@pouchy_ai/companion-sdk 0.15.0 → 0.18.0

package/CHANGELOG.md

@@ -12,7 +12,64 @@ a protocol bump is always called out explicitly here.
 
 ## [Unreleased]
 
-## [0.15.0] - 2026-07-08
+## [0.18.0] - 2026-07-08
+
+### Added
+
+- **`close()`** — one-call teardown for a non-voice (text) session: stops the
+  event stream and calls `endSession()` once (idempotent). The text-path mirror
+  of what a `connectCall()` handle's `close()` already does for voice.
+- **`EndSessionResult`** type — exported. `endSession()` now RETURNS the server's
+  consolidation diagnostic `{ ok, facts?, skipped? }` (or `null`) instead of
+  discarding it, so an integrator whose memory write silently does nothing (wrong
+  id → `skipped: 'no_session'`, empty transcript → `'no_content'`) gets the
+  signal the server already provides. Backwards-compatible: callers ignoring the
+  return value are unaffected (`connectCall`'s internal `void endSession()` too).
+- **`CompanionError.code`** — an optional stable, machine-readable tag on the
+  thrown error. Local precondition mistakes now throw a `CompanionError`
+  (`status: 0`) instead of a bare `Error`, with codes `not_connected` (a method
+  called before `connect()`), `missing_option` (no `baseUrl`/`token`), and
+  `not_representative` (`pairVisitor` off a non-representative session); HTTP
+  failures carry the server's error `code` when present. `catch (e) { if (e
+  instanceof CompanionError) … }` — the natural one-error-type pattern — now
+  catches the common first-run mistakes too.
+
+### Changed
+
+- `endSession(opts?)` return type: `Promise<void>` → `Promise<EndSessionResult | null>`.
+
+## [0.17.0] - 2026-07-08
+
+### Added
+
+Surface completion — the last three wire types that lacked a typed
+client accessor now have one. All additive; wire protocol unchanged
+(`PROTOCOL_VERSION 1`).
+
+- **`onVoiceInject(fn)`** + `VoiceInjectPayload { text, speak }` — a typed
+  subscription for `companion.voice_inject` (a `voiceRelevant` world-state
+  line the companion should say aloud during a live call). The event was
+  already emitted; this is the public handler + payload type for it.
+- **`client.setModalities(modalities)`** — change a live session's I/O
+  modalities mid-session (e.g. toggle `voice`). Intersected with the
+  token's granted modalities server-side; returns the effective set.
+  Backed by `POST /api/companion/session/{id}/modalities`.
+- **`client.ping()`** — keepalive that bumps the session's last-seen time
+  so a long-idle embed stays "live" within the TTL (cross-app A2A friend
+  messages keep reaching it). Backed by
+  `POST /api/companion/session/{id}/ping`.
+
+### Added
+
+- **Conversation history** — `client.history({ limit })` fetches this session's
+  recent turns (`{ user, assistant, ts }`, oldest→newest) so a reconnecting
+  embed can restore its transcript. Distinct from `recall` (durable memory /
+  facts): this is the raw exchange log. Reads the token's OWN session only
+  (tenant-safe by construction — the turn log is keyed by the token's uid);
+  internal per-turn trace (`meta`) is stripped server-side. `limit` defaults to
+  20, capped at 50. New type `CompanionTurn`. Backed by
+  `GET /api/companion/session/{sessionId}/history`. Wire protocol unchanged
+  (`PROTOCOL_VERSION 1`) — this is a REST method, not a stream event.
 
 ### Added
 

package/README.md

@@ -18,6 +18,10 @@ No bundler? Pull it from a CDN via an import map instead — see
 [`docs/companion-integration-faq.md`](../../docs/companion-integration-faq.md).
 Changes per release are tracked in [`CHANGELOG.md`](./CHANGELOG.md).
 
