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.
The root barrel is now core-only and side-effect free: types,
createModels/createProvider, auth substrate, lazyStream/lazyApi, faux,
utils. Generated catalogs, api-registry, env-api-keys, images, global
stream functions, and per-API lazy wrappers leave the root.
New @earendil-works/pi-ai/compat preserves the old surface verbatim as
a strict superset of the root: api-dispatch stream/complete with env
key injection, the builtin registration side effect (skip-if-present so
it cannot clobber earlier overrides), deprecated getModel/getModels/
getProviders aliases of the new getBuiltin* reads in providers/all,
lazy api wrappers + setBedrockProviderModule, and image generation.
Compat dies with the coding-agent ModelManager migration.
Packaging: exports map gains ./compat, ./providers/*, ./api/*;
sideEffects array lists only the effectful modules.
Old-global imports across agent/coding-agent/examples and pi-ai tests
switch to /compat (path-only; compat is a superset). The coding-agent
extension loader resolves the pi-ai ROOT specifier to compat, so
existing user extensions using the old global API keep working at
runtime until compat is removed. vitest configs alias /compat to src;
browser smoke imports old globals from /compat.
* fix(typebox): migrate to v1 with extension compat
Replace AJV-based validation with TypeBox-native validation, keep legacy extension imports working (including @sinclair/typebox/compiler), and restore coercion for serialized/plain JSON schemas.
This change closes#3112.
* fix(typebox): use canonical imports and harden coercion
Switch first-party code to canonical typebox imports while retaining legacy extension aliases in the loader.
Remove obsolete runtime codegen guards, expand serialized JSON-schema coercion coverage, and update related tests and fixtures.
Fixes#3112.
---------
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
When auto-retry fires after a retryable error (e.g. overloaded_error) and the
retry response includes tool_use, session.prompt() returned prematurely because
_resolveRetry() was called on the first successful message_end — while the
agent loop was still executing tools via the fire-and-forget agent.continue().
This caused callers to observe isStreaming=true after prompt() returned, and
follow-up session.prompt() calls threw 'Agent is already processing'. The
tool execution results were silently lost.
Fix: move _resolveRetry() from the message_end handler to the agent_end
handler. The _retryAttempt counter reset stays on message_end (preventing
accumulation across LLM calls within a turn), but the promise that unblocks
waitForRetry() now only resolves when the full agent loop completes.
Mario Zechner