CommandCodeAI/command-code

View on GitHub

Command Code AI — the best coding agent for open models.

Stars: 4k
Forks: 350
Open beginner issues: 0
Indexed issues: 306

Dominant language: No language data
License: No license data
Last GitHub push: Aug 4, 2026
Latest indexed: Sep 20, 2026
Contributing guide: No contributing guide
Code of conduct: Code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

306 open issues indexed

Provider API /v1/responses rejects Codex's tool_search_call / tool_search_output input items with 400 "Invalid input" Open

Difficulty 3/5 1-2 days Newbie friendliness 70/100

CommandCodeAI/command-code#893 · Opened Sep 20, 2026
Error: 400 This model's maximum context length is 1048576 tokens. However, you requested 1049647 tokens (985647 in the messages, 64000 in the completion). Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

CommandCodeAI/command-code#892 · Opened Sep 20, 2026
Session wedged over the 1M window: repeated 400 prompt-too-long despite auto-compaction (v1.58.0) Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

CommandCodeAI/command-code#891 · Opened Sep 20, 2026
Desktop app renderer crashes on launch (render-process-gone, exit code -2147483645 / STATUS_BREAKPOINT) on Windows 11 24H2 Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

CommandCodeAI/command-code#890 · Opened Sep 19, 2026
Feature request: read-only usage/balance API for Provider users Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

CommandCodeAI/command-code#889 · Opened Sep 19, 2026
Provider API: failed requests and no-op agent runs are billed in full ($15.56 in under 3 minutes on gpt-5.6-sol) Open

Difficulty 4/5 3-5 days Newbie friendliness 42/100

CommandCodeAI/command-code#888 · Opened Sep 18, 2026
BYOK DeepSeek thinking mode: multi-turn 400 'reasoning_content must be passed back' Open

Difficulty 3/5 1-2 days Newbie friendliness 76/100

CommandCodeAI/command-code#887 · 2 comments · Opened Sep 18, 2026
bug: In Plan review cannot paste text when commenting Open

CommandCodeAI/command-code#886 · 1 comment · 1 assignee · Opened Sep 18, 2026
Bug: Command Code 1.56.0 TUI does not accept keyboard input on Windows Open

Difficulty 3/5 1-2 days Newbie friendliness 58/100

CommandCodeAI/command-code#884 · 3 comments · Opened Sep 18, 2026
CRITICAL: Uncaught `write EPIPE` on macOS kills the session after a large built-in read_file result (no MCP involved) Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

CommandCodeAI/command-code#883 · 2 comments · Opened Sep 18, 2026
macOS: a path that differs only in letter case from the workspace root is flagged as outside the workspace Open

Difficulty 3/5 1-2 days Newbie friendliness 78/100

CommandCodeAI/command-code#881 · Opened Sep 18, 2026
Improve Korean (Hangul) input in the terminal — composing text is not visible Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

CommandCodeAI/command-code#880 · Opened Sep 18, 2026
Request: bless a stable headless contract so a Linux desktop client can embed `cmd` Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

CommandCodeAI/command-code#879 · Opened Sep 18, 2026
CLI abandons to-do list tracker during execution (Potential harness failure) Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

CommandCodeAI/command-code#878 · Opened Sep 18, 2026
BYOK: reasoning_content gets dropped from history, breaks multi-turn calls to thinking-mode models (400 Invalid_request_error) Open

Difficulty 3/5 1-2 days Newbie friendliness 58/100

CommandCodeAI/command-code#877 · Opened Sep 17, 2026
Sooo manyyy models for go plan that we cant use Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

CommandCodeAI/command-code#876 · 1 comment · Opened Sep 17, 2026
Detached sub-agent runs show "Done (0s | 0 tokens)" while running, never correct, and the Background panel lists no agent row Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

CommandCodeAI/command-code#874 · Opened Sep 17, 2026
CLI crashes (unhandled rejection) when a shell command contains a literal ${} — shell-quote parse throws in classifyShellCommand Open

Difficulty 3/5 1-2 days Newbie friendliness 72/100

CommandCodeAI/command-code#873 · 1 comment · Opened Sep 17, 2026
TUI hangs after `/compact` — input is blocked and the queued message is never sent Open

CommandCodeAI/command-code#872 · 2 comments · 2 assignees · Opened Sep 17, 2026
Scroll down with mouse wheel bugged Open

windows

CommandCodeAI/command-code#871 · 1 comment · 1 assignee · Opened Sep 16, 2026
Left side bar, switching among projects/chats often lags/freezes Open

windows

CommandCodeAI/command-code#870 · 1 comment · 1 assignee · Opened Sep 16, 2026
WSL Project Folder in Windows app Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

CommandCodeAI/command-code#869 · Opened Sep 16, 2026
✖ CRITICAL: Uncaught Exception! Open

windows

CommandCodeAI/command-code#868 · 1 comment · 1 assignee · Opened Sep 16, 2026
Regarding API rate limits Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

CommandCodeAI/command-code#866 · 1 reaction · Opened Sep 16, 2026
/tree crashes with RangeError: Maximum call stack size exceeded on sessions deeper than ~2k entries Open

