@adia-ai/a2ui-compose 0.2.5 → 0.3.1

package/CHANGELOG.md

@@ -12,6 +12,63 @@ generator graph.
 
 _No pending changes._
 
+## [0.3.1] - 2026-05-06
+
+**9-package lockstep patch cut.** All 9 published `@adia-ai/*` packages bump 0.3.0 → 0.3.1 per [`docs/specs/package-architecture.md` § 15](../../../docs/specs/package-architecture.md#15-versioning-policy). Internal `@adia-ai/*` dep ranges remain at `^0.3.0` (covers `0.3.1` under semver — patch-cut asymmetry).
+
+This package itself ships **no source changes** in v0.3.1. The cut bumps version only — substantive content lives in [`@adia-ai/web-components`](https://github.com/adiahealth/gen-ui-kit/releases/tag/web-components-v0.3.1) (folder-per-trait restructure; barrel API unchanged).
+
+### Changed
+
+- `version`: `0.3.0` → `0.3.1`.
+- Internal `@adia-ai/*` dep ranges: unchanged at `^0.3.0` (covers `0.3.1` under semver — patch-cut asymmetry).
+
+## [0.3.0] - 2026-05-05
+
+**9-package lockstep cut + LLM subpath dropped.** All 9 published `@adia-ai/*` packages bump 0.2.5 → 0.3.0 per [`docs/specs/package-architecture.md` § 15](../../../docs/specs/package-architecture.md#15-versioning-policy). Internal `@adia-ai/*` dep ranges bump `^0.2.0` → `^0.3.0`.
+
+This is a **minor cut on top of v0.2.5 with one BREAKING change**: the `./llm` subpath export is removed. The LLM adapters that previously shipped under `@adia-ai/a2ui-compose/llm` now ship as their own package, `@adia-ai/llm` (9th lockstep member, first publish in this cut).
+
+### Removed
+
+- **`./llm` subpath export.** The package no longer re-exports the LLM
+  adapters or bridge. Migrate to `@adia-ai/llm`:
+
+  ```diff
+  - import { streamChat } from '@adia-ai/a2ui-compose/llm/adapters/index.js';
+  + import { streamChat } from '@adia-ai/llm';
+
+  - import { createAdapter } from '@adia-ai/a2ui-compose/llm/llm-bridge.js';
+  + import { createAdapter } from '@adia-ai/llm/bridge';
+  ```
+
+  See `@adia-ai/llm@0.3.0` CHANGELOG for the full migration narrative.
+
+### Changed
+
+- `dependencies["@adia-ai/llm"]`: NEW, `^0.3.0`. The compose engines'
+  internal LLM use now resolves through the new package.
+- `dependencies["@adia-ai/a2ui-utils"]` removed (renamed to `a2ui-runtime`); replaced by `dependencies["@adia-ai/a2ui-runtime"]: ^0.3.0`.
+- All other internal `@adia-ai/*` dep ranges: `^0.2.0` → `^0.3.0`.
+- `version`: `0.2.5` → `0.3.0`.
+- Source paths internal to compose that referenced `./llm/` updated to
+  `../../../llm/` (e.g. `core/generator.js` imports `StubLLMAdapter`
+  from the new package location).
+- `transpiler/transpiler-maps.js`: `@adia-ai/a2ui-utils` import → `@adia-ai/a2ui-runtime` (matches the package rename — see runtime's CHANGELOG).
+
+### Migration
+
+```diff
+{
+  "dependencies": {
+    "@adia-ai/a2ui-compose": "^0.3.0",
++   "@adia-ai/llm": "^0.3.0"
+  }
+}
+```
+
+Plus rewrite imports as shown above. The change is mechanical.
+
 ## [0.2.5] - 2026-05-04
 
 **8-package lockstep cut.** All 8 published `@adia-ai/*` packages bump 0.2.4 → 0.2.5 per [`docs/specs/package-architecture.md` § 15](../../../docs/specs/package-architecture.md#15-versioning-policy). Internal `@adia-ai/*` dep ranges remain at `^0.2.0` (covers 0.2.5 under semver — patch-cut asymmetry).

package/README.md

@@ -8,7 +8,7 @@ ready for a renderer.
 
 > This package is pipeline runtime only. UI components live in
 > [`@adia-ai/web-components`](../../web-components); the A2UI runtime (renderer,
-> registry, streams, wiring) in [`@adia-ai/a2ui-utils`](../utils);
+> registry, streams, wiring) in [`@adia-ai/a2ui-runtime`](../runtime);
 > the pattern corpus in [`@adia-ai/a2ui-corpus`](../corpus);
 > the MCP server in [`@adia-ai/a2ui-mcp`](../mcp).
