claude.ai/code/session_011XiGZRhainhyvZ8BKKrfzj
Contributor
Summary of ChangesHello @Hmbown, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request focuses on enhancing the user experience of the DeepSeek TUI by simplifying its interface and improving information density. The changes streamline the welcome banner and footer display, making key information more accessible and reducing visual clutter. Additionally, the README has been significantly updated for better clarity and ease of use, and minor code cleanups were performed to improve maintainability. Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
Owner
Author
|
@claude |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces several valuable UI/UX improvements and code simplifications. The redesigned footer provides more relevant information like session ID and token count, which is a great enhancement. The welcome banner is now more concise, and the color changes for status messages improve visual clarity. The extensive overhaul of the README.md makes it much more organized and easier for new users to follow. I've made one suggestion to restore the shell completion examples for bash and fish in the README to maintain completeness. Overall, this is a solid update that refines the user experience.
Contributor
There was a problem hiding this comment.
Pull request overview
This PR simplifies the TUI interface and improves the footer display by showing more relevant context information.
Changes:
- Version bumped from 0.3.13 to 0.3.14
- Footer redesigned to show session ID, token count, and help hint instead of time/mode/agent info
- Status colors updated:
STATUS_SUCCESSchanged to green andSTATUS_WARNINGto amber for better visual distinction - Welcome banner simplified to remove temporary session ID display
- Removed unused imports and functions (chrono::Local, uuid::Uuid, mode badge styling)
- README restructured for better clarity and organization
Reviewed changes
Copilot reviewed 4 out of 5 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| Cargo.lock | Version bump to 0.3.14 |
| src/palette.rs | Updated STATUS_SUCCESS to green and STATUS_WARNING to amber for better semantic meaning |
| src/tui/app.rs | Simplified welcome banner by removing unused session ID parameter and removing uuid import |
| src/tui/ui.rs | Footer redesign showing session ID, token count, and help hint; removed unused imports and helper functions; simplified thinking taglines |
| README.md | Comprehensive restructuring for improved clarity and readability |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Hmbown
added a commit
that referenced
this pull request
Feb 19, 2026
* Polish UI, fix bugs, and rewrite README for clarity
- Fix welcome banner generating a fake session ID (random UUID that
didn't match the actual session); now shows tips and omits the
misleading session line
- Fix footer redundancy: mode and model were shown in both the header
and footer; footer now shows session ID, token count, and help hint
- Fix STATUS_SUCCESS and STATUS_WARNING being the same color
(both DEEPSEEK_SKY), making success/warning states indistinguishable;
success is now green, warning is amber
- Remove unprofessional thinking tagline ("You're absolutely right!
... maybe."); replaced with professional labels
- Fix README mode cycle documentation (said Normal->Plan->Agent->YOLO
but code actually cycles Plan->Agent->YOLO->Plan)
- Fix README tool miscategorization: web.run, web_search,
request_user_input, and multi_tool_use.parallel were listed under
"File Operations" instead of their own categories
- Rewrite README with numbered getting-started steps, keyboard
shortcuts table, cleaner tool categories, environment variable table,
and compact troubleshooting table
- Remove unused imports (chrono::Local, uuid::Uuid, Color, Modifier)
and dead code (mode_color, mode_badge_style)
https://claude.ai/code/session_011XiGZRhainhyvZ8BKKrfzj
* Update src/tui/app.rs
* Update README.md
Hmbown
added a commit
that referenced
this pull request
Apr 28, 2026
Sub-area #2 of the v0.6.6 UI redesign (issue #121). Reasoning is the only deliberately-warm element in the redesigned transcript. The treatment makes that visible: - Header opener becomes `…` (slow exhale) instead of the spinner glyph - Body left rail switches from solid `▏` to dashed `╎` so it visibly differs from message body and tool output rails - Body text carries an italic modifier - Body lines tint with `palette::reasoning_surface_tint(depth)` — 12% blend of SURFACE_REASONING (#362C1A) over DEEPSEEK_INK. ANSI-16 terminals get no bg (the named-color mapping would distort the warm) - A trailing `▎` cursor in ACCENT_REASONING_LIVE follows the most recent body line during streaming, suppressed under low_motion Wires up palette helpers from the prior commit: `ColorDepth::detect`, `reasoning_surface_tint`, `blend`. SURFACE_REASONING is no longer dead-coded. The unused `thinking_symbol` helper is removed since the new header doesn't spin. Tests: dashed rail and italic body land on every body line; streaming cursor appears only when motion is allowed; collapsed-summary affordance keeps working. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This was referenced May 2, 2026
