* feat(ai): route xAI models through Responses and default to Grok 4.6
Send built-in xAI catalog models through the Responses API with
store: false and include reasoning.encrypted_content so encrypted
reasoning is requested and replayed, including future models.dev
additions. Thinking levels come from models.dev reasoning_options
(grok-4.6 exposes xhigh); models without verified options
(grok-build-0.1) keep reasoning always on and never send unsupported
"none"/"minimal" efforts. Narrow the xAI provider to the Responses API,
send pi's runtime User-Agent on xAI requests for provider-side
attribution, and make Grok 4.6 the default xAI model.
* fix(ai): drop duplicate xAI encrypted-reasoning tests
Azure already covers the shared replay path; keep the xAI-specific include-without-effort case next to the existing request tests.
---------
Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com>
Move provider auth and OAuth flows onto pi-ai Models, compose models.json and extension overlays through ModelRuntime, and retain ModelRegistry as an extension compatibility facade.
Update the coding-agent default model picks for ZAI, Cerebras,
and MiniMax so new sessions prefer the current model lineup.
Add the missing MiniMax-M2.1-highspeed direct provider entries
and normalize MiniMax Anthropic-compatible context limits so the
catalog matches the provider's supported model set.
When resolving --model zai/glm-5, the resolver now correctly interprets
'zai' as the provider and 'glm-5' as the model id, rather than matching
a vercel-ai-gateway model whose id is literally 'zai/glm-5'.
If the provider/model split fails to find a match, falls back to raw id
matching to still support OpenRouter-style ids like 'openai/gpt-4o:extended'.
- Fix ai/CHANGELOG.md: add PR link and author attribution
- Add coding-agent/CHANGELOG.md entry for vercel-ai-gateway provider
- Fix model-resolver.test.ts: use anthropic-messages API type to match generated models
- Add vercel-ai-gateway to test suites: tokens, abort, empty, context-overflow, unicode-surrogate, tool-call-without-result, image-tool-result, total-tokens, image-limits
When enabledModels is configured without thinking level suffixes (e.g.,
'claude-opus-4-5' instead of 'claude-opus-4-5:high'), the scoped model's
default 'off' thinking level was overriding defaultThinkingLevel from
settings.
Now thinkingLevel in ScopedModel is optional (undefined means 'not
explicitly specified'). When passing to SDK, undefined values are filled
with defaultThinkingLevel from settings.
Major changes:
- Replace monolithic SessionEvent with reason discriminator with individual
event types: session_start, session_before_switch, session_switch,
session_before_new, session_new, session_before_branch, session_branch,
session_before_compact, session_compact, session_shutdown
- Each event has dedicated result type (SessionBeforeSwitchResult, etc.)
- HookHandler type now allows bare return statements (void in return type)
- HookAPI.on() has proper overloads for each event with correct typing
Additional fixes:
- AgentSession now always subscribes to agent in constructor (was only
subscribing when external subscribe() called, breaking internal handlers)
- Standardize on undefined over null throughout codebase
- HookUIContext methods return undefined instead of null
- SessionManager methods return undefined instead of null
- Simplify hook exports to 'export type * from types.js'
- Add detailed JSDoc for skipConversationRestore vs cancel
- Fix createBranchedSession to rebuild index in persist mode
- newSession() now returns the session file path
Updated all example hooks, tests, and emission sites to use new event types.
