Nano-Collective profile

What's Changed

• Added a first-class provider template for Cheaper Inference, an OpenAI-compatible gateway, to the /settings providers wizard. Selecting it fills in the base URL (https://api.cheaperinference.com/v1) so only an API key and a model name are needed, and the wizard can fetch the account's model list over the standard /models endpoint.
• Added a showAgentBashOutput preference (/settings → Behavior → Tool Results and Thinking). By default a completed card for a command the agent runs shows the command and its status, and the command output is not kept; with compact tool display on, the card collapses into a tally line. This preference shows the output on that card, whether compact tool display is on or off, and for failed commands too. Commands you type yourself (!command) always show their output and are unaffected.
• Publish a JSON Schema for agents.config.json as schemas/agents.config.schema.json. It is generated deterministically from the on-disk DiskConfig type (pnpm run generate:schema), ships with an Ajv validation suite plus a CI drift check, and enables editor autocompletion — either by dropping the $schema key into your config or by wiring up the schema via jsonValidation / a JSON Schema mapping in your editor.
• Added automatic session titles. A session keeps its opening prompt as the title, and when that prompt is too thin to be useful the agent generates a descriptive name once, after the first turn that ran a tool or the first follow-up message. Manual renames are never overwritten.

Titling runs in the ACP agent, so it applies to the VS Code extension and other ACP clients; the CLI keeps its heuristic title. It uses the session's own model by default - set sessions.titleModel / sessions.titleProvider to point it at a cheaper or local one, or sessions.smartTitles: false to turn it off. Pointing titleProvider at a different provider sends it the opening user turns and a summary of the tools that ran, which includes file paths and bash command strings.

Two things worth knowing: the tokens a title costs are billed by the provider but are not counted in /usage, since the call is made outside the conversation loop that builds usage records; and existing sessions are retitled from their first message on their next autosave, which is a one-time visible reshuffle of the history list.

Also fixed the CLI's autosave deriving the session title from the latest user message and rewriting it on every save, which overwrote titles in the store the VS Code extension reads from. Closes #808.

• Added Anthropic prompt caching. The system prompt, tool schemas, and conversation history are now marked with cache breakpoints, so multi-turn sessions read the stable prefix back out of cache instead of paying full price for it every turn. Cost reporting is cache-aware throughout: /usage and the per-response indicator price cache reads and writes at their own rates instead of billing every cache hit at the full input rate, and the per-response indicator surfaces the cached token count alongside the total. Opt out with "promptCaching": false on the provider config. Closes #888.
• Fix multi-line paste submitting the prompt partway through.

Nanocoder never enabled bracketed paste, so the terminal delivered a paste as bare bytes and the carriage return at each line break reached Ink's keypress parser as Enter. Pasting two lines sent the first line to the model and left the second in the input box. Paste handling relied entirely on heuristics (input rate, size, line count) that only ever saw text which had already made it into the buffer.

DECSET 2004 is now enabled in both screen modes. Paste payloads are lifted off stdin before Ink sees them and delivered to the input as a single event, so a pasted newline can no longer submit. The old heuristics remain as a fallback for terminals without bracketed paste support.

Fullscreen mode enables mouse reporting for wheel scrolling, which takes click-drag text selection away from the terminal. Selection there is Shift+drag (Option+drag in iTerm2), or turn mouse reporting off for the session with --no-mouse.

• Add JSON exports for /export --json and .json filenames, preserving full message content and session metadata for replay and evaluation workflows. Closes #1309.
• Grouped each VS Code chat turn's thoughts, tool calls, edit cards, and task plan into one ordered, collapsible work summary while leaving the final answer visible. The summary reports completed, stopped, or failed duration and reopens for pending approvals. Thanks to @Gambit-Checkmate. Closes #858.
• Added support for a .nanocoderignore file. Patterns in it keep tracked-but-noisy files (lockfiles, generated fixtures) out of directory listings, file search and the file explorer, so they stop eating context even though .gitignore doesn't cover them. It is a context-hygiene tool rather than a secrets boundary: read_file and execute_bash don't consult it, and checkpoints deliberately skip it so hidden files are still snapshotted and restored. Thanks to @A-S-Manoj. Closes #755.
• Add configurable agent-loop retry limits to prevent token drain (#897). A new nanocoder.retries section in agents.config.json exposes the previously hardcoded caps: maxRepeatedToolCalls (default 3), maxEmptyTurns (default 2), and maxMalformedRetries (default 2). When the repeated-tool-call limit is hit in an interactive session, Nanocoder now pauses and asks whether to continue (granting another window of attempts) or stop, instead of always hard-stopping; non-interactive runs keep the hard stop. The same limits now also protect the --plain runtime used by nanocoder run in CI and non-TTY environments, which previously had no repeated-call cap at all: each cap hard-stops with a clear error there. Note this also loosens --plain in two places: it used to return an error on the first empty response and on the first malformed tool call, and it now nudges or asks the model to self-correct up to maxEmptyTurns / maxMalformedRetries before stopping, so a silent or malformed-output model costs up to 3 model calls instead of 1. Set either limit to 0 to restore the old fail-fast behaviour. Calls to unknown tools count toward the repeated-call streak in both runtimes, so a model stuck on a nonexistent tool trips the same cap instead of looping until the turn ceiling. Delegated subagent runs, whose loop previously had no cap at all, now apply maxRepeatedToolCalls too and stop with an error naming the setting.

One change reaches further than the retry limits themselves: a tool call naming a tool that does not exist is now kept in the assistant message's tool_calls rather than dropped from it. Without this the paired Unknown tool: X result was orphaned and pruned before the request went out, so the self-correction hint never reached the model and it re-emitted the same nonexistent call. This applies to all three runtimes that partition tool calls, including the ACP loop (--acp, used by editor clients), which is otherwise unaffected by the retry limits. The practical consequence is that providers now receive a tool call naming a tool that was not in the request's tool list.

• Add nanocoder config to see your settings and which file each one came from.

Settings come from four places: built-in defaults, your global config folder, the project folder you're in, and NANOCODER_* environment variables. When a setting didn't do what you expected, finding out which file set it meant opening all four by hand.

Three commands:

• nanocoder config list — every setting, its value, and the file it came from
• nanocoder config show <key> — one setting in detail: its default, and any values it beat
• nanocoder config diff — only what your files change, plus values that are set but unused

All three take --json.

The part worth knowing. Settings are grouped into blocks, like autoCompact. Nanocoder takes the whole block from the first file that mentions it — it does not mix fields from two files. So if your global config sets threshold and notifyUser, and your project config sets only threshold, your notifyUser

…

What's Changed

• Added first-class provider template for Groq to the setup wizard.

• Added first-class provider template for OrcaRouter to the setup wizard.

• Added a /commit slash command that generates Conventional Commit messages from staged Git diffs using the active LLM client. Thanks to @DeepamJha. Closes #757.

• Consolidated upload actions under a single '+' menu in the VS Code webview to reduce UI clutter and improve scalability for future attachment types.

• Added context attachment functionality with UI for file/folder chips and drag-and-drop support.

• Added Settings Tab to the VS Code extension webview for configuring providers and behavior directly from the UI.

• list_directory no longer includes file sizes by default — they cost an lstat syscall per file plus output tokens for information that's rarely needed just to orient in a directory. Pass showSizes=true to opt back in, or use read_file with metadata_only=true for a single file's size.

• Added a per-response token usage and estimated cost indicator. Every assistant message in the CLI now ends with a subtle gray footer showing the provider-reported token count and estimated cost (e.g. Tokens: 4.2k | ~$0.01), computed from models.dev pricing; the cost segment is omitted for local/free models and the footer falls back to the previous client-side estimate when the provider reports no usage. The VS Code extension shows the same indicator under each finished response, fed by the per-turn usage now returned on the ACP prompt response. Note: the estimate prices all input tokens at the standard rate — cache read/write discounts are not factored in, so costs can be overstated for providers with prompt caching. Closes #756.

