* fix(tui): blockquote multiline rendering and wrapping
Fix two bugs in blockquote rendering:
1. ANSI codes split incorrectly on newlines - when text tokens contain
newlines, applyDefaultStyle() wrapped the entire string including the
newline in ANSI codes. Any caller splitting by \n would break the codes.
Fixed by splitting text by newlines before styling in renderInlineTokens().
2. Wrapped blockquote lines lost the │ border - long blockquote lines
that wrapped to multiple lines only had the border on the first line.
Fixed by wrapping within the blockquote case and adding border to each line.
* test(tui): add test for inline formatting inside blockquotes
When cursor is on the first visual line and up is pressed, jump to
start of line instead of doing nothing. When cursor is on the last
visual line and down is pressed, jump to end of line instead of doing
nothing. This matches standard behavior in most native text inputs.
- Add isImageLine() to terminal-image.ts with single startsWith check based on detected terminal protocol
- Replace dual includes() checks in tui.ts with imported isImageLine()
- Add image line handling to markdown.ts to skip wrapping and margins for image escapes
- Consolidate Box cache into RenderCache type with childLines/width/bgSample/lines fields
- Use in-place mutation in applyLineResets() to avoid array allocation
* 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.
* fix(tui): keep file suggestions open when typing in Tab-triggered mode
Previously, pressing Tab on an empty prompt or after a space would show
file suggestions, but typing a letter would dismiss them because the
text didn't look like a path pattern. Now the editor tracks whether
autocomplete was triggered via Tab (force mode) or naturally (regular
mode), and uses the appropriate suggestion method when updating.
* fix(tui): hide autocomplete when backspacing slash command to empty
Previously, typing / showed slash command suggestions, but pressing
Backspace to delete it showed file suggestions instead of hiding all
suggestions.
Instead of buffering `\` and waiting for the next key, let it be
inserted immediately. On Enter, check if preceded by `\` and treat as
newline.
Removed backslash handling from the Input component entirely.
- 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