+**React?** [`@pouchy_ai/react`](../react-sdk/README.md) wraps this SDK in a
+`<CompanionProvider>` + `useCompanion` / `useMessages` / `useTyping` / `useCall`
+hooks so you don't wire the handshake, stream, or teardown yourself.
+
 ## Quickstart
 
 Two steps. **1)** Your backend exchanges the project **Secret Key** (create one
@@ -70,6 +74,7 @@ Subscribe with `on(type, fn)` (or `'*'`), or these typed convenience helpers:
 | `onConfirmRequest(fn)` | `companion.confirm_request` | a sensitive-op approval request. **Platform session tokens** (your end users): show your own confirm card and resolve it with `confirmAction` — this is how confirm-gated custom skills (POST / credentialed) run. First-party user tokens: observe-only — approval stays first-party (where the `stepUp:true` biometric gate lives) |
 | `onAudio(fn)` | `companion.audio` | TTS clip (non-call modality) |
 | `onExpression(fn)` | `companion.expression` | avatar viseme / expression / gesture |
+| `onVoiceInject(fn)` | `companion.voice_inject` | `fn({text, speak})` — a `voiceRelevant` world-state line to say aloud during a live call; route `text` to your voice session when `speak` |
 | `onTyping(fn)` | `companion.typing` | activity indicator — `fn({active})` fires `true` when a turn starts working and `false` when it finishes / pauses, spanning the tool-loop / thinking phase before the first text delta. Drive a "typing…" state |
 | `onUsage(fn)` | `control.usage` | per-token metering echo |
 | `onError(fn)` | `control.error` | agent / stream errors |