• Moved the rest of nanocoder's configuration into the /settings menu, so you can set things up without editing .json files by hand. Settings are grouped into Appearance, Input, Behavior, Providers, MCP, and Advanced tabs. New menu items let you set the default mode, auto-compact, sessions, reasoning traces, tool auto-approval, and a Web Search API key; view your configured providers and MCP servers before opening the setup wizards; open the Tune Model and Connect IDE wizards; and see the active NANOCODER_* environment variables. Advanced also includes an in-app JSON editor for agents.config.json: edit strings with the cursor inside the quotes, flip booleans with the arrow keys, and save atomically (a crash can't leave a half-written file).

• Sunset /setup-providers and /setup-mcp in favour of /settings. Both retired names still work for now — they open the matching /settings tab with a notice instead of erroring. /settings now takes a tab argument (/settings providers, /settings mcp), MCP has its own settings tab, and provider edits made from settings apply to the running session instead of waiting for the next launch. Selecting a provider or MCP server in settings now opens that entry's edit/delete choice directly, with a separate row for adding a new one.

• Added editor code lenses to the VS Code extension: every function, method, constructor and class now carries Explain Code and Generate Tests links, and clicking one reveals the chat view and sends that symbol - instruction, file:startLine-endLine and the source, fenced with the document language - as a prompt. Symbols come from the language server, so no per-language parsing is involved, and the lenses can be turned off with nanocoder.codeLens. Long symbols are capped before being inlined, so a lens click on a large class cannot spend a whole context window on one turn. Also fixes a pre-existing hang where sending a message while a tool approval was still pending left the composer spinning forever. Closes #750.

• Added @ mention autocomplete to the VS Code extension's chat composer: typing @ opens a floating dropdown of workspace files, folders and open editors, and selecting one attaches it as a context chip. Search runs on the extension host, which merges your files.exclude and search.exclude settings into the exclude list so hidden files stay out of the dropdown, and a bare @ lists open editor tabs with no disk I/O. Attached files are now read with a 100 KB cap and binaries are skipped, so a mis-picked lockfile can no longer swallow the context window. Closes #747.

• Added support for image uploads and pasting in the VS Code extension chat panel, allowing users to send multimodal messages (text + images) to the AI assistant.

• VS Code extension: Added /copy code and a Ctrl+Alt+Shift+C (Cmd+Alt+Shift+C on macOS) keybinding to copy the last code block from the previous assistant response.

• Added a copy-to-clipboard button to the VS Code extension's chat panel: hovering over a user prompt or agent response bubble reveals a clipboard icon that copies the raw markdown text and briefly shows a checkmark to confirm. Streamed agent responses always copy the latest in-progress text. Closes #746.

• execute_bash and custom tools now truncate long output by keeping both the head and the tail (tail-weighted) instead of only the head, so the actionable part of compiler/test-runner output (error list, failure summary, exit status) — which usually lands at the end — isn't discarded.

• Bound string_replace results to a context window around the edited range.

• Fixed the Atlas Cloud wizard to store provider-qualified GPT-5.6 model IDs, while preserving compatibility with existing shorthand configurations. Thanks to @RealBhupesh. Closes #803.

• Bound oversized tool results before they re-enter model context while preserving both the beginning and the actionable tail.

• Fixed diff_edit returning the entire modified file by limiting results to changed-region previews. Thanks to @RealBhupesh. Closes #795.

• Added a nanocoder svg pulse effect as a visual loading indicator in vscode extension. It uses the provided svg and css to create a pulsing animation that indicates when the agent is processing a request.

• Added /commit --copy (short form -c), which copies the generated Conventional Commit message to the system clipboard. If the clipboard is unavailable the message is still shown with a note, rather than being lost, and an unrecognised option now reports a usage line instead of being silently ignored. /commit also shows a spinner while the model generates the message, so the round-trip is no longer a silent pause - commands opt into this by declaring progressLabel.

• Defer ink and @/app loading in the CLI entry point until the interactive TUI branch, so --acp, --plain and auth paths no longer pay the Ink/App module-graph cost at startup.

• Fixed bash commands entered with ! keeping the whitespace that followed the prefix, so ! git status now runs git status instead of git status.

• Fixed the VS Code extension's stop button leaving a request running. Two holes: AcpSession.cancel() aborted the current controller and immediately replaced it with a fresh one, so a cancel that landed before the turn read the signal — the window while the agent is still resolving the prompt's file references — handed the turn an unaborted controller and the stop was lost. The controller is now rotated when a turn begins instead. Separately, the extension never answered the agent's pending permission request when you hit stop: the tool card kept its spinner and Allow/Deny buttons, and because the request stayed on the pending list every later message was refused with "Please approve or deny the pending tool before sending a new message" until the window was reloaded. Stopping (or reconnecting after the agent process restarts) now resolves those requests as cancelled. Thanks to @akramcodez. Closes #864.

• Fixed Cannot read properties of undefined (reading 'summaryParts') when streaming from GitHub Copilot with reasoning models such as gpt-5.3-codex. Copilot's Responses API proxy rotates the opaque reasoning item id mid-stream while output_index

…

What's Changed

• Added the ability to attach to a running subagent session from the terminal UI for interactive debugging. This feature allows users to inspect exactly what a subagent is doing in real-time, including streaming text and reasoning. You can press Ctrl+S while a subagent is running to attach to it, cycle between multiple running subagents, and press Esc to detach.

• Added privacy-aware prompt scrubbing. A new PrivacyContext scrubs sensitive content from prompts before they leave your machine, with tool-argument rehydration and privacy session support, a /privacy command to inspect what is being scrubbed, and automated scrubbing telemetry notifications. Thanks to @akramcodez.

• Added an interactive questions system for plan mode, so the agent can ask structured questions while planning instead of guessing. Thanks to @akramcodez. Closes #96.

• Added mode-specific provider and model configuration, so each development mode can use its own provider and model. Thanks to @akramcodez. Closes #277.

• Added dual TUI screen modes, with a more reliable /clear and graceful exit handling. Thanks to @llupRisinglll.

• Added multiline cursor navigation and word-jump in the input box. Thanks to @llupRisinglll.

• Added --resume / --continue CLI session flags. --continue (-c) resumes the most recent session for the current directory, and --resume [id] (-r) resumes a session by id, list index, or last, with a bare --resume opening the session picker at startup. Thanks to @llupRisinglll.

• Added a fuzzy search filter to the /model picker, with a capped, centered scrolling window so large model catalogs no longer overflow the terminal and the current model is preselected. Thanks to @rakshith1928. Closes #683.

• Added PDF and DOCX support to read_file via get-md, so those documents can be read directly. Thanks to @akramcodez.

• Added a doctor diagnostic command that checks your setup and reports common configuration problems. Thanks to @Dhirenderchoudhary. Closes #609.

• Added a retry command to re-run the last user turn. Thanks to @Dhirenderchoudhary. Closes #608.

• Added message queueing while the agent is busy so you can type ahead. Queued messages can be recalled before streaming, are truncated properly on narrow terminals, and no longer double-dispatch. Thanks to @Dhirenderchoudhary. Closes #597, #598.

• Added estimated dollar cost tracking to /usage, with a per-provider cost breakdown and a cumulative per-call cost history. Thanks to @rakshith1928. Closes #602.

• Added a --json output flag to the non-interactive plain run path. Thanks to @OMEE-Y.

• Added a diff_edit tool for nano-profile models. Thanks to @Dhirenderchoudhary. Closes #604.

• Added automatic diagnostics after file edits, surfacing errors introduced by an edit right away. Thanks to @2409324124. Closes #538.

• Added the foundation for semantic memory (storage layer and initial wiring), groundwork for upcoming memory features. Thanks to @Dhirenderchoudhary.

• Reworked the client to a stateless API with history-boundary rehydration, improving conversation reliability. Thanks to @akramcodez.

• Added a Together AI provider template and docs, and MiniMax Coding now defaults to MiniMax-M3. Thanks to @octo-patch. Added Atomic Chat local provider configuration docs. Thanks to @yanalialiuk.