 >
@@ -140,7 +140,7 @@ output, not a safety net.
 Multi-provider adapter with a common interface:
 
 ```javascript
-import { getAdapter } from '@adia-ai/a2ui-compose/llm';
+import { getAdapter } from '@adia-ai/llm';
 
 const adapter = getAdapter('anthropic');     // or 'openai', 'gemini'
 const stream = await adapter.streamChat({ model, messages, tools });

package/core/generator.js

@@ -19,8 +19,8 @@ import { decomposeIntent, composeSubtasks } from '../../retrieval/intent/decompo
 import { getWiringCatalog } from '../../retrieval/wiring-catalog.js';
 import { getComponentData } from '../../retrieval/pattern-library.js';
 
-import { StubLLMAdapter } from '../llm/llm-stub.js';
-import { createAdapter } from '../llm/llm-bridge.js';
+import { StubLLMAdapter } from '../../../llm/llm-stub.js';
+import { createAdapter } from '../../../llm/llm-bridge.js';
 import { assessClarity } from '../../retrieval/intent/clarity.js';
 import { isConversational } from '../../retrieval/intent/intent-gate.js';
 import { classifyIntent } from '../../retrieval/domain-router.js';

package/index.js

@@ -7,8 +7,8 @@
  *   import { generateUI }      from '@adia-ai/a2ui-compose';
  *   import { pick, registerEngine } from '@adia-ai/a2ui-compose/strategies/registry';
  *   import { generateZettel }  from '@adia-ai/a2ui-compose/strategies/zettel';
- *   import { llmBridge }       from '@adia-ai/a2ui-compose/llm';
  *
+ * The LLM bridge moved to its own package — `@adia-ai/llm/bridge`.
  * See README for the full public surface.
  */
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@adia-ai/a2ui-compose",
-  "version": "0.2.5",
+  "version": "0.3.1",
   "description": "AdiaUI A2UI compose engine \u2014 framework-agnostic. Takes natural-language intents + a catalog and produces A2UI protocol messages. Pairs with `@adia-ai/a2ui-retrieval` (intent classification, catalog lookup) and `@adia-ai/a2ui-validator` (schema + semantic checks).",
   "type": "module",
   "exports": {
@@ -8,8 +8,6 @@
     "./core": "./core/generator.js",
     "./strategies/zettel": "./strategies/zettel/generator-adapter.js",
     "./strategies/registry": "./strategies/registry.js",
-    "./llm": "./llm/llm-bridge.js",
-    "./llm/*": "./llm/*.js",
     "./transpiler": "./transpiler/transpiler.js",
     "./evals": "./evals/harness.mjs",
     "./engine": "./core/generator.js",
@@ -19,7 +17,6 @@
   "files": [
     "core/",
     "strategies/",
-    "llm/",
     "evals/",
     "transpiler/",
     "index.js",
@@ -37,8 +34,9 @@
     "directory": "packages/a2ui/compose"
   },
   "dependencies": {
-    "@adia-ai/a2ui-utils": "^0.2.0",
-    "@adia-ai/a2ui-retrieval": "^0.2.0",
-    "@adia-ai/a2ui-validator": "^0.2.0"
+    "@adia-ai/a2ui-runtime": "^0.3.0",
+    "@adia-ai/a2ui-retrieval": "^0.3.0",
+    "@adia-ai/a2ui-validator": "^0.3.0",
+    "@adia-ai/llm": "^0.3.0"
   }
 }

package/transpiler/transpiler-maps.js

@@ -8,7 +8,7 @@
  *   3. Input type / ARIA role sub-maps
  */
 
-import { registry } from '@adia-ai/a2ui-utils';
+import { registry } from '@adia-ai/a2ui-runtime';
 
 // ── Alias types to skip in reverse registry (prefer primary type) ────────
 

package/llm/adapters/anthropic.js

@@ -1,106 +0,0 @@
-/**
- * Anthropic Messages API adapter.
- * Endpoint: https://api.anthropic.com/v1/messages
- */
-
-import { readSSE } from './sse.js';
-
-const API_URL = 'https://api.anthropic.com/v1/messages';
-const API_VERSION = '2023-06-01';
-const DEFAULT_MAX_TOKENS = 4096;
-
-export const anthropic = {
-  name: 'anthropic',
-
-  buildRequest(opts) {
-    const body = {
-      model: opts.model,
-      max_tokens: opts.maxTokens || DEFAULT_MAX_TOKENS,
-      messages: opts.messages,
-      stream: !!opts.stream,
-    };
-    if (opts.system) {
-      // Prompt caching: the AdiaUI system prompt is ~23KB and constant across
-      // a session. Emitting it as a cached block marks it as a cache breakpoint
-      // (ephemeral, ~5 min TTL). First call = cache write (+25% cost), every
-      // subsequent call in the window = cache read (−90% cost). No-op below
-      // the model's minimum cacheable size (1024 tok Sonnet/Opus, 2048 Haiku).
