Repository Issue Activity (beta)

#683 TUI - bad color contrast in choices options in light mode

#779 Background shell tasks return empty logs; provider errors (too_many_images, timeouts) and subagent failures stall long coding sessions

#874 Detached sub-agent runs show "Done (0s | 0 tokens)" while running, never correct, and the Background panel lists no agent row

#897 Allow removing/canceling a queued message without interrupting the active run

#896 CLI startup cost: --version/-h load the full 2.6MB bundle; package installs 238MB (231MB transitive deps)

#858 CLI Issue - Losing Connection Mid-Prompt

#895 Feature request: `/btw` side-channel for asking questions without interrupting an active run

#894 Feature request: `/btw` side-channel for asking questions without interrupting an active run

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

#892 Error: 400 This model's maximum context length is 1048576 tokens. However, you requested 1049647 tokens (985647 in the messages, 64000 in the completion).

#891 Session wedged over the 1M window: repeated 400 prompt-too-long despite auto-compaction (v1.58.0)

#835 MaxListenersExceededWarning for resize after resume; one run later loses shell spawning with persistent EBADF

#872 TUI hangs after `/compact` — input is blocked and the queued message is never sent

#873 CLI crashes (unhandled rejection) when a shell command contains a literal ${} — shell-quote parse throws in classifyShellCommand

#887 BYOK DeepSeek thinking mode: multi-turn 400 'reasoning_content must be passed back'

#890 Desktop app renderer crashes on launch (render-process-gone, exit code -2147483645 / STATUS_BREAKPOINT) on Windows 11 24H2

#889 Feature request: read-only usage/balance API for Provider users

#652 Error: 400 Input length ____ exceeds the maximum allowed input length of ____ tokens

#885 Provider API `/v1/responses` rejects Codex's non-function tool types (tools.N.type) and breaks the endpoint for Codex

#888 Provider API: failed requests and no-op agent runs are billed in full ($15.56 in under 3 minutes on gpt-5.6-sol)

#884 Bug: Command Code 1.56.0 TUI does not accept keyboard input on Windows

#886 bug: In Plan review cannot paste text when commenting

#883 CRITICAL: Uncaught `write EPIPE` on macOS kills the session after a large built-in read_file result (no MCP involved)

#882 BYOK `opencode` or `opencode-go` not working due to missing `x-opencode-session`

#804 Feature request: Add OpenAI Responses API support