• Fix: nanocoder.tune loading and configuration precedence from agents.config.json now resolve correctly. Thanks to @rakshith1928. Closes #648.

• Fix: patch malformed SSE termination strings from providers, preventing stream parsing errors. Thanks to @akramcodez. Closes #614.

• Fix: bound slash command completions so the menu no longer overflows. Thanks to @2409324124. Closes #624.

• Fix: decouple console log verbosity from NODE_ENV and quiet noisy LSP discovery logs. Thanks to @A-S-Manoj. Closes #606.

• Fix: removed the strip-ansi runtime dependency. Thanks to @2409324124. Closes #643.

• Docs: added a Simplified Chinese README and Traditional Chinese translations, with fixes to the Simplified Chinese copy, plus a star-history chart. Thanks to @2409324124, @jason1015-coder, and @zerone0x.

• Updated dependencies: @ai-sdk/google, @ai-sdk/openai-compatible, undici, diff, and knip.

• The VS Code extension saw major work this cycle (ACP process manager and handshake, a chat sidebar webview with tool-permission and diff UI, session persistence, and Tailwind styling). It is versioned separately from the CLI. Thanks to @akramcodez and @Dhirenderchoudhary.

• File tools now resolve relative paths against the shell's current working directory, and cd in bash persists across commands — so relative reads and edits work after moving into a subdirectory or worktree. File tools also accept absolute paths that point inside the project, and can still reach the project root or a sibling worktree after cd-ing into a subdirectory.

• Added a tabbed /settings dialog with searchable categories, so settings are easier to scan and filter from the TUI. Thanks to @llupRisinglll. Closes #471.

• Added a native VS Code GUI. The VS Code extension now ships a sidebar chat powered by the Agent Client Protocol (ACP): the extension spawns and manages nanocoder --acp itself - nothing to run in a terminal. Responses stream with collapsible thinking sections, tool activity renders as live cards, and file edits open in VS Code's diff viewer. Thanks to @akramcodez.

• Sessions in the GUI: conversations persist to disk, with a New Chat action, a session history view with resume and delete, and full thread replay (including thinking and completed tool cards) on resume.

• Provider, model, and mode switching from dropdowns in the chat header, with the model list refreshing on provider switch.

• Slash commands in the GUI: /help, /clear, and custom commands from .nanocoder/commands; CLI-only commands explain themselves, and messages starting with file paths are not mistaken for commands.

• Interactive tools in the GUI: ask_user questions render with one button per answer; tool approvals show Approve/Deny inline.

• Live progress: subagent runs stream token/tool counts onto their card, and the task tool (write_tasks) renders as a live checklist via ACP plan updates - which also lights up in other ACP clients like Zed.

• Cancellation: Stop ends the whole turn - the current tool aborts, queued tools are skipped, and no follow-up model request is issued.

• Robust CLI spawning: the extension resolves the login shell's PATH (nvm-friendly when VS Code launches from the Dock), runs the CLI in the workspace folder, validates nanocoder.cliPath, and surfaces the last stderr line in the crash dialog. Fixed a silent --acp startup crash when the working directory was unwritable.

• Legacy WebSocket companion mode is now opt-in (nanocoder.autoConnect defaults to off); extension docs rewritten around the GUI.

• Fixed static vs. live content misalignment in --alt-screen

…

What's Changed

• Added image attachments on user messages. Paste an image from the clipboard with Ctrl+V (via osascript on macOS, wl-paste/xclip on Linux, PowerShell on Windows), drag an image file into the terminal, or type a path - quoted, unquoted, and macOS backslash-escaped paths are all recognised, and http(s) URLs are left untouched. Attachments (PNG/JPEG/GIF/WebP, up to 10 MB) show above the input box and Ctrl+X removes the last one; references are stripped from the text and sent as image parts to vision-capable models. A missing clipboard tool now logs a debug breadcrumb instead of silently no-op'ing. Thanks to @ragini-pandey. Closes #572.

• Added skill promotion and demotion. Skills can now be promoted and demoted between project and personal scope, with a --move flag to relocate rather than copy the skill files.

• Fix: slash commands now run with their arguments. Once a space is typed after a slash command, the completion menu hides so Enter submits the full command with its arguments instead of selecting a completion and dropping everything after the command name.

• Fix: the chat view no longer snaps to the bottom when a slash command completion menu opens. The completion and file-suggestion menus now render inside the bounded input layout, so the container expands without disrupting the window height calculation that previously forced the history to scroll in smaller terminals. Thanks to @Dhirenderchoudhary. Closes #581.

• Fix: empty frontmatter blocks are recognised instead of leaking --- markers into the body or throwing. splitFrontmatter now matches an empty block, and extractRawFrontmatter uses the shared parseYamlObject helper so an empty subagent frontmatter flows through to validation and surfaces a clear name is required error. Thanks to @Fadhlan. Closes #592.

• Fix: ask_user unwraps label-as-key option objects, so options expressed as a { label: value } map render as readable choices.

• Fix: surface real network errors instead of mislabeling them as context overflow. A failed request from a network error is no longer misreported as exceeding the context window.

• Fix: size MoE models by total parameter count, not active count, when auto-resolving the tool profile, so mixture-of-experts models get the correct tune.

• Fix: number formatting on the /copy command output.

• Docs: clarified MCP tool profile visibility and documented the image-attachments feature. Thanks to @zerone0x. Closes #593.

If there are any problems, feedback or thoughts please drop an issue or message us through Discord! Thank you for using Nanocoder.

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.28.0...v1.28.1

What's Changed

• Added Agent Client Protocol (ACP) support. Nanocoder can now run as an ACP agent (nanocoder --acp), exposing its conversation, tool-calling, and permission flows over the protocol so it can be driven by ACP-compatible editors and clients (Zed and others). New source/acp/ module covers the agent, server, session, conversation loop, content conversion, capability negotiation, and permission handling. Thanks to @Avtrkrb. Closes #529. Follow-up work added the missing ACP docs, kept the parallel tool-execution loop in sync with the plain shell, and made NANOCODER_MAX_TURNS configurable (with a raised default) so long ACP and plain-mode runs are not cut short.

• Consolidated the built-in tool surface from 33 tools down to 19 and added automatic tool profiling. Tasks collapse from four tools into a single TodoWrite-style write_tasks (replace-whole-list, no IDs for the model to juggle); file ops merge delete/move/copy/create_directory into one file_op; git shrinks from eleven tools to six (status/diff/log/add/commit/pr) with rarer operations going through execute_bash. A new auto tune profile - now the default - infers full/minimal/nano from the model's parameter count, so small local models automatically get the slim tool set and prompt while large/cloud models are unchanged. The resolved profile re-resolves live on model switch and is surfaced in the input indicator (e.g. tune: nano (auto)). /usage and the context indicator now rebuild from the live tune/mode/model with the profile-filtered tool count, so usage and context reporting are trustworthy. Roughly 6.3k lines removed.

• Added structured tool results and single-source validation. Tool arguments are now type-checked against each tool's JSON schema at the execution boundary (schema-validate.ts), so malformed model output returns a clear field-level error the model can self-correct from, instead of being coerced at the render layer. Validation runs through the single withValidation seam shared by both the native and XML-fallback execution paths, ahead of any per-tool validator. Approval policy is likewise centralised and the old global mode context removed, so the current development mode (including a mid-run switch) is honoured consistently across the main loop and subagents.

• Added session resume with full history replay. Resuming a saved session now replays the message and tool-call history into the chat view via a new session-history-renderer, so you pick up exactly where you left off with the conversation visible rather than an empty screen. Companion fixes resolved an autosave race, history-truncation, and resume edge cases, with regression coverage. Thanks to @akramcodez. Closes #545.

• Added the /copy command to copy the most recent assistant response to the system clipboard. Cross-platform via clipboardy (pbcopy / xclip / clip.exe), with a clear warning when there is no assistant message and a surfaced error when the clipboard write fails.