package/dist/client.d.ts

@@ -1,4 +1,4 @@
-import type { AudioClipPayload, CompanionEnvelope, ConfirmRequestPayload, ExpressionPayload, InterfaceUpdatePayload, OutboundType, PendingConfirm, RenderInterfacePayload, SocialMessagePayload, TypingPayload, UsagePayload, WorldStateEvent } from './protocol.js';
+import type { AudioClipPayload, CompanionEnvelope, ConfirmRequestPayload, ExpressionPayload, InterfaceUpdatePayload, OutboundType, PendingConfirm, RenderInterfacePayload, SocialMessagePayload, TypingPayload, UsagePayload, VoiceInjectPayload, WorldStateEvent } from './protocol.js';
 /** Ergonomic world-state input: a WorldStateEvent with the CloudEvents plumbing
  *  (specversion / id / source) optional — sendWorldState fills them. */
 export type WorldStateInput<D = unknown> = Omit<WorldStateEvent<D>, 'specversion' | 'id' | 'source'> & Partial<Pick<WorldStateEvent<D>, 'specversion' | 'id' | 'source'>>;
@@ -100,6 +100,14 @@ export interface RecalledMemory {
     namespace: string;
     createdAt?: string;
 }
+/** One exchange from a session's conversation log (see `history`). `user` is the
+ *  end-user's message, `assistant` the companion's reply; either may be `''` for
+ *  a paused / assistant-only row. `ts` is epoch ms. */
+export interface CompanionTurn {
+    user: string;
+    assistant: string;
+    ts: number;
+}
 /** The user's current companion avatar (see getAvatar). */
 export interface CompanionAvatar {
     /** Companion display name (the user's chosen name), or null. */
@@ -121,9 +129,25 @@ export type BrandIconSize = 256 | 512 | 1024;
  *  deployment origin. Standalone (no client/token needed) so a surface can show
  *  the Pouchy mark before/without connecting. */
 export declare function pouchyBrandIconUrl(baseUrl: string, size?: BrandIconSize): string;
+/** The single error type the SDK throws — for HTTP failures (`status` is the
+ *  response code) AND for local precondition mistakes (`status: 0`, e.g. calling
+ *  a method before `connect()`). `code` is a stable machine-readable tag you can
+ *  switch on, shared with the `control.error` stream event vocabulary:
+ *  `'not_connected'`, `'missing_option'`, `'not_representative'`, or the server's
+ *  own error code for an HTTP failure (when it sends one). */
 export declare class CompanionError extends Error {
     status: number;
-    constructor(message: string, status: number);
+    code?: string;
+    constructor(message: string, status: number, code?: string);
+}
+/** The server's memory-consolidation diagnostic from `endSession()` / `close()`.
+ *  `ok` is whether consolidation ran; `facts` is how many memories it wrote;
+ *  `skipped` (when present) says why nothing was written
+ *  (`'no_session'` | `'no_content'` | `'throttled'`). */
+export interface EndSessionResult {
+    ok: boolean;
+    facts?: number;
+    skipped?: string;
 }
 type Handler = (envelope: CompanionEnvelope) => void;
 /** Token-streaming subscriber (P1-2). `chunk` is a raw text delta of the reply
@@ -234,13 +258,27 @@ export declare class CompanionClient {
      *  Called automatically when a connectCall() handle is closed; call it directly
      *  when a non-voice session ends. Best-effort + idempotent (safe to call twice;
      *  uses keepalive so it survives a page unload). Pass the voice transcript when
-     *  you have it (connectCall does this for you). */
+     *  you have it (connectCall does this for you).
+     *
+     *  Returns the server's consolidation diagnostic — `{ ok, facts?, skipped? }`
+     *  — or `null` if there was no session or the (swallowed) keepalive request
+     *  failed. `skipped` tells you WHY nothing was written: `'no_session'` (you
+     *  passed the instance id, not the session id), `'no_content'` (empty turn log
+     *  / a voice transcript that never arrived), `'throttled'` (a duplicate end
+     *  beacon — harmless). `facts` is how many memories were consolidated. */
     endSession(opts?: {
         transcript?: {
             role: string;
             text: string;
         }[];
-    }): Promise<void>;
+    }): Promise<EndSessionResult | null>;
+    /** Tear the session down in one call: stop the event stream and consolidate
+     *  memory (endSession) exactly once. The single teardown entry point for a
+     *  NON-voice (text) session — mirror of what a connectCall() handle's close()
+     *  does for voice. Idempotent. Returns endSession's diagnostic (or null).
+     *  NOTE: if you drive `ping()` on your own timer for a background tab, clear
+     *  that timer yourself — the client doesn't own it. */
+    close(): Promise<EndSessionResult | null>;
     /** Report the result of a companion.tool_call this surface performed. When all
      *  of the turn's calls are reported, the companion resumes and the continuation
      *  (a companion.message or more tool calls) arrives on the event stream. */
@@ -273,6 +311,25 @@ export declare class CompanionClient {
     recall(opts?: {
         limit?: number;
     }): Promise<RecalledMemory[]>;
+    /** Fetch this session's recent conversation turns (oldest→newest) so a
+     *  reconnecting embed can restore its transcript. Distinct from `recall`
+     *  (durable memory / facts) — this is the raw exchange log. Returns the
+     *  token's OWN session turns only; requires a live session (call `connect`
+     *  first). `limit` defaults to 20, capped at 50. */
+    history(opts?: {
+        limit?: number;
+    }): Promise<CompanionTurn[]>;
+    /** Change this session's I/O modalities mid-session (e.g. enable/disable
+     *  `voice`). The request is intersected with the token's granted modalities
+     *  server-side — a session can't widen past its key — and the EFFECTIVE set is
+     *  returned. Requires a live session. */
+    setModalities(modalities: string[]): Promise<{
+        modalities: string[];
+    }>;
+    /** Keepalive: bump this session's last-seen time so a long-idle embed stays
+     *  "live" within the session TTL (cross-app A2A friend messages keep reaching
+     *  it). Cheap; call it on a timer for a background tab. Requires a live session. */
+    ping(): Promise<void>;
     /** Remember a fact (into this app's namespace unless `namespace` is given and
      *  the token has the core scope). Intimate-tier writes are rejected server-side. */
     remember(fact: {
@@ -407,6 +464,11 @@ export declare class CompanionClient {
      *  tool-loop / thinking phase before the first text delta. Drive a "typing…"
      *  affordance from it: `client.onTyping(({ active }) => setTyping(active))`. */
     onTyping(handler: (payload: TypingPayload, envelope: CompanionEnvelope) => void): () => void;
+    /** Convenience: subscribe to voice-inject cues (companion.voice_inject) — a
+     *  `voiceRelevant` world-state line the companion should say aloud during a
+     *  live call. Route `payload.text` to your active voice session when
+     *  `payload.speak`. A text-only host can ignore it. */
+    onVoiceInject(handler: (payload: VoiceInjectPayload, envelope: CompanionEnvelope) => void): () => void;
     /** Open the event stream (auto-reconnecting with the resume cursor). Uses the
      *  WebSocket plane when opted in + available, else SSE. */
     start(): void;

