| Files | Last commit | Last update |
|---|---|---|
chore(release): bump version to v5.1.0 | 1 month ago | |
docs: pretty-print search-index.{en,zh}.json and keep generator output formatted search-index.en.json and search-index.zh.json were committed as single-line minified blobs, hard to review in diffs. Format them with 2-space indentation and make build-search-index.mjs emit the same format (JSON.stringify(out, null, 2) plus trailing newline) so regeneration stays idempotent. Data is unchanged — only whitespace differs from before. Closes #1466 Co-Authored-By: AtomCode (qwen3.8-27b) <noreply@atomgit.com> | 2 months ago | |
feat(session): harden native session storage | 3 months ago | |
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 months ago | |
chore(release): bump version to v5.1.0 | 1 month ago | |
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 months ago | |
chore(release): finish v5.1.0 reference cleanup and fix y18n lockfile The v5.1.0 bump missed the follow-up cleanup that v5.0.9 had (eda3e3ef), leaving 5.0.9 test fixtures behind: - version_check.rs / updater lib.rs: version-compare fixtures - retained.rs / event_loop commands.rs: release branch refs - vscode process.ts / daemon-identity.test.ts: daemon identity Also revert a bogus dependency bump: the v5.0.9 release commit rewrote y18n from 5.0.8 to 5.0.9, a version that does not exist on npmjs or npmmirror (latest is 5.0.8), while keeping the 5.0.8 integrity hash. Restore 5.0.8 in both lockfiles. Co-Authored-By: AtomCode (deepseek-flash) <duxin@csdn.net> | 1 month ago | |
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 months ago | |
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 months ago | |
chore(release): bump version to v5.1.0 | 1 month ago | |
fix: shift+enter handling and optimize website performance - Fix shift+enter key combination handling in tuix - Optimize website performance: reduce dependencies, minify assets | 6 months ago |
| Files | Last commit | Last update |
|---|---|---|
| 1 month ago | ||
| 2 months ago | ||
| 3 months ago | ||
| 7 months ago | ||
| 1 month ago | ||
| 7 months ago | ||
| 1 month ago | ||
| 5 months ago | ||
| 7 months ago | ||
| 1 month ago | ||
| 6 months ago |
