nano-claude-code

English | 中文 | Français | 한국어 | 日本語 | Deutsch | Português

🔥🔥🔥 News (Pacific Time)

• 10:04 PM, Apr 05, 2026 (v3.05.5): Interactive Ollama Model Picker, Windows fixes, /brainstorm command

  • Interactive Ollama Model Picker — when a request fails with 404 (model not found), nano-claude now queries the local Ollama API (/api/tags) and presents a numbered model selector so you can switch to an available model and retry without restarting. Cancelling the picker aborts gracefully without crashing the REPL.
  • Windows file handling — _read, _write, and _edit in tools.py now force UTF-8 encoding and newline="" to prevent encoding failures with accented characters and double-CRLF on Windows. _edit detects pure-CRLF files (all \n are part of \r\n) and restores their line endings after edit; mixed-line-ending files are left as-is to avoid corruption.
  • /brainstorm command — /brainstorm [topic] runs a multi-persona AI debate with 5 specialized agents (Architect, Innovator, Security, Code Quality, Performance). Results are saved to brainstorm_outputs/ and synthesized by the main agent.
  • threading.RLock — replaced threading.Lock with RLock in the REPL loop to support re-entrant calls from brainstorm synthesis and Ollama retry paths.

• 05:39 PM, Apr 05, 2026 (v3.05.4): Reasoning, Rendering, and Packaging Improvements, Enhanced Memory System, Native vision support for local Ollama models, Bracketed Paste Mode, Rich Tab Completion

  • Bracketed Paste Mode — replaced the old timing-based multi-line paste detection with the standard terminal Bracketed Paste Mode protocol. Pasted text of any length (code blocks, long prompts, multi-paragraph instructions) is now collected as a single turn with zero latency and no blank-line artifacts. Falls back to a 60 ms timing window for terminals that don't support BPM. Bracketed paste mode is cleanly disabled on REPL exit.
  • Rich Tab Completion with descriptions — pressing Tab after / now shows every command with a one-line description and a hint of its subcommands. Typing /plugin then Tab lists all subcommands (install, uninstall, enable, …). Auto-completes to the unique match when only one command matches the prefix. Subcommands supported for /mcp, /plugin, /tasks, /cloudsave, /voice, /permissions, /proactive, and /memory.
  • Model name bug fix — --model ollama/qwen3.5:35b no longer gets corrupted to ollama/qwen3.5/35b. The startup colon-to-slash conversion now only fires when the left side of : is a known provider name and no / is already present, preserving Ollama's model:tag format.
  • Native vision support for local Ollama models (llava, gemma4, llama3.2-vision): new /image [prompt] command captures the current clipboard image, encodes it to Base64, and attaches it to the next prompt. Install Pillow with pip install nano-claude-code[vision]; Linux users also need xclip (sudo apt install xclip).
  • Enhanced Memory System — added confidence / source / last_used_at / conflict_group metadata to every memory entry; conflict detection on MemorySave warns before overwriting; MemorySearch re-ranks results by confidence × recency (30-day decay) and updates last_used_at on hits; new /memory consolidate command runs a lightweight AI analysis of the current session and auto-saves up to 3 long-term insights (user preferences, feedback corrections, project decisions) at 0.8 confidence — never overwrites higher-confidence user memories.
  • Post-merge fixes — removed a debug debug_payload.json file write that was firing on every OpenAI-compatible API call (left over from PR #11 development). Also fixed ANSI dim color not being reset after the thinking block ends, which caused subsequent text to appear dim in non-Rich terminals. Bumped pyproject.toml version to 3.05.4, and moved sounddevice to the optional voice extra (pip install nano-claude-code[voice]).
  • Native Ollama reasoning + terminal rendering fix — local reasoning models (deepseek-r1, qwen3, gemma4) now stream their <think> blocks to the terminal. Ollama exposes thoughts in msg["thinking"], but nano-claude was previously dropping them; this is now fixed by yielding ThinkingChunk from the Ollama adapter. Also fixed a Windows CMD/PowerShell rendering issue where token-by-token ANSI dim resets caused thoughts to print vertically, and corrected flush_response() so it runs once at the end instead of on every thinking token. Enable with /verbose and /thinking.
  • uv support — added pyproject.toml; install with uv tool install . to make the nano_claude command available globally from anywhere in an isolated environment, without manual PATH setup.

• 00:41 PM, Apr 05, 2026: v3.05.3 add structured session history — Structured session history: on every exit, sessions are saved to daily/YYYY-MM-DD/ (capped at session_daily_limit, default 5 per day) and appended to a master history.json (capped at session_history_limit, default 100). Each session file now includes session_id and saved_at metadata. /load groups sessions by date with time, ID, and turn-count display; supports multi-select (1,2,3) to merge sessions and H to load the full history with token-count confirmation. Both limits are configurable via /config.

• 00:41 PM, Apr 05, 2026: v3.05.3 fix session — Structured session history: on every exit, sessions are saved to daily/YYYY-MM-DD/ (capped at session_daily_limit, default 5 per day) and appended to a master history.json (capped at session_history_limit, default 100). Each session file now includes session_id and saved_at metadata. /load groups sessions by date with time, ID, and turn-count display; supports multi-select (1,2,3) to merge sessions and H to load the full history with token-count confirmation. Both limits are configurable via /config.

• 09:34 AM, Apr 05, 2026: v3.05.3 — Added GitHub Gist cloud sync: /cloudsave setup <token> to configure, /cloudsave to upload the current session to a private Gist, /cloudsave auto on to sync automatically on /exit, /cloudsave list to browse cloud sessions, and /cloudsave load <id> to restore from the cloud. Uses stdlib urllib — no new dependencies. Also added version number (e.g., v3.05.2) in the startup banner: The startup banner now displays the current version number (v3.05.2) in green, making it easy to identify which version is running at a glance.

• 08:58 AM, Apr 05, 2026: v3.05.2 — Introduced /proactive [duration] command: a background daemon thread watches for user inactivity and automatically wakes the agent up after the specified interval (e.g. /proactive 5m), enabling continuous monitoring loops without user intervention. /proactive with no args now shows current status; /proactive off disables it explicitly. Proactive polling state is stored in config (no module-level globals). Watcher exceptions are logged via traceback instead of silently swallowed. Also fixed duplicated output in Rich-enabled terminals by buffering text during streaming and rendering Markdown once via rich.live.Live — updates happen in-place for a true streaming Markdown experience.

• 10:51 PM, Apr 04, 2026: v3.05_fix04 — Fixed a crash on /model and config save commands caused by the newly introduced _run_query_callback being serialized to JSON; also added SleepTimer usage
  guidance to the system prompt so the agent knows when to invoke background timers proactively.

• 10:28 PM, Apr 04, 2026: v3.05_fix03 — Added a native SleepTimer tool that lets the agent schedule background timers and autonomously wake itself up after a delay — no user prompt required. Paired with a threading.Lock to prevent output collisions when background and foreground calls overlap. Also includes cross-platform fixes: Windows ANSI color support, CRLF-aware Edit tool matching, an interactive numbered menu for /load, native Ollama streaming via /api/chat, and auto-capping max_tokens per provider to prevent API errors.

• 08:31 PM, Apr 04, 2026: v3.05_fix — Autosave + /resume: session is automatically saved to mr_sessions/session_latest.json on /exit, /quit, Ctrl+C, and Ctrl+D. Run /resume to restore the last session instantly, or /resume <file> to load a specific file from mr_sessions/, and better support for api and local Ollama models (specifically gemma4), along with Windows c