• Added read-before-edit guards and tool-call loop detection for local models. string_replace and write_file now require the file to have been read first, and a tool-signature tracker detects a model repeating the same tool call in a tight loop. Both make smaller local models materially safer to run unattended.

• Added a skill linter (/skills check <name> and a check_skill tool) that validates a bundle from disk with the same parsers the loader uses, so a PASS means it will load. It is wired into /skills create so the model verifies and self-corrects what it generates, and it lints member template bodies (unsupported mustache tags, unbalanced or unclosed sections, placeholders referencing undeclared parameters), not just frontmatter. Also added optional command arguments: inline defaults (name=default) and conditional sections ({{# name }}, {{^ name }}) in command bodies, plus inverted-section support in custom-tool templates via a shared section engine. Fixed subagents ignoring the development mode (the executor captured normal once at startup and never updated it).

• Added Atlas Cloud as a first-class provider and sponsor, with a wizard onboarding template and a dedicated provider docs page.

• Added the Requesty provider (https://requesty.ai) as a first-class OpenAI-compatible provider, mirroring the OpenRouter integration with a name matcher, app-attribution headers, a wizard onboarding template, and docs. Thanks to @Thibaultjaigu. Closes #589.

• Added API-reported context usage with an estimate fallback. The ctx: NN% indicator now reflects provider-accurate token counts when the model reports them (captured from the final step's usage, not the tool-loop-summed totalUsage), falling back to client-side estimation otherwise. Estimated figures are marked with a leading ~ (ctx: ~42%); API-reported figures render bare. Thanks to @JimStenstrom. Refs #381. Follow-up work anchored the API figure across turns, counted real tool definitions in the auto-compact gate, and added a tiktoken-based generic fallback tokenizer for more accurate counts on models without a native tokenizer.

• Added git branch display in the boot summary and /status panel, with a narrower-terminal-friendly rendering. Thanks to @ragini-pandey. Closes #539.

• Reworked provider model discovery UX in the wizard, surfacing real discovery errors instead of silently falling back, and showing model names in the selection list with long labels truncated by ellipsis. Thanks to @akramcodez and @Dhirenderchoudhary. Closes #554.

• Added arrow-key navigation and highlighting for slash-command completion. The completion menu now navigates with the arrow keys, with the double-submit-on-select bug fixed (TextInput ignores Enter; UserInput handles select-then-submit behind a guard flag) and customCompletion restored. Thanks to @rakshith1928. Closes #578.

• Added a force-compact-and-retry fallback. When the LLM server rejects a request for exceeding its context window, nanocoder now compacts and nudges the conversation to continue instead of failing outright. Thanks to @lordoski. Closes #546.

• Added timeout, output limits, and abort support to the bash executor, with regression tests covering the executor lifecycle. Thanks to @akramcodez. Closes #547.

• Custom display: failed tool results condense to a one-liner in compact mode. Generic Error: / Validation failed: results now render as a short red line (e.g. write_file failed.) in compact display mode, while the model still receives the full error in history and non-compact mode still shows it in full.

• Improved ask_user prompt rendering: dropped the leading ? from the header, fixed spacing and the hanging indent, added arrow-key navigation, and normalised object-shaped options to readable strings (preferring a label over a value id).

• Improved @-file-mention handling: mention placeholders are kept in the chat instead of being expanded inline, and large-file inlining is capped to avoid blowing up the prompt.

• Fix: Copilot GPT-5 reasoning streams are now handled correctly via an @ai-sdk/openai patch and chat-handler changes, so reasoning content streams properly instead of breaking the response. Thanks to @EntropyParadigm. Closes #577.

• Fix: propagate AbortSignal to streaming bash execution, so cancelling a turn actually stops a long-running streamed command. Thanks to @Dhirenderchoudhary. Closes #550.

• Fix: prevent silent overwrite of corrupted config files. A corrupted agents.config.json no longer gets silently clobbered; the wizard now honours the projectDir prop for config-path resolution and the infinite render loop on the existingProviders

…

What's Changed

• Added Skills, a unified extension primitive that brings commands, subagents, and tools under a single ergonomic surface. Two forms over one primitive: single-file (a .md in .nanocoder/commands|agents|tools/, fully backwards-compatible with the existing flat dirs) and bundle (a directory under .nanocoder/skills/<name>/ with skill.yaml plus optional commands/, agents/, tools/ subdirs). Bundles are for multi-piece features that need to ship and version together: a bundle's subagent automatically gets its sibling tools, scoped tools are hidden from the global tool list (default for bundles, opt-in for single-file), and bundle commands auto-namespace (commands/status.md in bundle git invokes as /git:status). New /skills slash command lists everything loaded, and bundled members fan out into the existing CustomCommandLoader, SubagentLoader, and ToolManager.registry so downstream consumers keep using their familiar registries. Closes #515.

• Added event-triggered skill runs via a new per-project daemon. Skill members can declare subscribe: blocks in frontmatter (or a bundle manifest) and the daemon wakes them on file.changed and schedule.cron events. The daemon (nanocoder daemon <start|stop|status|logs>) runs as a long-lived background process with a lockfile, Unix-socket IPC, and installers for launchd (macOS) and systemd user units (Linux). The interactive TUI never starts event sources, so file watching and cron only run when you opt in. Triggered runs execute in a new internal headless mode (no ask_user, no foreground confirmations) which supersedes the legacy scheduler mode. Per-subscription confirm: true opts into plan mode instead. Backpressure caps per-subscription concurrency and trailing-debounces file.changed by 500ms so chatty save loops don't pile up.

• Removed the legacy source/schedule/ module (runner, storage, index, types). Schedules are now expressed as schedule.cron subscriptions on a skill member and dispatched by the daemon. The old useSchedulerMode hook, scheduler-view component, and the .nanocoder/schedules.json / .nanocoder/schedules/*.md storage layout are gone. The /schedule command has been trimmed and refocused around the new model. Closes #524.

• Added Custom Tools: markdown-defined, model-callable tools that sit between custom commands (prompt injection only) and MCP servers (full external process). Drop a .md into .nanocoder/tools/ (project) or ~/.config/nanocoder/tools/ (personal), declare parameters in YAML frontmatter (with JSON Schema-style type, required, pattern, maxLength, etc.), and write a shell command body using {{ name }} and {{# section }} template placeholders. All substitutions are shell-quoted to prevent injection. Includes approval (always/never) and read_only flags that participate in mode policy: plan mode requires approval=never && read_only=true, scheduler/headless requires approval=never. New /tools create <name> scaffolds a template and asks the model to help fill it in. Project tools shadow personal ones by name, and they register into the same ToolManager registry as built-ins and MCP tools so /tools, subagents, and mode filtering see them through a single unified registry. Closes #520.

• Added LLM-based context compaction as the default /compact strategy. The active model writes a structured markdown summary of the compressible segment (Context / Decisions / Files modified / Tools used / Open questions) using a dedicated summariser prompt, replacing the older messages with one synthetic summary while recent messages are kept verbatim. Higher fidelity than mechanical truncation at the cost of one extra round-trip. New strategy field in autoCompact config (llm default, mechanical legacy), new CLI flags (--llm, --mechanical, --strategy <name>), and automatic fallback to mechanical compression on LLM failure (network error, empty response, summary larger than original). Auto-compact uses the same strategy.

• Added OpenRouter request configuration via a dedicated openrouter block on the provider config. Forwards OpenRouter-specific request body fields (provider routing rules, reasoning, plugins, models fallback list, service_tier, route, user, etc.) on every request - always-on transport/routing concerns, not gated by /tune. Provider is detected by name (case-insensitive). tune.modelParameters.reasoningEffort populates openrouter.reasoning.effort when unset; explicit values on the provider config always win. Closes #519.

• Added config lint at startup. Surfaces common misconfigurations as warnings before they cause silent failures - e.g. an openrouter block on a provider that is not OpenRouter, unknown fields, type mismatches. Includes a full test suite. Closes #523.

