- Make @mariozechner/clipboard an optional dependency
- Lazy-load clipboard module with graceful fallback
- Add Termux clipboard support via termux-clipboard-set
- Skip image clipboard on Termux (not supported)
fixes#1164
update(source) unconditionally called updateSourceForScope for both
user and project scopes, creating a local install even when the source
was only registered globally. Unify into a single code path that
iterates settings per scope, filtering by identity when a source is
provided.
Matches ToolResultEvent pattern with typed inputs via discriminated union.
- Export *ToolInput types from tool schemas
- Add *ToolCallEvent interfaces for each built-in tool
- Add isToolCallEventType() guard with overloads for built-ins
Direct narrowing (event.toolName === "bash") doesn't work due to
CustomToolCallEvent.toolName: string overlapping with literals.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds Ctrl+N toggle to filter sessions by named-only vs all in the /resume picker.
- Add NameFilter type and filtering logic to session-selector-search.ts
- Add toggleSessionNamedFilter app keybinding (default: ctrl+n)
- Show Name: All/Named state in header
- Empty state mentions toggle keybinding as escape hatch
- Export hasSessionName() to avoid duplication
Co-authored-by: warren <warren.winter@gmail.com>
Models were resolving relative paths in skill files from cwd instead of
the skill directory. Added explicit instruction that relative paths are
resolved from the skill directory (parent of the location path).
Fixes#1136
Model definitions now only require 'id'. All other fields have sensible
defaults for local models (Ollama, LM Studio, etc.):
- name: defaults to id
- reasoning: defaults to false
- input: defaults to ["text"]
- cost: defaults to {input: 0, output: 0, cacheRead: 0, cacheWrite: 0}
- contextWindow: defaults to 128000
- maxTokens: defaults to 16384
Existing configs that specify all fields continue to work unchanged.
Fixes#1146
* fix(coding-agent): tree selector focuses nearest visible ancestor
When the selected entry is not visible (filtered out by mode change or a
metadata entry like model_change), walk up the parent chain to find the
nearest visible ancestor instead of jumping to the last item.
Fixes selection behavior for:
- Initial selection when currentLeafId is a metadata entry
- Filter switching, e.g. Ctrl+U for user-only mode
* fix(coding-agent): tree selector preserves selection through empty filters
When switching to a filter with no results, e.g. labeled-only with no
labels and back, the cursor would reset to the first message instead of
the original selection.
Track lastSelectedId as a class member and only update it when
filteredNodes is non-empty, preserving the selection across empty filter
results.
* test(coding-agent): add tree selector filter and selection tests
- Test metadata entry handling (model_change, thinking_level_change)
- Test filter switching with parent traversal (default ↔ user-only)
- Test empty filter preservation (labeled-only with no labels)
Allows users to override the Antigravity User-Agent version when Google
updates their version requirements, avoiding the need to wait for a
package release.
Fixes#1129
Adds 'Threaded' as a new sort mode (now default) that displays sessions
in a tree structure based on parent-child relationships. Compact one-line
format with message count and age right-aligned for clean title alignment.
Closes#1108
Adds 'Threaded' as a new sort mode (now default) that displays sessions
in a tree structure based on parent-child relationships. Compact one-line
format with message count and age right-aligned for clean title alignment.
Closes#1108
When a provider (e.g., Google Gemini CLI) requests a retry delay longer
than maxDelayMs (default: 60s), the request fails immediately with an
informative error instead of waiting silently for hours.
The error is then handled by agent-level auto-retry, which shows the
delay to the user and allows aborting with Escape.
- Add maxRetryDelayMs to StreamOptions (packages/ai)
- Add maxRetryDelayMs to AgentOptions (packages/agent)
- Add retry.maxDelayMs to settings (packages/coding-agent)
- Update _isRetryableError to match 'retry delay' errors
fixes#1123
- Add --error-on-warnings to biome check in root and web-ui package.json
- Convert string concatenation to template literals in daxnuts.ts
- Convert string concatenation to template literals in test file
Fixes#1103
switchSession() was appending spurious thinking_level_change entries
to session log on resume because setThinkingLevel() unconditionally
persisted. Now only persists if the level actually changes.
fixes#1118
- One line per session instead of multi-line (message + metadata + blank)
- Age shown in compact format (now, 5m, 2h, 3d, 2w, 1mo, 1y)
- Message count on the left side
- Current session highlighted in accent color
- Selected row has background highlight
- Increased maxVisible from 5 to 10 sessions
WSL2/WSLg often provides clipboard images as image/bmp only.
Previously this resulted in invalid PNG files being written.