-      body.system = opts.cache
-        ? [{ type: 'text', text: opts.system, cache_control: { type: 'ephemeral' } }]
-        : opts.system;
-    }
-    if (opts.temperature != null) body.temperature = opts.temperature;
-    if (opts.thinking) {
-      body.thinking = { type: 'enabled', budget_tokens: opts.thinkingBudget || 10000 };
-    }
-
-    return {
-      url: opts.proxyUrl || API_URL,
-      headers: {
-        'content-type': 'application/json',
-        'x-api-key': opts.apiKey,
-        'anthropic-version': API_VERSION,
-      },
-      body,
-    };
-  },
-
-  parseResponse(data) {
-    const text = data.content?.find(b => b.type === 'text')?.text ?? '';
-    return {
-      text,
-      usage: {
-        input: data.usage?.input_tokens ?? 0,
-        output: data.usage?.output_tokens ?? 0,
-        // Cache telemetry: non-zero cacheRead on turn 2+ is the signal that
-        // caching is actually kicking in. Recorded per-turn for hit-rate analysis.
-        cacheCreation: data.usage?.cache_creation_input_tokens ?? 0,
-        cacheRead: data.usage?.cache_read_input_tokens ?? 0,
-      },
-      stopReason: data.stop_reason ?? 'end',
-    };
-  },
-
-  async *parseStream(response) {
-    let snapshot = '';
-    let usage = { input: 0, output: 0, cacheCreation: 0, cacheRead: 0 };
-    let stopReason = 'end';
-
-    for await (const event of readSSE(response.body)) {
-      if (event.done) break;
-      let data;
-      try { data = JSON.parse(event.data); } catch { continue; }
-      const eventType = event.event ?? data.type;
-
-      switch (eventType) {
-        case 'message_start':
-          if (data.message?.usage) {
-            usage.input = data.message.usage.input_tokens ?? 0;
-            usage.cacheCreation = data.message.usage.cache_creation_input_tokens ?? 0;
-            usage.cacheRead = data.message.usage.cache_read_input_tokens ?? 0;
-          }
-          break;
-        case 'content_block_delta': {
-          const delta = data.delta;
-          if (delta?.type === 'text_delta') {
-            snapshot += delta.text;
-            yield { type: 'text', text: delta.text, snapshot };
-          } else if (delta?.type === 'thinking_delta') {
-            yield { type: 'thinking', text: delta.thinking };
-          }
-          break;
-        }
-        case 'message_delta':
-          if (data.delta?.stop_reason) stopReason = data.delta.stop_reason;
-          if (data.usage) usage.output = data.usage.output_tokens ?? 0;
-          break;
-        case 'message_stop':
-          yield { type: 'done', text: snapshot, usage, stopReason };
-          break;
-        case 'error':
-          yield { type: 'error', error: new Error(data.error?.message ?? 'Stream error') };
-          break;
-      }
-    }
-  },
-};

package/llm/adapters/gemini.js

@@ -1,99 +0,0 @@
-/**
- * Google Gemini generateContent API adapter.