• Reworked OpenRouter model selection in the provider wizard. Replaced the previous list with a paginated, searchable ModelSelectionList (12 visible items, page navigation, multi-select with running counter, select-all, error state). Makes browsing OpenRouter's hundreds of models actually usable from the wizard. Closes #516.

• Added unified Session Service for key generation and session infrastructure. Consolidates the various ad-hoc keying strategies scattered across commands, handlers, and tool result display into one place. Touched 50 files across handlers, commands, hooks, and the chat handler, removing duplicated key-derivation logic and shrinking useAppState by ~38 lines. Fully closes #229.

• Added the Nanocoder Battlemap - a long-form competitive comparison doc covering Nanocoder against Claude Code, OpenAI Codex CLI, Gemini CLI, Aider, OpenCode, Crush, and Pi across twelve axes (license, pricing, local-model support, MCP, extensibility, tool-calling, subagents, surface, plain mode, stars, contributors, telemetry). Honest where Nanocoder leads, honest where it does not. Closes #423.

• Made code blocks copyable without ASCII artifacts. Reworked the markdown parser and AssistantMessage rendering so fenced code blocks render as plain selectable text without surrounding box borders that previously got copied into the clipboard. Thanks to @aravindinduri.

• Fix: streaming OOM on long responses. StreamingMessage was calling wrapWithTrimmedContinuations() on the entire growing assistant message on every ~150ms flush, allocating per-line arrays proportional to the full message size. A ~37k-token (~150 KB) response would overwhelm GC and crash the 4 GB Node heap. Now slices the message to a bounded tail (MAX_LINES * textWidth * 4 chars, snapped to a newline boundary) before wrapping, so per-render work is constant in the visible window rather than linear in total streamed content. Thanks to @abhishekDeshmukh74. Closes #526.

• Fix: performance entry buffer OOM in long sessions. React 19's react-reconciler (dev build) calls performance.measure/performance.mark on every render, and Node's built-in fetch (undici) pushes a resource-timing entry per HTTP request. Both write to the same global buffer, which nanocoder never drained. Over long subagent-heavy sessions the buffer accumulated millions of entries until V8 thrashed in mark-compact GC and crashed with Ineffective mark-compacts near heap limit. Fix installs an unref'd 30s interval that calls performance.clearMarks() / performance.clearMeasures() in the Ink render path. Thanks to @ragini-pandey. Closes #521.

• Fix: auto-compact ignored the per-provider contextWindow

…

What's Changed

• Bumped @nanocollective/get-md to ^1.4.0, which makes node-llama-cpp an optional peer dependency. Drops the entire node-llama-cpp transitive — including ~500 MB of platform-specific native binaries (CUDA, Vulkan, Metal, ARM variants) that pnpm fetched eagerly regardless of host — from the install graph and the Nix closure. The fetch_url tool (the only consumer of get-md) uses the standard HTML→Markdown path which doesn't need the LLM converter, so there's no functional change.

• Patched flake.nix for pnpm 11 compat. Overrides nixpkgs's bundled pnpm (currently 10.x) to pnpm 11.0.9 to match packageManager, then handles two pnpm-11-specific quirks: chmod +x on bin/pnpm.cjs (a Corepack-compat shim shipped without the execute bit by upstream) and a replaceStrings patch on fetchPnpmDeps's installPhase to skip the now-rejected pnpm config set manage-package-manager-versions false global write. Unblocks the update-nix.yml workflow that's been failing on ERR_PNPM_LOCKFILE_CONFIG_MISMATCH.

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.26.0...v1.26.1

What's Changed

• BREAKING: Removed redundant nanocoderTools.alwaysAllow setting. It duplicated the top-level alwaysAllow with no extra behaviour. Move any entries from nanocoderTools.alwaysAllow to the top-level alwaysAllow array in agents.config.json. The deprecated agents.config.example.json has also been removed.

• Added nano mode — a third tool profile under /tune designed for the smallest open-weights models or low-end hardware running larger models locally. Strictly more aggressive than minimal: drops find_files, list_directory, and agent; trims CORE PRINCIPLES and CODING PRACTICES; uses ≤4-line TASK APPROACH, FILE OPERATIONS, and CONSTRAINTS sections; replaces the verbose SYSTEM INFORMATION block with a single-line ## SYSTEM line; and omits AGENTS.md from the prompt by default. Brings the system prompt from ~500–700 tokens (minimal) down to ~150–250 tokens. Includes a new "Nano (low-end hardware)" preset and an Include AGENTS.md toggle.

• Added reasoning trace support. Reasoning content from models (Codex GPT-5, DeepSeek-R1-style, Anthropic extended thinking, etc.) now streams in real time, renders as a collapsible Thought block above the response, persists across history, and is included in logs. Toggle expansion with Ctrl+R, configure default expansion via the new Display Settings panel, and pin per-session via the tune expandedReasoning option. <think> tags are now stripped on the native tool-calling path so reasoning never leaks into rendered output. Thanks to @Daniel5055. Closes #457.

• Added refined non-interactive mode. A new --plain flag streams output suitable for CI pipelines, scripts, and pipes — no Ink rendering, no interactive prompts, deterministic exit codes, and proper handling of stdin/stdout. Includes a dedicated non-interactive-shell component and full test coverage for the plain transport.

• Reworked VS Code extension integration. Removed the "Ask Nanocoder" command in favour of a more natural flow: highlighted text and the currently focused file are automatically pulled into Nanocoder as context. Backed by a rewritten extension protocol, a simplified extension entrypoint, a new useVSCodeServer hook, and tighter UI hooks for the development mode indicator and chat input.

• Added /rename command for renaming the current chat session. Accessible from the chat input and reflected in the development mode indicator. Thanks to @lordoski.

• Added defaultMode config option for interactive sessions. Set a starting mode (normal, auto-accept, yolo, plan) in agents.config.json instead of always launching in normal mode. Thanks to @lordoski.

• Added custom system prompt support via agents.config.json. Define a project-level system prompt that replaces or augments the built-in prompt sections, with full validation and prompt-builder integration. Closes #487.

• Added per-provider and per-model context window overrides in agents.config.json via contextWindow and contextWindows[model]. New resolution order: session override (/context-max, --context-max) → provider model override → provider default → NANOCODER_CONTEXT_LIMIT → models.dev / Ollama fallback. /usage, status bar, auto-compact, and context reporting all use the active provider config consistently. Closes #455.

• Added subagent context window overrides so delegated agents can run with a different context limit than the main session. Thanks to @zerone0x.

• Added disabledTools config option in agents.config.json to disable specific built-in tools project-wide. Honoured by both the main agent and subagents.

• Added --trust-directory CLI flag to bypass the first-run directory trust prompt for automation. Yolo mode now also skips file path validators in line with its "auto-accept everything" semantics.

• Added JSON tool fallback mode for non-tool-calling open-weights models (Qwen, Kimi, GLM). The tune menu now cycles through Native ON / OFF (XML) / OFF (JSON), with formatToolsForJSONPrompt() embedding literal JSON Schema and a JSON branch in the tool-call parser. Native path also gains JSON/XML hallucination recovery: parseToolCalls() is run against text content when the SDK reports no tool_calls, and stripEmbeddedToolCallText() removes echoed tool-call text so Ghost Echo no longer leaks into the UI or history. Reference #500.

• Added <function=...> format to the tool-call parser for models that emit OpenAI-style function tags.

• Added Display Settings panel under /settings ("Tool Results and Thinking") with two new toggles: Show Thinking by default (Ctrl+R) and Expand Tool Results by default (Ctrl+O), persisted to nanocoder-preferences.json. Thanks to @cleyesode. Closes #499.

• Added 12+ new themes to the bundled theme set.

• Removed the in-repo release content generator workflow. Release content is now generated from another repo via ContentForest.

• Bumped CI and devcontainer toolchain to Node.js 22 + pnpm 11 across pr-checks.yml, release.yml, update-badges.yml, and .devcontainer/Dockerfile. engines.node raised to >=22, with a packageManager field (pnpm@11.x.x) added to package.json so Corepack pins the pnpm version automatically for both contributors and CI — no more drift, no per-workflow version: lines. CONTRIBUTING.md / docs/getting-started/installation.md / .devcontainer/README.md updated to match. Fixes the node:sqlite ERR_UNKNOWN_BUILTIN_MODULE crash hit by pnpm 11 on Node 20 runners.