Now readClipboardImage() converts unsupported formats to PNG
via Photon before returning.
Closes#1109
Based on #1112 by @lightningRalf
Adds 'Threaded' as a new sort mode (now default) that displays sessions
in a tree structure based on parent-child relationships. The tree is
sorted by root session's modified date. Other sort modes (Recent, Fuzzy)
continue to show flat lists.
Sort mode cycles: Threaded -> Recent -> Fuzzy -> Threaded
Package resolution now uses the same discovery logic as local extensions:
only index.ts (or manifest-declared entries) are loaded from subdirectories,
not helper modules.
fixes#1102
Adds a method to access the effective system prompt (after any per-turn
extension modifications) from the extension context.
Implementation:
- Add systemPrompt getter to AgentSession reading from agent.state.systemPrompt
- Wire getSystemPrompt through ExtensionContextActions to ExtensionRunner
- Add getSystemPrompt to interactive-mode's shortcut context
- Update docs with ctx.getSystemPrompt() section
- Add system-prompt-header.ts example
- Add example to docs reference table
Closes#1098
* feat(ai): add Vercel AI Gateway routing support
Add vercelGatewayRouting to OpenAICompletionsCompat, parallel to
openRouterRouting. When a model targets ai-gateway.vercel.sh and has
vercelGatewayRouting configured, the openai-completions provider passes
providerOptions.gateway with only/order in the request body.
Changes:
- types.ts: VercelGatewayRouting interface + field on OpenAICompletionsCompat
- openai-completions.ts: buildParams passes providerOptions.gateway,
detectCompat/getCompat include the new field
- model-registry.ts: VercelGatewayRoutingSchema for models.json validation
- test: updated Required<OpenAICompletionsCompat> in test fixture
* docs(coding-agent): add vercelGatewayRouting to custom models documentation
Add Bash/Readline-style character search:
- Ctrl+] enters forward jump mode, awaits next character, jumps to it
- Ctrl+Alt+] does the same but searches backward
- Multi-line search
- Case-sensitive matching
- Pressing the hotkey again cancels; control chars cancel and fall
through
- Add set_session_name command with empty name validation
- Expose sessionName in get_state response
- Add setSessionName() to AgentSession and RpcClient
- Document in docs/rpc.md
Fixes#1078
- Add tryNFDVariant() to normalize paths to NFD form
- Add tryCurlyQuoteVariant() to convert straight quotes to curly quotes
- Try combined NFD + curly quote variant for French macOS screenshots
- Add comprehensive tests for path-utils
- Add kimi-coding provider using Anthropic Messages API
- API endpoint: https://api.kimi.com/coding/v1
- Environment variable: KIMI_API_KEY
- Models: kimi-k2-thinking (text), k2p5 (text + image)
- Add context overflow detection pattern for Kimi errors
- Add tests for all standard test suites
Swapped order of initExtensions() and renderInitialMessages() in init()
so loaded resources (Context, Skills, Prompts, Extensions) appear at the
top of the chat instead of at the bottom when resuming a session.
- Add huggingface to KnownProvider type
- Add HF_TOKEN env var mapping
- Process huggingface models from models.dev (14 models)
- Use openai-completions API with compat settings
- Add tests for all provider test suites
- Update documentation
fixes#994
Previously, within a single tool-use turn, rate limit retries would
accumulate across separate LLM calls. For example, if each of 3 tool
calls hit a 429 and retried once, the counter would show '3/3' and fail
even though each individual retry succeeded.
Now the counter resets immediately when a successful (non-error)
assistant message arrives, so each LLM call gets a fresh set of retries.
Fixes#1019
- Add alt+b/alt+f as alternative bindings for cursorWordLeft/cursorWordRight
- Add ctrl+d as alternative binding for deleteCharForward
- Fix ctrl+d in custom editor to perform delete when text is present
(previously it was always consumed, even with non-empty input)
Closes#1043
Co-authored-by: Jason Ish <ish@unx.ca>
* Add get_commands RPC for headless clients
Headless clients like Emacs can now query which commands are available.
Previously they could only discover file-based prompt templates by
scanning the filesystem; extension commands and skills were invisible.
The response includes each command's name, description, and source
(extension, template, or skill). Commands appear in the same order
as the TUI's autocomplete: extension commands first, then templates,
then skills.
Built-in TUI commands (/settings, /fork, etc.) are excluded since
they require the interactive UI. Commands like /compact have dedicated
RPC equivalents instead.
* Add location and path to get_commands response
Clients can show where commands come from (user/project/path) and
display file paths in tooltips. The data is already available on
templates and skills - just exposing it.
