| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
chore(release): bump version to v5.0.9 | 2 个月前 | |
fix(docs): 搜索结果锚点失效——生成器注入标题 id + 点击关闭弹窗 搜索小节链接指向 #<slug>,但页面标题没有对应 id(生成器只把 slugify 出的 id 写进索引、从没写回 HTML),导致所有 #小节 锚点滚 动不到任何地方。叠加 docs.js 点击结果不关闭弹窗,同页锚点点击被 overlay 遮住,看着"完全没反应"。 - build-search-index.mjs: collectHeadings/sectionsOf/injectHeadingIds 给每个缺 id 的标题注入与索引同源的 slugify id(页内去重),写回 HTML; 幂等(已有 id 原样不动)。索引 id 与 HTML 锚点从此一致。 - docs.js: 结果点击(委托 .search-item)与 Enter 导航前 close(), 同页锚点也能可见滚动。 - 重建 40 个 docs HTML(注入 id) + 两个 search-index.json。 验证:zh 266 + en 266 个小节锚点全部解析,0 缺失;幂等;HTML 改动 仅标题行加 id,零重格式化。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Provider-URL: https://gitcode.com/atomgit_atomcode/atomcode | 2 个月前 | |
feat(session): harden native session storage | 3 个月前 | |
feat: major architecture overhaul — context management, smart truncation, agent discipline Phase 1: Tool result externalization - ToolResultRef + ToolResultStore: large tool outputs cached to disk - Hot zone inflated from disk, cold zone uses summaries Phase 2: Turn-aware context windowing - TurnTracker: tracks conversation turns (user message → completion) - Budgeted windowing operates at turn granularity - Cold turns: only user question + assistant conclusion retained - Synthesized outcomes for turns without assistant text Phase 3: Smart per-tool truncation - bash: preserve error lines, skip verbose build logs - read_file: threshold raised to 2000 lines (prevents multi-read cycles) - First read of any file forces full content (ignores offset/limit) - edit_file returns compact diff + file outline after edit Agent discipline: - Sleep loop detection (warn at 2, block at 3+) - Repeated command detection (normalized, warn at 2, block at 3+) - Same-file multi-edit blocking (threshold 4) - Re-read soft reminder (not blocking) - Over-verification detection (3+ consecutive check commands) - HTTP 200 detection → stop verifying - 429 rate limit retry with exponential backoff (up to 5 retries) - Loop detection allows retry after edit (fix-then-retry is not a loop) - Intercepted/blocked calls don't count toward step limit - Bash pipe/cat detection with redirect to proper tools System prompt: - Restored v1.3.1 proven rules + new additions - ACT DON'T INSTRUCT / BE CONCISE / ONE SIGNAL IS ENOUGH - COMMAND DISCIPLINE / ERROR HANDLING sections - Glob wildcard guidance - Tech-stack neutral (zero specific tool/language names) Project context: - Added pom.xml, build.gradle, requirements.txt, composer.json, CMakeLists.txt to descriptors - Cross-session context: previous session turns injected into system prompt - Conversation history loaded on startup (not fresh each session) - Active services detection: port scanning on startup + URL extraction from bash output - Frontend hot-reload hint when dev server detected UX improvements: - TTFT per LLM call (not cumulative), removed from status bar - Spinner shows last tool name: "After read_file, thinking..." - Tool call streaming: shows file_path/command as args stream in - Turn completion summary: "✻ Completed in N steps, Xs" - Streaming markdown: trim incomplete backtick/bold tokens - Pangu spacing (CJK-ASCII) - Code block styling refresh - Append input during streaming (Enter sends additional context) - UTF-8 safe string truncation (char boundary check) Tooling: - edit_file: atomic_write retry on rename failure (dev server file locks) - edit_file: suggested fix on old_string mismatch - glob: rewritten pattern parser (handles absolute paths, **/ splits) - LLM request logging to ~/.atomcode/logs/ - Datalog analyzer script (scripts/analyze_datalogs.py) with --deep mode (Claude Code) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> | 7 个月前 | |
chore(release): bump version to v5.0.9 | 2 个月前 | |
feat: major architecture overhaul — context management, smart truncation, agent discipline Phase 1: Tool result externalization - ToolResultRef + ToolResultStore: large tool outputs cached to disk - Hot zone inflated from disk, cold zone uses summaries Phase 2: Turn-aware context windowing - TurnTracker: tracks conversation turns (user message → completion) - Budgeted windowing operates at turn granularity - Cold turns: only user question + assistant conclusion retained - Synthesized outcomes for turns without assistant text Phase 3: Smart per-tool truncation - bash: preserve error lines, skip verbose build logs - read_file: threshold raised to 2000 lines (prevents multi-read cycles) - First read of any file forces full content (ignores offset/limit) - edit_file returns compact diff + file outline after edit Agent discipline: - Sleep loop detection (warn at 2, block at 3+) - Repeated command detection (normalized, warn at 2, block at 3+) - Same-file multi-edit blocking (threshold 4) - Re-read soft reminder (not blocking) - Over-verification detection (3+ consecutive check commands) - HTTP 200 detection → stop verifying - 429 rate limit retry with exponential backoff (up to 5 retries) - Loop detection allows retry after edit (fix-then-retry is not a loop) - Intercepted/blocked calls don't count toward step limit - Bash pipe/cat detection with redirect to proper tools System prompt: - Restored v1.3.1 proven rules + new additions - ACT DON'T INSTRUCT / BE CONCISE / ONE SIGNAL IS ENOUGH - COMMAND DISCIPLINE / ERROR HANDLING sections - Glob wildcard guidance - Tech-stack neutral (zero specific tool/language names) Project context: - Added pom.xml, build.gradle, requirements.txt, composer.json, CMakeLists.txt to descriptors - Cross-session context: previous session turns injected into system prompt - Conversation history loaded on startup (not fresh each session) - Active services detection: port scanning on startup + URL extraction from bash output - Frontend hot-reload hint when dev server detected UX improvements: - TTFT per LLM call (not cumulative), removed from status bar - Spinner shows last tool name: "After read_file, thinking..." - Tool call streaming: shows file_path/command as args stream in - Turn completion summary: "✻ Completed in N steps, Xs" - Streaming markdown: trim incomplete backtick/bold tokens - Pangu spacing (CJK-ASCII) - Code block styling refresh - Append input during streaming (Enter sends additional context) - UTF-8 safe string truncation (char boundary check) Tooling: - edit_file: atomic_write retry on rename failure (dev server file locks) - edit_file: suggested fix on old_string mismatch - glob: rewritten pattern parser (handles absolute paths, **/ splits) - LLM request logging to ~/.atomcode/logs/ - Datalog analyzer script (scripts/analyze_datalogs.py) with --deep mode (Claude Code) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> | 7 个月前 | |
chore(release): bump version to v5.0.9 | 2 个月前 | |
docs(site): refresh main + docs site with i18n, search and unified design - rewrite main page as self-contained warm-dark + orange theme (no Tailwind) - restyle docs to match main: counters-numbered sidebar, callouts, prose tokens - add chrome i18n (zh/en) and Cmd+K full-text search via build-time index - split docs into docs/zh and docs/en; English translation for all 16 pages - hide headless-daemon from sidebar (still reachable via cross-references) - rename sidebar group 运维/Operations -> 问题/Help - make sidebar flow inline on narrow viewports and drop internal scrollbar Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> | 5 个月前 | |
feat: major architecture overhaul — context management, smart truncation, agent discipline Phase 1: Tool result externalization - ToolResultRef + ToolResultStore: large tool outputs cached to disk - Hot zone inflated from disk, cold zone uses summaries Phase 2: Turn-aware context windowing - TurnTracker: tracks conversation turns (user message → completion) - Budgeted windowing operates at turn granularity - Cold turns: only user question + assistant conclusion retained - Synthesized outcomes for turns without assistant text Phase 3: Smart per-tool truncation - bash: preserve error lines, skip verbose build logs - read_file: threshold raised to 2000 lines (prevents multi-read cycles) - First read of any file forces full content (ignores offset/limit) - edit_file returns compact diff + file outline after edit Agent discipline: - Sleep loop detection (warn at 2, block at 3+) - Repeated command detection (normalized, warn at 2, block at 3+) - Same-file multi-edit blocking (threshold 4) - Re-read soft reminder (not blocking) - Over-verification detection (3+ consecutive check commands) - HTTP 200 detection → stop verifying - 429 rate limit retry with exponential backoff (up to 5 retries) - Loop detection allows retry after edit (fix-then-retry is not a loop) - Intercepted/blocked calls don't count toward step limit - Bash pipe/cat detection with redirect to proper tools System prompt: - Restored v1.3.1 proven rules + new additions - ACT DON'T INSTRUCT / BE CONCISE / ONE SIGNAL IS ENOUGH - COMMAND DISCIPLINE / ERROR HANDLING sections - Glob wildcard guidance - Tech-stack neutral (zero specific tool/language names) Project context: - Added pom.xml, build.gradle, requirements.txt, composer.json, CMakeLists.txt to descriptors - Cross-session context: previous session turns injected into system prompt - Conversation history loaded on startup (not fresh each session) - Active services detection: port scanning on startup + URL extraction from bash output - Frontend hot-reload hint when dev server detected UX improvements: - TTFT per LLM call (not cumulative), removed from status bar - Spinner shows last tool name: "After read_file, thinking..." - Tool call streaming: shows file_path/command as args stream in - Turn completion summary: "✻ Completed in N steps, Xs" - Streaming markdown: trim incomplete backtick/bold tokens - Pangu spacing (CJK-ASCII) - Code block styling refresh - Append input during streaming (Enter sends additional context) - UTF-8 safe string truncation (char boundary check) Tooling: - edit_file: atomic_write retry on rename failure (dev server file locks) - edit_file: suggested fix on old_string mismatch - glob: rewritten pattern parser (handles absolute paths, **/ splits) - LLM request logging to ~/.atomcode/logs/ - Datalog analyzer script (scripts/analyze_datalogs.py) with --deep mode (Claude Code) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> | 7 个月前 | |
chore(release): bump version to v5.0.9 | 2 个月前 | |
fix: shift+enter handling and optimize website performance - Fix shift+enter key combination handling in tuix - Optimize website performance: reduce dependencies, minify assets | 6 个月前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 2 个月前 | ||
| 2 个月前 | ||
| 3 个月前 | ||
| 7 个月前 | ||
| 2 个月前 | ||
| 7 个月前 | ||
| 2 个月前 | ||
| 5 个月前 | ||
| 7 个月前 | ||
| 2 个月前 | ||
| 6 个月前 |