package/dist/client.js

@@ -19,12 +19,21 @@ import { openCompanionCall, HOST_CONTROL_TOOLS, HOST_CONTROL_TOOL_NAMES, AVATAR_
 export function pouchyBrandIconUrl(baseUrl, size = 512) {
     return baseUrl.replace(/\/+$/, '') + `/brand-assets/icon/pouchy-icon-${size}.png`;
 }
+/** The single error type the SDK throws — for HTTP failures (`status` is the
+ *  response code) AND for local precondition mistakes (`status: 0`, e.g. calling
+ *  a method before `connect()`). `code` is a stable machine-readable tag you can
+ *  switch on, shared with the `control.error` stream event vocabulary:
+ *  `'not_connected'`, `'missing_option'`, `'not_representative'`, or the server's
+ *  own error code for an HTTP failure (when it sends one). */
 export class CompanionError extends Error {
     status;
-    constructor(message, status) {
+    code;
+    constructor(message, status, code) {
         super(message);
         this.name = 'CompanionError';
         this.status = status;
+        if (code)
+            this.code = code;
     }
 }
 const SEEN_CAP = 512;
@@ -44,9 +53,9 @@ export class CompanionClient {
     pendingVoiceTools = new Map();
     constructor(opts) {
         if (!opts.baseUrl)
-            throw new Error('CompanionClient: baseUrl is required');
+            throw new CompanionError('CompanionClient: baseUrl is required', 0, 'missing_option');
         if (!opts.token)
-            throw new Error('CompanionClient: token is required');
+            throw new CompanionError('CompanionClient: token is required', 0, 'missing_option');
         this.opts = opts;
         this.doFetch = opts.fetch ?? globalThis.fetch.bind(globalThis);
     }
@@ -62,7 +71,7 @@ export class CompanionClient {
     }
     requireSession() {
         if (!this._session)
-            throw new Error('CompanionClient: call connect() first');
+            throw new CompanionError('CompanionClient: call connect() first', 0, 'not_connected');
         return this._session;
     }
     async postJson(path, body) {
@@ -73,7 +82,7 @@ export class CompanionClient {
         });
         const json = (await res.json().catch(() => null));
         if (!res.ok || !json || json.ok === false) {
-            throw new CompanionError(json?.error || `request failed (${res.status})`, res.status);
+            throw new CompanionError(json?.error || `request failed (${res.status})`, res.status, json?.code);
         }
         return json;
     }
@@ -106,10 +115,10 @@ export class CompanionClient {
      *  — as proof + consent. The visitor must therefore also be a Pouchy user. */
     async pairVisitor(visitorToken) {
         if (!this.opts.visitor) {
-            throw new Error('pairVisitor() requires a representative session (createCompanion({ visitor }))');
+            throw new CompanionError('pairVisitor() requires a representative session (createCompanion({ visitor }))', 0, 'not_representative');
         }
         if (!visitorToken)
-            throw new Error('pairVisitor: visitorToken is required');
+            throw new CompanionError('pairVisitor: visitorToken is required', 0, 'missing_option');
         const json = await this.postJson('/api/companion/pair', {
             visitorToken,
             visitorId: this.opts.visitor.id
@@ -320,28 +329,47 @@ export class CompanionClient {
      *  Called automatically when a connectCall() handle is closed; call it directly
      *  when a non-voice session ends. Best-effort + idempotent (safe to call twice;
      *  uses keepalive so it survives a page unload). Pass the voice transcript when
-     *  you have it (connectCall does this for you). */
+     *  you have it (connectCall does this for you).
+     *
+     *  Returns the server's consolidation diagnostic — `{ ok, facts?, skipped? }`
+     *  — or `null` if there was no session or the (swallowed) keepalive request
+     *  failed. `skipped` tells you WHY nothing was written: `'no_session'` (you
+     *  passed the instance id, not the session id), `'no_content'` (empty turn log
+     *  / a voice transcript that never arrived), `'throttled'` (a duplicate end
+     *  beacon — harmless). `facts` is how many memories were consolidated. */
     async endSession(opts) {
         const id = this._session;
         if (!id)
-            return;
+            return null;
         // Cap the payload (fetch keepalive bodies are size-limited): last 60 lines.
         const transcript = (opts?.transcript ?? [])
             .filter((t) => t && typeof t.text === 'string' && t.text.trim())
             .slice(-60)
             .map((t) => ({ role: t.role, text: t.text.slice(0, 500) }));
         try {
-            await this.doFetch(this.url(`/api/companion/session/${id}/end`), {
+            const res = await this.doFetch(this.url(`/api/companion/session/${id}/end`), {
                 method: 'POST',
                 headers: this.jsonHeaders(),
                 body: JSON.stringify({ transcript }),