• Migrated pnpm config from package.json to pnpm-workspace.yaml for pnpm 11 compatibility: overrides, patchedDependencies, and the new allowBuilds block now live in the workspace file. While migrating, audited and removed all 16 existing version overrides — every one was redundant under current dependency resolution (each transitive resolved to a version already exceeding the override's floor), and removing them left pnpm audit output unchanged.

• Major spring-clean refactor across the codebase. Extracted shared oauth-login command from the duplicated codex-login and copilot-login flows; introduced shared item-selector component used by model-selector and provider-selector; centralised tool-needs-approval logic; moved AI SDK error-handling specs into a dedicated subdirectory; tightened logging method factory; and trimmed redundant code paths in conversation-loop, subagent-executor, and the plain shell.

• Refactored App.tsx and added missing test coverage for the app container and chat input components.

• Refactored settings theme selector UX. Replaced the scrollable SelectInput with arrow-key navigation, real-time theme preview, and a "Theme Name [n/N]" position indicator. Preferences are only persisted on Enter.

• Updated the system prompt to encourage subagent use more proactively for complex multi-step tasks.

• Strip leading and trailing whitespace from assistant messages so blank lines and stray newlines from the model no longer push content around in the UI.

• Fix: Empty model responses now trigger a capped auto-continue instead of crashing or burning tokens forever. Empty-response retry notices are coalesced into a single live counter so the chat history stays readable.

• Fix: Surface context-size failures explicitly instead of silently retrying empty responses. Thanks to @zerone0x. Closes #501.

…

What's Changed

• Fixed Nix package: copy themes.json and prompt section files into the Nix store so nix run no longer crashes at startup
• Fixed Nix package: corrected wrapper script heredoc indentation that broke the shebang line

If there are any problems, feedback or thoughts please drop an issue or message us through Discord! Thank you for using Nanocoder.

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.25.1...v1.25.2

What's Changed

• Removed rogue document from docs/

If there are any problems, feedback or thoughts please drop an issue or message us through Discord! Thank you for using Nanocoder.

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.25.0...v1.25.1

What's Changed

• Added yolo mode — a new development mode that auto-accepts every tool without exception, including bash commands and destructive git operations (hard reset, force delete, stash drop/clear). Cycles between normal → auto-accept → yolo → plan via Shift+Tab. The status bar turns red when yolo mode is active.

• Added subagents — isolated child conversations that the LLM can delegate work to. Ships with two built-in agents: Explore (read-only codebase investigation) and Reviewer (code review with actionable feedback). Subagents are defined as markdown files with YAML frontmatter specifying name, description, model, and allowed tools. User-defined subagents can be placed in .nanocoder/agents/. Managed via the /agents command (show, create). Thanks to @brijeshkr for the initial subagent implementation. Closes #414.

• Added concurrent subagent execution. The LLM can launch multiple subagents in parallel, each with independent tool sets and live in-place progress rendering via the AgentProgress component.

• Added subagent tool approval matching main agent behaviour. Subagent write tools prompt for approval and bash always prompts unless in alwaysAllow. The agent tool itself no longer requires approval since internal tools have their own gates.

• Redesigned the system prompt into a modular, composable architecture. The monolithic main-prompt.md has been replaced with individual section files under source/app/prompts/sections/ (identity, core principles, coding practices, file editing, tool rules, diagnostics, task management, etc.). The new prompt-builder assembles the prompt dynamically based on the current mode — normal, auto-accept, plan, and scheduler each get a tailored prompt with only the sections and tools relevant to that mode. Includes a generate-system-prompts script for offline token counting and prompt inspection.

• Made plan mode useful. Plan mode now enforces read-only tools at the policy level — all mutation tools (write, bash, git commit/push, task management) are blocked, leaving only exploration tools (read, search, find, list, git log/diff/status). The dedicated plan mode system prompt instructs the LLM to investigate thoroughly and produce a structured plan with summary, files to modify, step-by-step approach, dependencies/risks, and open questions — instead of trying to execute changes.

• Added /tune command for per-session prompt and tool customization. Includes a tune selector UI (Ctrl+T) with tool profiles (full, minimal), a disableNativeTools toggle for forcing XML fallback, and aggressive compact mode. Tune state persists for the session and is reflected in the mode indicator.

• Centralized tool policy into ToolManager so prompt-time tool filtering and runtime approval use the same source of truth. Extracted tool-registry.ts for cleaner separation of tool definitions from policy logic.

• Added ChatGPT Codex as a provider with OAuth device flow authentication (/codex-login), streaming response support via a dedicated StreamingMessage component, and Codex-specific credential management. Includes provider template and setup wizard integration.

• Migrated web_search tool from Brave Search scraping to the official Brave Search API. Now requires a webSearch.apiKey in agents.config.json under nanocoderTools. Removes the cheerio scraping dependency.

• Added /setup-config command that lists all config files (project and global agents.config.json, .mcp.json, nanocoder-preferences.json) with their paths and opens the selected one in your editor.

• Added configurable paste threshold for single-line paste handling, with tests for the configurable placeholder threshold. The threshold is a user preference in nanocoder-preferences.json. Changed the default config file for paste settings from agents.config.json to nanocoder-preferences.json. Thanks to @grenkoca.

• Added live in-place task list display. Task progress now updates in place instead of appending repeated static lists to the conversation.

• Improved tool output truncation across all tools. Every tool formatter now respects terminal width for cleaner output, including execute_bash, file ops, git tools, search_file_contents, and web_search.

• Redesigned the provider setup wizard with a unified model fetcher that auto-detects API compatibility (OpenAI-compatible, Ollama, Anthropic, Google) and fetches available models from the provider's endpoint. Simplified the provider step UI and added MiniMax and Kimi provider templates.

• Fix: alwaysAllow config not being respected for execute_bash. Three interconnected bugs prevented it from working: top-level alwaysAllow was never loaded from agents.config.json, isNanocoderToolAlwaysAllowed only checked nanocoderTools.alwaysAllow not the top-level list, and nonInteractiveAlwaysAllow set needsApproval on AI SDK tools but the conversation loop evaluated it from the original registry entries. Closes #431.

• Fix: dimColor making text inaccessible to reading on some screens. Closes #440.

• Fix: Tasks now clear when running /clear command.

• Fix: Prevent edit flow from resolving MiniMax/Kimi to Anthropic template.

• Fix: Set correct default model for MiniMax provider.

• Fix: /usage and context percentage showing stale system prompt length. Added setLastBuiltPrompt and fixed useContextPercentage overwriting cache.

• Added debug logging to 15 silent catch blocks in git utilities that were swallowing errors invisibly. Operational catches now log at debug level for easier diagnosis while boolean probes (e.g. isGitAvailable, branchExists) remain intentionally silent. Thanks to @ragini-pandey. Closes #452.

• Security: Address semgrep security finding in console.error. Thanks to @brijeshkr.

• Security: Fixed vulnerable packages. Thanks to @brijeshkr.

• Security: Replaced exec() with execFile() in VS Code extension installer to prevent command injection. Removes shell interpretation from CLI discovery and extension status checks. Thanks to @ragini-pandey.

• Added /credits command showing project contributors (auto-generated from git history via pnpm run build:credits) and dependency versions.

• Added desktop notifications for tool confirmations, question prompts, and generation completions. Supports macOS (terminal-notifier with osascript fallback), Linux (notify-send), and Windows (PowerShell). Configurable per-event in nanocoder-preferences.json and in /settings with custom messages and optional sound. Includes a "Notifications" settings menu for preference management.

• Added CLI quality metrics framework (benchmarks/measure.ts, benchmarks/report.ts) tracking correctness, performance (module count, boot time, bundle size), stability (tool/command counts, help text hash), and health (test counts, vulnerabilities).