Difficulty 4/5 3-5 days Newbie friendliness 70/100

CommandCodeAI/command-code#865 · 1 comment · Opened Sep 16, 2026
Cannot paste clipboard images into the CLI prompt Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

CommandCodeAI/command-code#864 · 2 comments · Opened Sep 16, 2026
Mod-registered tools cannot be scoped to a specific agent — addTool is global and no blocking hook receives agent identity Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

CommandCodeAI/command-code#863 · Opened Sep 15, 2026
Supports pnpm/yarn for cmd auto upgrade and the taste cli Open

Difficulty 3/5 1-2 days Newbie friendliness 55/100

CommandCodeAI/command-code#862 · Opened Sep 15, 2026
Project root is resolved inconsistently across surfaces (git root vs. cwd) — a project's .commandcode/mods/ can be silently unscanned, with no project-scoped override Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

CommandCodeAI/command-code#861 · 1 comment · Opened Sep 15, 2026
chatgpt plan shows up in /model but the session doesn\'t run as the selected model Open

CommandCodeAI/command-code#860 · 1 assignee · Opened Sep 15, 2026
Uncaught `write EOF` on Windows kills the session after a large MCP tool result Open

windows

CommandCodeAI/command-code#859 · 1 comment · 1 assignee · Opened Sep 15, 2026
CLI Issue - Losing Connection Mid-Prompt Open

Difficulty 5/5 Over a week Newbie friendliness 30/100

CommandCodeAI/command-code#858 · 12 comments · Opened Sep 14, 2026
Add ACP Support Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

CommandCodeAI/command-code#857 · Opened Sep 14, 2026
Unhandled Promise Rejection: Bad substitution: chunks[1].startOffset Open

Difficulty 3/5 1-2 days Newbie friendliness 48/100

CommandCodeAI/command-code#856 · 1 comment · Opened Sep 14, 2026
Bundled product reference names a non-existent memory file (COMMANDCODE.md) and links a repository URL that 404s Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

CommandCodeAI/command-code#855 · Opened Sep 14, 2026
Taste docs don't state whether global packages are applied to every project automatically or must be pulled in first Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

CommandCodeAI/command-code#854 · Opened Sep 14, 2026
Plan mode skips all hooks, disabling the guard layer in the mode recommended for security-sensitive exploration Open

Difficulty 5/5 Over a week Newbie friendliness 38/100

CommandCodeAI/command-code#853 · 1 comment · Opened Sep 14, 2026
Sub-agent tool calls bypass PreToolUse hooks and mod beforeToolCall hooks — only permission rules apply Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

CommandCodeAI/command-code#852 · 1 comment · Opened Sep 14, 2026
Allow disabling individual built-in models Open

p2

Difficulty 4/5 3-5 days Newbie friendliness 65/100

CommandCodeAI/command-code#851 · 1 comment · Opened Sep 14, 2026
Taste learning silently finds 0 Claude Code sessions when the project path contains spaces (encodeAgentProjectDir mismatch) Open

CommandCodeAI/command-code#849 · 1 comment · 1 assignee · Opened Sep 13, 2026
Application icon / title on the taskbar falshing on windows taskbar Open

windows

CommandCodeAI/command-code#848 · 4 comments · 1 assignee · Opened Sep 13, 2026
/learn-taste learns nothing from Codex sessions: extractor only reads legacy event_msg/user_message format Open

Difficulty 3/5 1-2 days Newbie friendliness 72/100

CommandCodeAI/command-code#847 · 1 comment · Opened Sep 13, 2026
TUI shows background sub-agent tool call as 0s / 0 tokens while the agent is still running Open

Difficulty 3/5 1-2 days Newbie friendliness 72/100

CommandCodeAI/command-code#845 · 1 comment · Opened Sep 13, 2026
Add a "Discuss" Mode Open

Difficulty 5/5 Over a week Newbie friendliness 38/100

CommandCodeAI/command-code#843 · Opened Sep 12, 2026
Show usage per API key Open

p2

Difficulty 4/5 3-5 days Newbie friendliness 55/100

CommandCodeAI/command-code#842 · Opened Sep 12, 2026
Shift+Enter can't insert a newline Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

CommandCodeAI/command-code#841 · 1 comment · Opened Sep 12, 2026
RuntimeError: memory access out of bounds in yoga-layout WASM during "Loading sessions" Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

CommandCodeAI/command-code#839 · Opened Sep 11, 2026
MaxListenersExceededWarning for resize after resume; one run later loses shell spawning with persistent EBADF Open

Difficulty 4/5 3-5 days Newbie friendliness 38/100

CommandCodeAI/command-code#835 · 5 comments · Opened Sep 10, 2026
Provider API: meta/muse-spark-1.3* fails with misleading "Stream error occurred" — non-streaming reveals HTTP 503 overloaded_error Open

CommandCodeAI/command-code#834 · 1 assignee · Opened Sep 10, 2026
todo_write removal-detection note causes an oscillating resubmission loop with literal-minded models (grok-4.6): case/rewording flips treated as "REMOVED unfinished items", recovery note mandates resubmission, never converges Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

CommandCodeAI/command-code#826 · 1 comment · Opened Sep 10, 2026

CommandCodeAI/command-code

Get new issues in your inbox