                 keepalive: true
             });
+            return (await res.json().catch(() => null));
         }
         catch {
             /* best-effort — memory consolidation is not on the user's critical path */
+            return null;
         }
     }
+    /** Tear the session down in one call: stop the event stream and consolidate
+     *  memory (endSession) exactly once. The single teardown entry point for a
+     *  NON-voice (text) session — mirror of what a connectCall() handle's close()
+     *  does for voice. Idempotent. Returns endSession's diagnostic (or null).
+     *  NOTE: if you drive `ping()` on your own timer for a background tab, clear
+     *  that timer yourself — the client doesn't own it. */
+    async close() {
+        this.stop();
+        return this.endSession();
+    }
     /** Report the result of a companion.tool_call this surface performed. When all
      *  of the turn's calls are reported, the companion resumes and the continuation
      *  (a companion.message or more tool calls) arrives on the event stream. */
@@ -465,6 +493,52 @@ export class CompanionClient {
         }
         return json.memories ?? [];
     }
+    /** Fetch this session's recent conversation turns (oldest→newest) so a
+     *  reconnecting embed can restore its transcript. Distinct from `recall`
+     *  (durable memory / facts) — this is the raw exchange log. Returns the
+     *  token's OWN session turns only; requires a live session (call `connect`
+     *  first). `limit` defaults to 20, capped at 50. */
+    async history(opts) {
+        const id = this.requireSession();
+        const qs = opts?.limit ? `?limit=${encodeURIComponent(opts.limit)}` : '';
+        const res = await this.doFetch(this.url(`/api/companion/session/${encodeURIComponent(id)}/history${qs}`), { headers: { Authorization: `Bearer ${this.opts.token}` } });
+        const json = (await res.json().catch(() => null));
+        if (!res.ok || !json || json.ok === false) {
+            throw new CompanionError(json?.error || `history failed (${res.status})`, res.status);
+        }
+        return json.history ?? [];
+    }
+    /** Change this session's I/O modalities mid-session (e.g. enable/disable
+     *  `voice`). The request is intersected with the token's granted modalities
+     *  server-side — a session can't widen past its key — and the EFFECTIVE set is
+     *  returned. Requires a live session. */
+    async setModalities(modalities) {
+        const id = this.requireSession();
+        const res = await this.doFetch(this.url(`/api/companion/session/${encodeURIComponent(id)}/modalities`), {
+            method: 'POST',
+            headers: {
+                Authorization: `Bearer ${this.opts.token}`,
+                'Content-Type': 'application/json'
+            },
+            body: JSON.stringify({ modalities })
+        });
+        const json = (await res.json().catch(() => null));
+        if (!res.ok || !json || json.ok === false) {
+            throw new CompanionError(json?.error || `setModalities failed (${res.status})`, res.status);
+        }
+        return { modalities: json.modalities ?? modalities };
+    }
+    /** Keepalive: bump this session's last-seen time so a long-idle embed stays
+     *  "live" within the session TTL (cross-app A2A friend messages keep reaching
+     *  it). Cheap; call it on a timer for a background tab. Requires a live session. */
+    async ping() {
+        const id = this.requireSession();
+        const res = await this.doFetch(this.url(`/api/companion/session/${encodeURIComponent(id)}/ping`), { method: 'POST', headers: { Authorization: `Bearer ${this.opts.token}` } });
+        if (!res.ok) {
+            const json = (await res.json().catch(() => null));
+            throw new CompanionError(json?.error || `ping failed (${res.status})`, res.status);
+        }
+    }
     /** Remember a fact (into this app's namespace unless `namespace` is given and
      *  the token has the core scope). Intimate-tier writes are rejected server-side. */
     async remember(fact) {
@@ -655,6 +729,17 @@ export class CompanionClient {
                 handler(p, env);
         });
     }
+    /** Convenience: subscribe to voice-inject cues (companion.voice_inject) — a
+     *  `voiceRelevant` world-state line the companion should say aloud during a
+     *  live call. Route `payload.text` to your active voice session when
+     *  `payload.speak`. A text-only host can ignore it. */
+    onVoiceInject(handler) {
+        return this.on('companion.voice_inject', (env) => {
+            const p = env.payload;
+            if (p && typeof p === 'object' && typeof p.text === 'string')
+                handler(p, env);
+        });
+    }
     /** Open the event stream (auto-reconnecting with the resume cursor). Uses the
      *  WebSocket plane when opted in + available, else SSE. */
     start() {

