@praxisui/ai 9.0.0-beta.9 → 9.0.0-beta.90

package/README.md

@@ -34,7 +34,7 @@ Peer dependencies:
 - `@angular/forms` `^21.0.0`
 - `@angular/material` `^21.0.0`
 - `@google/generative-ai` `^0.24.1`
-- `@praxisui/core` `^9.0.0-beta.4`
+- `@praxisui/core` `^9.0.0-beta.12`
 - `rxjs` `~7.8.0`
 
 ## When to use
@@ -138,11 +138,13 @@ When a component exposes factual grounding for consultative answers, include a `
 
 Use `createComponentAuthoringContext(...)` from `@praxisui/ai` when returning the adapter context. The helper normalizes the contract into a JSON-safe object, drops `undefined` fields and rejects non-JSON values before they leak into `contextHints`.
 
+Specialized component-authoring flows should also apply `withAuthoringScopePolicy(...)` or `withAuthoringScopePolicyContextHints(...)` before calling the backend turn resolver. These helpers do not classify prompts locally. They add a shared semantic policy that tells the backend/LLM to return `info` with no patch for loose instructions, greetings, meta-prompts or other turns outside the active component authoring context, while still allowing consultative answers and governed component edits when the semantic intent fits the declared contracts.
+
 The shell ships with centralized PT-BR default labels and accepts the `labels` input for a flow-specific override. The override is partial: omitted labels continue to come from the shared defaults.
 
 By default, the prompt composer submits with `Enter` and keeps `Shift+Enter` for multiline prompts. Hosts with custom composer behavior can set `submitOnEnter` to `false`.
 
-The prompt composer can expose browser-native speech recognition as an opt-in input method with `voiceInputMode="browser-speech"`. Hosts can also set the application-wide default through `PRAXIS_ASSISTANT_VOICE_INPUT_MODE`; direct shell input still wins for specialized flows that need a stricter policy. This mode uses the browser `SpeechRecognition`/`webkitSpeechRecognition` surface when available, appends the recognized text to the prompt and never auto-submits the assistant turn. It is intended as an initial low-latency UX path; governed provider-backed transcription should remain a backend-owned Praxis Config capability when promoted to enterprise/default usage. Corporate hosts should keep this mode disabled unless their privacy policy allows browser/vendor speech recognition for the current tenant and environment.
+The prompt composer supports governed provider-backed transcription with `voiceInputMode="governed-transcription"`. It captures a short audio blob with `MediaRecorder`, sends it to `POST /api/praxis/config/ai/transcriptions` using the normal tenant/user/environment scope, appends the returned text to the prompt and never auto-submits the assistant turn. Provider selection, credentials, limits and audit policy remain backend-owned by Praxis Config. The older `browser-speech` mode remains an explicit compatibility option for approved low-risk environments, but it is not the enterprise/default path because `SpeechRecognition` availability varies by browser.
 
 When a user pastes an image into the prompt composer, the shell emits `attachmentsPasted` with `PraxisAssistantShellAttachment` items containing the original `File`, image metadata, `source: 'paste'` and a local preview URL.
 
@@ -283,7 +285,7 @@ Notes:
 
 `AiBackendApiService.startAgenticAuthoringTurnStream`, `connectAgenticAuthoringTurnStream` and `cancelAgenticAuthoringTurnStream` use the same SSE envelope contract as patch streaming. Browser `EventSource` cannot send custom headers, so signed stream tokens returned by the backend should be passed to `connectAgenticAuthoringTurnStream` and `cancelAgenticAuthoringTurnStream` when the backend uses signed-url stream auth.
 
-`AgenticAuthoringTurnClientService` is the shared client for assistant turn flows that consume this canonical stream. It starts the turn, connects SSE and exposes two levels: `streamEvents()` for component flows that already own rich preview/apply semantics, and `streamTurn()` for flows that can consume normalized `PraxisAssistantTurnResult` values directly. The client can emit shared lifecycle status for silent streams, enforce a terminal-result timeout and surface transport lifecycle events such as probe readiness, transport opening and first-event receipt. `AiBackendApiService.connectAgenticAuthoringTurnStream` also falls back to `fetch` SSE parsing when `EventSource` is unavailable. Per-call `baseUrl` and header overrides allow component services with existing endpoint options to migrate without losing host configuration. Component-specific flows should use this shared client when migrating away from `/patch`, then add only component-owned context assembly and apply semantics locally.
+`AgenticAuthoringTurnClientService` is the shared client for assistant turn flows that consume this canonical stream. It starts the turn, connects SSE and exposes two levels: `streamEvents()` for component flows that already own rich preview/apply semantics, and `streamTurn()` for flows that can consume normalized `PraxisAssistantTurnResult` values directly. The client can emit shared lifecycle status for silent streams, enforce terminal-result and whole-turn timeouts, and surface transport lifecycle events such as probe readiness, transport opening and first-event receipt. Governed lifecycle telemetry records start and terminal outcomes (`result`, `error`, `cancelled`, `timeout`, and `transport-error`) with bounded provider/model dimensions, correlation identifiers, and duration, but never prompt text, API keys, headers, or raw payloads. `ObservabilityMetricsSnapshot.agenticTurns` materializes these events as success and timeout rates, average/P50/P95 latency, and provider/model breakdowns for the active dashboard window. When either timeout expires after the stream has started, the client also sends a bounded best-effort cancellation to the canonical backend using the same signed token, `baseUrl`, and headers, while preserving the original timeout as the user-facing failure. The cancellation outcome is emitted through the governed Praxis logger as a redacted structured diagnostic (`cancel-confirmed`, `cancel-timeout`, or `cancel-failed`) correlated by turn and stream identifiers. `AiBackendApiService.connectAgenticAuthoringTurnStream` also falls back to `fetch` SSE parsing when `EventSource` is unavailable. Per-call `baseUrl` and header overrides allow component services with existing endpoint options to migrate without losing host configuration. Component-specific flows should use this shared client when migrating away from `/patch`, then add only component-owned context assembly and apply semantics locally.
 
 ## Assistant local history (UI)
 

package/ai/component-registry.json

@@ -0,0 +1,11 @@
+{
+  "schemaVersion": "1.0.0",
+  "generatedAt": "2026-07-24T12:32:39.440Z",
+  "packageName": "@praxisui/ai",
+  "packageVersion": "9.0.0-beta.90",
+  "sourceRegistry": "praxis-component-registry-ingestion",
+  "sourceRegistryVersion": "1.0.0",
+  "componentCount": 0,
+  "components": {},
+  "note": "Package-scoped Praxis component registry for source-free agent discovery. Use the canonical ingestion registry for cross-package aggregate analysis."
+}