- * Endpoint: https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent
- * Streaming: .../{model}:streamGenerateContent?alt=sse
- */
-
-import { readSSE } from './sse.js';
-
-const API_URL = 'https://generativelanguage.googleapis.com/v1beta/models';
-const DEFAULT_MAX_TOKENS = 4096;
-
-export const gemini = {
-  name: 'gemini',
-
-  buildRequest(opts) {
-    const model = opts.model;
-    const contents = [];
-    for (const msg of opts.messages) {
-      contents.push({
-        role: msg.role === 'assistant' ? 'model' : 'user',
-        parts: [{ text: msg.content }],
-      });
-    }
-
-    const body = { contents };
-
-    if (opts.system) {
-      body.systemInstruction = { parts: [{ text: opts.system }] };
-    }
-
-    const generationConfig = {
-      maxOutputTokens: opts.maxTokens || DEFAULT_MAX_TOKENS,
-    };
-    if (opts.temperature != null) generationConfig.temperature = opts.temperature;
-    body.generationConfig = generationConfig;
-
-    const action = opts.stream
-      ? `streamGenerateContent?alt=sse`
-      : 'generateContent';
-
-    return {
-      url: opts.proxyUrl || `${API_URL}/${model}:${action}`,
-      headers: {
-        'content-type': 'application/json',
-        'x-goog-api-key': opts.apiKey,
-      },
-      body,
-    };
-  },
-
-  parseResponse(data) {
-    const parts = data.candidates?.[0]?.content?.parts ?? [];
-    const text = parts.map(p => p.text ?? '').join('');
-    return {
-      text,
-      usage: {
-        input: data.usageMetadata?.promptTokenCount ?? 0,
-        output: data.usageMetadata?.candidatesTokenCount ?? 0,
-      },
-      stopReason: data.candidates?.[0]?.finishReason === 'STOP' ? 'end' : 'end',
-    };
-  },
-
-  async *parseStream(response) {
-    let snapshot = '';
-    let usage = { input: 0, output: 0 };
-    let stopReason = 'end';
-
-    for await (const event of readSSE(response.body)) {
-      if (event.done) break;
-      let data;
-      try { data = JSON.parse(event.data); } catch { continue; }
-
-      if (data.usageMetadata) {
-        usage.input = data.usageMetadata.promptTokenCount ?? 0;
-        usage.output = data.usageMetadata.candidatesTokenCount ?? 0;
-      }
-
-      const candidate = data.candidates?.[0];
-      if (!candidate) continue;
-
-      if (candidate.finishReason && candidate.finishReason !== 'STOP') {
-        stopReason = candidate.finishReason;
-      }
-
-      const parts = candidate.content?.parts;
-      if (!parts?.length) continue;
-
-      for (const part of parts) {
-        if (part.text != null) {
-          snapshot += part.text;
-          yield { type: 'text', text: part.text, snapshot };
-        }
-      }
-    }
-
-    yield { type: 'done', text: snapshot, usage, stopReason };
-  },
-};

package/llm/adapters/index.js

@@ -1,138 +0,0 @@
-/**
- * LLM Client — Provider-agnostic chat interface.
- *
- * Usage:
- *   import { createClient, chat, streamChat } from './llm/index.js';
- *
- *   // Quick use (provider auto-detected from model name)
- *   const reply = await chat({
- *     apiKey: 'sk-ant-...',
- *     model: 'claude-sonnet-4-20250514',
- *     messages: [{ role: 'user', content: 'Hello' }],
- *   });
- *
- *   for await (const chunk of streamChat({
- *     apiKey: 'sk-...',
- *     model: 'gpt-4o',
- *     messages: [{ role: 'user', content: 'Hello' }],
- *   })) {
- *     if (chunk.type === 'text') process.stdout.write(chunk.text);
- *   }
- *
- *   // Explicit provider
- *   const reply = await chat({ provider: 'gemini', apiKey: '...', model: 'gemini-2.5-flash', ... });
- *
- *   // Reusable client instance
- *   const client = createClient({ provider: 'anthropic', apiKey: '...' });
- *   const reply = await client.chat({ model: 'claude-sonnet-4-20250514', messages: [...] });
- *   for await (const chunk of client.stream({ model: '...', messages: [...] })) { ... }
- *
- * Chunk types (streaming):
- *   { type: 'text',     text: 'delta', snapshot: 'full text so far' }
- *   { type: 'thinking', text: 'thinking delta' }
- *   { type: 'done',     text: 'full response', usage: { input, output }, stopReason }
- *   { type: 'error',    error: Error }
- */
-
-import { anthropic } from './anthropic.js';
-import { openai } from './openai.js';
-import { gemini } from './gemini.js';
-
-// ── Provider registry ──
-
-const providers = { anthropic, openai, gemini };
-
-/** Detect provider from model name. */
-function detectProvider(model) {
-  if (!model) return null;
-  const m = model.toLowerCase();
-  if (m.includes('claude') || m.startsWith('anthropic/')) return 'anthropic';
-  if (m.includes('gpt') || m.includes('o1') || m.includes('o3') || m.includes('o4') || m.startsWith('openai/')) return 'openai';
-  if (m.includes('gemini') || m.startsWith('google/')) return 'gemini';
-  return null;
-}
-
-function resolveAdapter(opts) {
-  const name = opts.provider || detectProvider(opts.model);
-  if (!name) throw new Error(`Cannot detect provider for model "${opts.model}". Set provider explicitly.`);
-  const adapter = providers[name];
-  if (!adapter) throw new Error(`Unknown provider "${name}". Available: ${Object.keys(providers).join(', ')}`);
-  return adapter;
-}
-
-// ── Standalone functions ──
-
-/**
- * Non-streaming chat completion.