package/dist/index.d.ts

@@ -1,8 +1,8 @@
 import { CompanionClient, type CompanionClientOptions } from './client.js';
 export { CompanionClient, CompanionError, pouchyBrandIconUrl } from './client.js';
-export type { CompanionClientOptions, HelloAck, RecalledMemory, CallCredentials, CompanionToolDecl, WorldStateInput, CompanionAvatar, BrandIconSize } from './client.js';
+export type { CompanionClientOptions, HelloAck, RecalledMemory, CompanionTurn, CallCredentials, CompanionToolDecl, WorldStateInput, CompanionAvatar, BrandIconSize, EndSessionResult } from './client.js';
 export { openCompanionCall, HOST_CONTROL_TOOLS, HOST_CONTROL_TOOL_NAMES, AVATAR_VISUAL_TOOLS, AVATAR_VISUAL_TOOL_NAMES } from './call.js';
 export type { CompanionCall, CompanionCallOptions, VoiceToolBridge } from './call.js';
-export type { CompanionEnvelope, OutboundType, InboundType, WorldStateEvent, RenderInterfacePayload, InterfaceUpdatePayload, SocialMessagePayload, ConfirmRequestPayload, PendingConfirm, AudioClipPayload, ExpressionPayload, TypingPayload, UsagePayload } from './protocol.js';
+export type { CompanionEnvelope, OutboundType, InboundType, WorldStateEvent, RenderInterfacePayload, InterfaceUpdatePayload, SocialMessagePayload, ConfirmRequestPayload, PendingConfirm, AudioClipPayload, ExpressionPayload, TypingPayload, VoiceInjectPayload, UsagePayload } from './protocol.js';
 /** Create a companion client. */
 export declare function createCompanion(opts: CompanionClientOptions): CompanionClient;

package/dist/protocol.d.ts

@@ -120,6 +120,15 @@ export interface SocialMessagePayload {
     /** ISO timestamp of delivery. */
     createdAt: string;
 }
+/** Payload of a `companion.voice_inject` event — a `voiceRelevant` world-state
+ *  line the companion should say aloud DURING a live call (the app pushed the
+ *  moment via `sendWorldState`; the server decided it's worth voicing). `speak`
+ *  is the host's cue to route `text` to the active voice session. A text-only
+ *  host can ignore it — the moment still shaped the next turn's context. */
+export interface VoiceInjectPayload {
+    text: string;
+    speak: boolean;
+}
 /** Payload of a `companion.typing` event — an activity indicator bracketing the
  *  model work of a turn: `active:true` when the companion starts working,
  *  `active:false` when it emits its reply or pauses for an app tool result. It

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pouchy_ai/companion-sdk",
-  "version": "0.15.0",
+  "version": "0.18.0",
   "description": "Embed the Pouchy companion — chat, voice, tools, memory, live world-state, instant UI, and agent-to-agent messaging — in any app, game, or site.",
   "type": "module",
   "license": "SEE LICENSE IN LICENSE",