• Reduced startup time by parallelizing and deferring non-critical initialization. LLM client and subagent init run in parallel on the critical path; update checks, MCP servers, and LSP servers now initialize in the background without blocking chat. Replaced the full Status box with a lightweight one-line BootSummary component.

• Fix: Scheduler mode memory leak — chat messages and components now clear before each scheduled job execution, preventing memory accumulation across repeated runs.

• Fix: Updated agent documentation (AGENTS.md, CLAUDE.md) with current project structure (766 files across 97 directories), added missing directory mappings, removed deprecated references, and documented the lazy-loading command system.

• Fix: Improved Ollama timeout handling for slow local models. Timeout errors are now detected case-insensitively, and IPv6 loopback addresses are correctly resolved. Thanks to @ragini-pandey.

…

What's Changed

• Added --context-max CLI flag for setting the context limit from the command line, complementing the existing /context-max command and NANOCODER_CONTEXT_LIMIT env variable.

• Removed time from the system prompt to keep the KV cache more stable across requests. Thanks to @initialxy. Closes #415.

• Task tool results are no longer displayed as compacted results during ensuring task progress remains visible in the conversation.

• User input now uses the same text wrapping as assistant messages for a more consistent chat appearance.

• Improved search_file_contents tool robustness.

If there are any problems, feedback or thoughts please drop an issue or message us through Discord! Thank you for using Nanocoder.

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.24.0...v1.24.1

What's Changed

• BREAKING: Removed legacy ~/.agents.config.json config file support. Nanocoder no longer checks the home directory for a dot-prefixed config file. If you are still using this path, move your config to the platform-specific directory: ~/Library/Preferences/nanocoder/agents.config.json (macOS), ~/.config/nanocoder/agents.config.json (Linux), or %APPDATA%\nanocoder\agents.config.json (Windows).

• BREAKING: Removed legacy ~/.nanocoder-preferences.json preferences file support. Preferences are now only loaded from the platform-specific directory (e.g. ~/Library/Preferences/nanocoder/nanocoder-preferences.json on macOS) or a project-level nanocoder-preferences.json in your working directory. To migrate, move your existing file: mv ~/.nanocoder-preferences.json ~/Library/Preferences/nanocoder/nanocoder-preferences.json

• BREAKING: Removed deprecated array format for MCP server configuration. Only the object format is now supported: { "mcpServers": { "serverName": { ... } } }. If you are using the array format in .mcp.json, convert each array entry to an object key using the server name.

• BREAKING: Removed agents.config.json fallback for MCP server loading. Global MCP servers must now be configured in ~/.config/nanocoder/.mcp.json (Linux), ~/Library/Preferences/nanocoder/.mcp.json (macOS), or %APPDATA%\nanocoder\.mcp.json (Windows). Provider configuration still uses agents.config.json.

• BREAKING: Removed auth and reconnect fields from MCP server configuration. The auth field was never functional (both HTTP and WebSocket transports logged warnings that it was unsupported). The reconnect field was never implemented. Use headers for HTTP authentication instead (e.g. "headers": { "Authorization": "Bearer $TOKEN" }).

• Added /resume command for restoring previous chat sessions. Sessions are automatically saved and can be resumed from an interactive selector. Sessions are filtered by the current project directory by default, with an --all flag to show all sessions. Thanks to @yashksaini-coder.

• Added --provider and --model CLI flags for non-interactive provider and model specification, allowing CI/CD scripts and automation to skip the setup wizard. Closes #394. Thanks to @james2doyle.

• Added NANOCODER_PROVIDERS environment variable support for configuring providers without config files, useful for Docker containers and CI environments. Closes #307. Thanks to @kaustubha07.

• Added GitHub Copilot as a provider template with OAuth device flow authentication and /copilot-login command. Thanks to @yashksaini-coder.

• Added MLX Server provider template for local Apple Silicon inference. Closes #318.

• Added parallel tool execution allowing the model to run multiple independent tool calls concurrently for faster task completion.

• Added compact mode toggle via Ctrl+L in chat input to collapse the conversation view.

• Added VS Code fork support for IDE integration (Cursor, Windsurf, VSCodium, etc.). Thanks to @kapsner.

• Added Aurora Borealis theme.

• Added notice when the model falls back to XML tool calls, informing users they can switch to a model with native tool calling support.

• Adopted AI SDK human-in-the-loop pattern for tool approval. Tool confirmation now uses the SDK's built-in tool-approval-request/tool-approval-response flow instead of manual tool-call splitting, improving reliability and reducing code complexity.

• Simplified tool processing by removing double XML parsing and the JSON tool call parser. Tool call parsing now happens in a single place and only on the XML fallback path for non-tool-calling models.

• Restructured documentation into a Nextra-compatible docs/ folder structure with nested sections for getting-started, configuration, and features. The README is now a concise landing page linking to the full docs.

• Refactored app-utils into focused handler files, extracted shared utilities, unified mode state, and stubbed commands for cleaner architecture.

• Fix: alwaysAllow field in MCP server configuration was silently dropped during config loading due to a missing field mapping. MCP tools configured with alwaysAllow now correctly skip confirmation prompts as documented.

• Fix: Provider timeouts are now respected in non-interactive mode. Thanks to @kaustubha07. Closes #402.

• Fix: Non-interactive mode no longer exits prematurely when the prompt or response contains the word "error".

• Fix: Invalid CLI arguments no longer trigger the setup wizard. Thanks to @james2doyle.

• Fix: Installation detector no longer falsely reports Homebrew on macOS when HOMEBREW_PREFIX is set but Nanocoder was installed via npm. Closes #392.

• Fix: Preserve draft message when navigating through history with arrow keys.

• Fix: fetch_url display now truncates to fit terminal width.

• Fix: Validation failures no longer incorrectly prompt for tool confirmation.

• Fix: Various error message and execute_bash formatter improvements.

• Fix: Safe process metrics refactored into shared module to prevent duplicate declarations. Thanks to @cleyesode.

• Security: Package audit failures resolved.

• Dependency updates: ai 6.0.116, @ai-sdk/anthropic 3.0.58, @ai-sdk/google 3.0.33, @ai-sdk/openai-compatible 2.0.30, @modelcontextprotocol/sdk 1.27.1, undici 7.24.0, cheerio 1.2.0, dotenv 17.3.1, wrap-ansi 10.0.0.

If there are any problems, feedback or thoughts please drop an issue or message us through Discord! Thank you for using Nanocoder.

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.23.0...v1.24.0

What's Changed

• Added ask_user tool for interactive question prompts. The LLM can now present the user with a question and selectable options during a conversation, returning their answer to guide the next step. Uses a global question-queue to bridge the tool's suspended Promise with the Ink UI component.

• Added per-project cron scheduler for running AI tasks on a schedule. Schedule files live in .nanocoder/schedules/ as markdown prompts with YAML frontmatter, managed via the /schedule command (create, add, remove, list, logs, start). Includes cron expression parsing, sequential job queue with deduplication, dedicated scheduler mode with auto-accept, and run history logging.

• Added centralized graceful shutdown system. A ShutdownManager now coordinates cleanup of all services (VS Code server, MCP client, LSP manager, health monitor, logger) on exit, preventing orphaned child processes and dangling connections. Configurable via NANOCODER_DEFAULT_SHUTDOWN_TIMEOUT env variable. Closes #239.

• Added file operation tools: delete_file, move_file, create_directory, and copy_file. Reorganized existing file tools into a file-ops/ directory group.

• Added readline keybind support to text input. Replaces ink-text-input with a custom TextInput component supporting Ctrl+W (delete word), Ctrl+U (kill to start), Ctrl+K (kill to end), Ctrl+A/E (jump to start/end), and Ctrl+B/F (move char). Closes #354.

• Added /context-max command and NANOCODER_CONTEXT_LIMIT env variable for manual context length override on models not listed on models.dev. Resolution order: session override > env variable > models.dev > null. Closes #379.

• Added /ide command matching the --vscode flag for toggling VS Code integration from within a session.