MMMarcinho
pushed a commit
to MMMarcinho/DeepSeek-TUI
that referenced
this pull request
May 6, 2026
Sub-area Hmbown#2 of the v0.6.6 UI redesign (issue Hmbown#121). Reasoning is the only deliberately-warm element in the redesigned transcript. The treatment makes that visible: - Header opener becomes `…` (slow exhale) instead of the spinner glyph - Body left rail switches from solid `▏` to dashed `╎` so it visibly differs from message body and tool output rails - Body text carries an italic modifier - Body lines tint with `palette::reasoning_surface_tint(depth)` — 12% blend of SURFACE_REASONING (#362C1A) over DEEPSEEK_INK. ANSI-16 terminals get no bg (the named-color mapping would distort the warm) - A trailing `▎` cursor in ACCENT_REASONING_LIVE follows the most recent body line during streaming, suppressed under low_motion Wires up palette helpers from the prior commit: `ColorDepth::detect`, `reasoning_surface_tint`, `blend`. SURFACE_REASONING is no longer dead-coded. The unused `thinking_symbol` helper is removed since the new header doesn't spin. Tests: dashed rail and italic body land on every body line; streaming cursor appears only when motion is allowed; collapsed-summary affordance keeps working. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
YaYII
added a commit
to YaYII/DeepSeek-TUI
that referenced
this pull request
May 9, 2026
🔴 Fix Hmbown#1 (Embedder blocks async runtime): - Pre-warm embedder in init_vector_db() via warmup_embedder() - Model downloaded during startup, not first retrieval - Eliminates 5-10s UI freeze on first embed call 🔴 Fix Hmbown#2 (Compaction summary pollution): - store_compaction_summary_to_vector_db() now extracts only the summary section from the SystemPrompt, stripping boilerplate headers and workflow context - Uses regex extraction between ## Summary and ## Workflow markers 🔴 Fix Hmbown#3 (No vector index → full table scan): - New ensure_vector_index() in LanceDbBackend - Checks list_indices() for existing IVF-PQ index on embedding column - Creates missing index via table.create_index(["embedding"], Index::Auto) - Called from ensure_tables() for all three tables 🔴 Fix Hmbown#4 (Compaction threshold regression for non-vector users): - Added MINIMUM_AUTO_COMPACTION_TOKENS_WITHOUT_VECTOR = 500K - should_compact() now accepts vector_db_enabled: bool - Non-vector users keep 500K floor; vector users use 50K floor - auto_floor_tokens=0 (explicit disable by tests) bypasses both floors - token_threshold default restored to 800K (fallback only; real values come from compaction_threshold_for_model_and_effort) 🟡 Fix Hmbown#7 (No score threshold → noise injection): - search_memories() and search_summaries() now filter results where score < 0.4 before returning - Prevents low-quality retrieval from polluting system prompt Tests: 62/62 compaction ✓, 17/17 vector_db ✓
YaYII
added a commit
to YaYII/DeepSeek-TUI
that referenced
this pull request
May 9, 2026
🔴 Hmbown#1 Embedder blocks async runtime: - Pre-warm embedder in init_vector_db() via warmup_embedder() - Model downloaded at startup, eliminating 5-10s UI freeze 🔴 Hmbown#2 Compaction summary boilerplate pollution: - store_compaction_summary_to_vector_db() now extracts only the actual summary section using regex, stripping headers and workflow context from embeddings 🔴 Hmbown#3 No vector index → full table scan: - New ensure_vector_index() checks list_indices() for IVF-PQ - Creates missing index via create_index(["embedding"], Auto) - Called from ensure_tables() for all 3 tables 🔴 Hmbown#4 Compaction threshold regression: - Added MINIMUM_AUTO_COMPACTION_TOKENS_WITHOUT_VECTOR = 500K - should_compact() accepts vector_db_enabled: bool - Non-vector users keep 500K floor; vector users get 50K - auto_floor_tokens=0 bypasses both (test compatibility) - token_threshold default restored to 800K 🟡 Hmbown#7 Score threshold filtering added: - search_memories() and search_summaries() filter score < 0.4 Tests: 62/62 compaction ✓, 17/17 vector_db ✓, 99/100 engine ✓
8 tasks
Hmbown
added a commit
that referenced
this pull request
May 11, 2026
…t drift (#1118 follow-up #2) The opening preamble from commit `47f6d69e5` works for the first few turns, but as English context accumulates in the session (code read into the transcript, error logs, file listings, search results, project context), the transformer's recency bias pulls `reasoning_content` back toward English even when the user keeps writing in their own language. The empirical fingerprint is "model thinks in Chinese for the first 3-4 turns, then quietly switches to English thinking around turn 5 as more code lands in context." Community feedback (WeChat thread on #1118 — @mumu describes an XML-tagged "bilingual bookend" pattern they used in another project, and @益达 confirms the translation-accuracy problem with fully-translated prompts) pointed at the bookend pattern: keep the rule-heavy middle of the prompt in English (single source of truth, model is natively multilingual), but reinforce the locale directive at