Extracted HTTP proxy setup to shared module and imported it from both
stream.ts and oauth/index.ts. This ensures fetch() calls during OAuth
flows (token exchange, refresh, project discovery) go through the proxy.
fixes#1132
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
- Add minimal example showing only required fields for local models
- Rename 'Basic Example' to 'Full Example' showing all fields
- Add 'Default' column to model configuration table
- Clarify that apiKey is required but ignored by Ollama
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
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
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
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
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.
Fixes#916
Adds an autocompleteMaxVisible setting (range 3-20, default 5) to control how many items are visible in the editor's autocomplete dropdown.
Co-authored-by: Colin Mason <masonc789@gmail.com>
- 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
Adds support for extended cache retention via PI_CACHE_RETENTION=long:
- Anthropic: 5m -> 1h TTL
- OpenAI: in-memory -> 24h retention
Only applies to direct API calls (api.anthropic.com, api.openai.com).
Proxies and other providers are unaffected.
fixes#967
- Handle pipe-separated IDs from OpenAI Responses API in openai-completions provider
- Strip trailing underscores after truncation in openai-responses-shared (OpenAI Codex rejects them)
- Add regression tests for tool call ID normalization
fixes#1022
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
429 (Too Many Requests) was incorrectly classified as context overflow,
triggering compaction instead of retry with backoff. The original logic
assumed token-based rate limiting correlates with context overflow, but
these are different concepts:
- Rate limiting (429): requests/tokens per time period (throughput)
- Context overflow: single request exceeds context window (size)
Now 429 errors are handled by the existing retry logic with exponential
backoff, while 400/413 remain as potential context overflow indicators.
fixes#1038
- 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>
Proxies like Portkey omit input_tokens in message_delta events (it's nullable
per the SDK). The previous code unconditionally overwrote usage fields, causing
input token counts to reset to 0.
Now only updates usage fields when they are present (not null), preserving
the correct input_tokens value captured from message_start.
Fixes#1045
Move setup callback handling from interactive/rpc modes into AgentSession.newSession().
After setup() runs, sync agent state via replaceMessages() so the LLM has context
and the UI renders the messages properly.
fixes#968
Appended lines were not committed to terminal scrollback because the
renderer used cursor movement (CSI B) and carriage return without
linefeed. This caused earlier content to be overwritten when the
viewport filled up.
Changes:
- For appended lines, emit \r\n to create real scrollback lines
- When target row is below viewport, scroll with \r\n before positioning
- Add PI_TUI_WRITE_LOG env var for debugging raw ANSI output
- Add fullRedraws readonly property to TUI class
- Add viewport-overwrite-repro.ts test script
fixes#954
Mario Zechner