• Added persistent context percentage display in the mode indicator, replacing the previous context checker component.

• Added include and path parameters to search_file_contents tool for scoping searches to specific file patterns and directories.

• Added Kanagawa theme.

• Refactored the skills system into custom commands, eliminating redundant parsers, loaders, and test suites. Commands gain optional skill-like fields (tags, triggers, estimated-tokens, resources) for auto-injection and relevance scoring. The /skills command is removed and its functionality absorbed into /commands with new subcommands (show, refresh). Thanks to @yashksaini-coder for the initial skills implementation in PR #370.

• V2 type-safe tool system overhaul with defensive parsing. Implements a three-tiered defense system for handling chaotic LLM outputs, preventing crashes from non-string responses and enabling robust self-correction. Includes universal type safety with ensureString(), response normalization, confidence system inversion, ghost echo deduplication, and AI SDK contract fixes. Local LLM experience is now significantly more stable. Thanks to @cleyesode. Closes #362.

• Fix: XML parser now uses optimistic matching for consistency with the JSON parser. Thanks to @cleyesode.

• Fix: Bash tool now emits progress immediately on stdout/stderr data instead of waiting for the 500ms timer, so fast-completing commands show streaming output.

• Fix: Recognize 127.0.0.1 as a local server URL and tighten error classification. Ollama users configuring 127.0.0.1 instead of localhost no longer experience misleading connection errors. Replaced broad connect substring match with specific error codes to prevent misclassifying "disconnect"/"reconnect". Closes #366.

• Fix: Skip loading git tools when not inside a git repository.

• Fix: Strip ANSI escape codes before running regex matching in tool formatters.

• Fix: Gap in layout during auto-compact.

• Fix: Hardened write_file validation and MCP client type safety.

• Fix: Use local TextInput component instead of the missing ink-text-input package.

• Fix(mcp): Use Python-based mcp-server-fetch instead of non-existent npm package.

• Security: Semgrep and audit fixes.

• Dependency updates: ai 6.0.95, @ai-sdk/anthropic 3.0.46, @ai-sdk/google 3.0.30, undici 7.22.0, sonic-boom 4.2.1.

If there are any problems, feedback or thoughts please drop an issue or message us through Discord! Thank you for using Nanocoder. 🙌

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.22.5...v1.23.0

What's Changed

• Added MiniMax Coding Plan and GLM-5 to provider templates in the configuration wizard.

• Fix: Model context limit lookups now use models.dev as the primary source instead of the hardcoded fallback table. This prevents stale hardcoded values from overriding accurate upstream data. The hardcoded table remains as an offline-only fallback. Also fixes greedy key matching where shorter keys like mixtral would match before mixtral:8x22b, and replaces first-match name lookups with scored matching for more accurate results.

• Fix: Binary and excessively large files tagged with @ no longer pollute the LLM context window with unreadable content.

• Fix: Diff preview panel no longer steals terminal focus from the active input.

• Fix: Reduced verbosity of the string_replace error formatter output.

• Fix: Reject null and non-object arguments in JSON tool calls, preventing formatter crashes from malformed tool call arguments. Thanks to @cleyesode.

• Fix: Restored formatError usage for validation and execution errors.

• Dependency updates: ink-gradient 4.0.0, react 19.2.4, @nanocollective/get-md 1.1.1, @ai-sdk/anthropic 3.0.43, pino 10.3.1, @types/react 19.2.14.

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.22.4...v1.22.5

What's Changed

• Security: Tool validators now run inside the AI SDK's auto-execution loop. Previously, tools with needsApproval: false (like read_file) were auto-executed by the AI SDK's generateText without any path validation, allowing the model to read or write files outside the project directory using absolute or ~ paths. Validators are now wrapped into each tool's execute function at registration time, ensuring validation runs in all code paths.

• Security: Reject home directory shorthand (~) in file path validation. Paths starting with ~ are not expanded by Node.js and could bypass project boundary checks.

• Fix: Tab characters in code blocks within assistant messages now render at 2-space width instead of the terminal default of 8 spaces. This prevents long lines from wrapping prematurely and eliminates the blocky visual effect on messages containing indented code.

• Fix: normalizeIndentation no longer short-circuits when the minimum indent is 0. Previously, if any line in the context window had zero indentation, raw tab characters passed through to the terminal unchanged, rendering at 8-space width in string_replace diff previews.

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.22.3...v1.22.4

What's Changed

• Fix: Removed tool call deduplication from JSON parser that silently dropped duplicate tool calls, breaking the 1:1 pairing between tool calls and results expected by AI SDK. This caused "Tool result is missing for tool call" errors that would end the agent's turn prematurely. Consolidated three overlapping regex patterns into a single comprehensive pattern to prevent duplicate matches. Thanks to @cleyesode.

• Fix: Added missing capture group for arguments in the consolidated JSON tool call regex pattern, which caused inline tool calls to have empty arguments instead of actual parsed values.

• Fix: When the model batched read-only and write tools in a single response (e.g. read_file + string_replace), the auto-executed read tools would recurse into the next conversation turn, abandoning the confirmation-needed write tools. This left orphaned tool_use blocks without matching tool_result entries, triggering intermittent "Tool result is missing for tool call" errors with the Anthropic provider.

• Dependency updates: @ai-sdk/openai-compatible 2.0.27, undici 7.21.0, @biomejs/biome 2.3.14, @types/vscode 1.109.0, @types/node 25.2.1.

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.22.2...v1.22.3

What's Changed

• Fix: Markdown tables in assistant messages were rendered at full terminal width instead of accounting for the message box border and padding, causing broken box-drawing characters when lines wrapped.

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.22.1...v1.22.2

What's Changed

• Added native Anthropic SDK support via @ai-sdk/anthropic package. The Anthropic Claude provider template now uses sdkProvider: 'anthropic' for direct API integration instead of the OpenAI-compatible wrapper.

• Fixed Kimi Code provider template to use the native @ai-sdk/anthropic SDK with correct base URL and configuration passthrough.

• Fix: User message token count now reflects the full assembled content including pasted content and tagged file contents, instead of only counting the placeholder text.

• Fix: Removed aggressive tool call deduplication that silently dropped duplicate tool call IDs and identical function signatures. This could cause "Tool result is missing for tool call" errors with providers like Anthropic that strictly validate tool call/result pairing.

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.22.0...v1.22.1

What's Changed

• Added /explorer command for interactive file browsing with tree view navigation, file preview with syntax highlighting, multi-file selection, search mode, and VS Code integration. Closes #298.

• Added task management tools (create_task, list_tasks, update_task, delete_task) with /tasks slash command for models to track and manage progress on complex work. Tasks persist in .nanocoder/tasks.json and are automatically cleared on CLI boot and /clear command.

• Added /settings command for interactive command menu to configure UI theme and shapes without editing config files directly.

• Added sdkProvider configuration option for native Google Gemini support. This fixes the "missing thought_signature" error with Gemini 3 models by using the @ai-sdk/google package. Closes #302.

• Added custom headers support in provider configuration. This enables authentication through tunnels like Cloudflare. Thanks to @nicolalamacchia.

• Added Kimi Code provider template in configuration wizard.

• Added new themes with updated user input and user message styling for better visual clarity and consistency.

• Added token count display after messages and completion message to provide visibility into context usage throughout conversations.

• Refactored git tools for better consistency, improved error handling, standardized parameter handling across all git operations, and enhanced user feedback messages.

• Added line truncation in write_file and string_replace formatters to prevent excessive output from files with very long lines and neaten user experience on narrow terminals.

• Fix: /usage command crash when context data is unavailable.

• Fix: String replace error handling for edge cases.

• Fix: Multiple security audit issues resolved.

• Fix: Various styling improvements across components.

• Fix: Dependency lockfile issues resolved.

If there are any problems, feedback or thoughts please drop an issue or message us through Discord! Thank you for using Nanocoder. 🙌

Installation

npm install -g @nanocollective/nanocoder

Usage

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.21.0...v1.22.0