BOTH ends in native script. The opening anchors behavior at session start; the closer sits at the maximum- recency position right before the user's next message and re-asserts the rule each turn. `locale_reinforcement_closer()` returns Some for `zh-Hans` / `zh-CN` / `zh`, `ja` / `ja-JP`, `pt-BR` / `pt`. English (and unmatched locales) return None — system prompt stays byte-identical to the previous behavior for English users. The closer is appended after the previous-session handoff block (the existing "last block" position), so it's the very last content before the user's first message. Any future block that needs to sit closer to the user should be added BEFORE the closer with an updated test invariant. Three new tests pin the contract: * `locale_reinforcement_closer_returns_native_script_for_supported_locales` — each supported locale's closer is in its native script and explicitly mentions `reasoning_content` (the V4 knob). * `system_prompt_bookends_zh_hans_with_preamble_and_closer` — the full zh-Hans system prompt contains both `## 语言要求` (preamble) and `## 语言再次提醒` (closer), in that order, and no other top-level `##` section follows the closer. * `system_prompt_skips_locale_preamble_for_english` (extended) — English locale gets neither the preamble nor any of the three locale closers. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
6 tasks
Hmbown
pushed a commit
that referenced
this pull request
May 15, 2026
) When an OpenAI-compatible backend (vLLM, Ollama, LM Studio, Together AI, self-hosted vLLM/SGLang, etc.) streams an assistant message containing multiple tool_calls in a single round, only the **last** tool's `Event::ToolCallStarted` was firing. The preceding N-1 tool calls executed and produced tool_result events, but never announced their start to consumers (TUI / runtime API / embedder bridges), leaving them with N orphan tool_result blocks and no matching tool_use blocks in the assistant history. ## Reproduction ```text backend dispatches: 7 × write_file + 1 × exec_shell log shows: 7 × ApprovalRequired events ✓ listeners receive: 1 × chat:tool_start, 7 × chat:tool_end session history: 1 tool_use + 7 tool_result (6 orphans) ``` Tested against vLLM 0.7 + Qwen3.6-35B-A3B with a "scaffold 7-file Tauri template" prompt. Any model+backend combo that emits batch tool_calls trips this — typical when a single LLM round asks for multiple parallel file writes or edits. ## Root cause `run_turn` tracked the currently-streaming tool block with a single `current_tool_index: Option<usize>`. The Anthropic-style adapter (non-streaming response → events at `chat.rs::L1807`) emits Start/Stop pairs in lockstep so the slot never overlaps. But the OpenAI streaming parser (`chat.rs::L1954-2064`) emits every `ContentBlockStart::ToolUse` as soon as a tool_call delta lands, then batches every `ContentBlockStop` at `finish_reason`: ```text Start { index: 0 } // tool #1 Delta { index: 0, .. } Start { index: 1 } // tool #2 — overwrites current_tool_index Delta { index: 1, .. } … Start { index: 6 } // current_tool_index = Some(6) Delta { index: 6, .. } Stop { index: 0 } // take() returns Some(6) ← wrong tool! Stop { index: 1 } // take() returns None Stop { index: 2 } // take() returns None … ``` The first `Stop` consumes the last index and emits `ToolCallStarted` for the wrong `tool_uses` entry; every subsequent `Stop` finds the slot already `None` and skips the entire `if let Some(index) = …` branch, dropping the announcement. ## Fix Replace the single slot with `HashMap<u32 block_index, usize tool_uses_idx>`: - `ContentBlockStart::ToolUse` and `::ServerToolUse` insert the `(event.index → tool_uses.len())` mapping. - `InputJsonDelta` looks up by the `ContentBlockDelta` outer index. - `ContentBlockStop` removes by the stop's index, so each Stop routes to its own `tool_uses` entry regardless of arrival order. Routing no longer depends on `current_block_kind` (which has the same single-slot overwrite problem); `current_tool_indices.remove(&index)` returning `Some(_)` already proves the Stop belongs to a tool block. ## Tests Added `batch_tool_calls_preserve_all_tool_use_indices` in `core/engine/turn_loop.rs::tests` — feeds 7 Starts and 7 Stops through the same `HashMap` API used by `run_turn`, asserts every index round-trips. Manual end-to-end verification: vLLM + Qwen3.6-35B + 7-file Tauri template prompt → frontend `messages` history now contains all 7 `write_file` tool_use blocks paired with their tool_result blocks. Co-authored-by: hexin <he.xin@h3c.com>
This was referenced May 17, 2026
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.
Summary
This release streamlines the TUI interface and improves information density in the footer:
STATUS_SUCCESSto green andSTATUS_WARNINGto amber for better visual distinctionchrono::Local,uuid::Uuid,Color,Modifier) and simplified mode cycling commentThe changes maintain all functionality while improving UX clarity and reducing visual clutter.
Testing
cargo test --all-featurescargo fmt --all -- --checkcargo clippy --all-targets --all-featuresChecklist
https://claude.ai/code/session_011XiGZRhainhyvZ8BKKrfzj