- * @returns {Promise<{text: string, usage: {input: number, output: number}, stopReason: string}>}
- */
-export async function chat(opts) {
-  const adapter = resolveAdapter(opts);
-  const { url, headers, body } = adapter.buildRequest({ ...opts, stream: false });
-
-  const res = await fetch(url, {
-    method: 'POST',
-    headers,
-    body: JSON.stringify(body),
-    signal: opts.signal,
-  });
-
-  if (!res.ok) {
-    const err = await res.json().catch(() => ({}));
-    throw new Error(err?.error?.message || `${adapter.name} API error ${res.status}`);
-  }
-
-  return adapter.parseResponse(await res.json());
-}
-
-/**
- * Streaming chat — yields chunks as they arrive.
- * @returns {AsyncGenerator<{type: string, text?: string, snapshot?: string, usage?: object, error?: Error}>}
- */
-export async function* streamChat(opts) {
-  const adapter = resolveAdapter(opts);
-  const { url, headers, body } = adapter.buildRequest({ ...opts, stream: true });
-
-  let res;
-  try {
-    res = await fetch(url, {
-      method: 'POST',
-      headers,
-      body: JSON.stringify(body),
-      signal: opts.signal,
-    });
-  } catch (err) {
-    yield { type: 'error', error: err };
-    return;
-  }
-
-  if (!res.ok) {
-    const err = await res.json().catch(() => ({}));
-    yield { type: 'error', error: new Error(err?.error?.message || `${adapter.name} API error ${res.status}`) };
-    return;
-  }
-
-  yield* adapter.parseStream(res);
-}
-
-// ── Client factory ──
-
-/**
- * Create a reusable client instance with defaults baked in.
- *
- * @param {object} defaults
- * @param {string} defaults.provider — 'anthropic' | 'openai' | 'gemini'
- * @param {string} defaults.apiKey
- * @param {string} [defaults.model] — default model
- * @param {string} [defaults.proxyUrl] — proxy URL (for CORS)
- * @param {string} [defaults.system] — default system prompt
- */
-export function createClient(defaults = {}) {
-  return {
-    chat: (opts) => chat({ ...defaults, ...opts }),
-    stream: (opts) => streamChat({ ...defaults, ...opts }),
-  };
-}
-
-// Re-export adapters for direct use
-export { anthropic, openai, gemini };

package/llm/adapters/openai.js

@@ -1,85 +0,0 @@
-/**
- * OpenAI Chat Completions API adapter.
- * Endpoint: https://api.openai.com/v1/chat/completions
- * Also compatible with: Groq, Together, Mistral, any OpenAI-compatible API.
- */
-
-import { readSSE } from './sse.js';
-
-const API_URL = 'https://api.openai.com/v1/chat/completions';
-const DEFAULT_MAX_TOKENS = 4096;
-
-export const openai = {
-  name: 'openai',
-
-  buildRequest(opts) {
-    const messages = [];
-    if (opts.system) messages.push({ role: 'system', content: opts.system });
-    for (const msg of opts.messages) {
-      messages.push({ role: msg.role, content: msg.content });
-    }
-
-    const body = {
-      model: opts.model,
-      messages,
-      stream: !!opts.stream,
-    };
-    if (opts.maxTokens) body.max_tokens = opts.maxTokens;
-    if (opts.temperature != null) body.temperature = opts.temperature;
-    if (opts.stream) body.stream_options = { include_usage: true };
-
-    return {
-      url: opts.proxyUrl || API_URL,
-      headers: {
-        'content-type': 'application/json',
-        'authorization': `Bearer ${opts.apiKey}`,
-      },
-      body,
-    };
-  },
-
-  parseResponse(data) {
-    const choice = data.choices?.[0];
-    const text = choice?.message?.content ?? '';
-    return {
-      text,
-      usage: { input: data.usage?.prompt_tokens ?? 0, output: data.usage?.completion_tokens ?? 0 },
-      stopReason: choice?.finish_reason === 'stop' ? 'end' : (choice?.finish_reason ?? 'end'),
-    };
-  },
-
-  async *parseStream(response) {
-    let snapshot = '';
-    let usage = { input: 0, output: 0 };
-    let stopReason = 'end';
-
-    for await (const event of readSSE(response.body)) {
-      if (event.done) break;
-      let data;
-      try { data = JSON.parse(event.data); } catch { continue; }
-
-      if (data.usage) {
-        usage.input = data.usage.prompt_tokens ?? 0;
-        usage.output = data.usage.completion_tokens ?? 0;
-      }
-
-      const choice = data.choices?.[0];
-      if (!choice) continue;
-
-      if (choice.finish_reason) {
-        stopReason = choice.finish_reason === 'stop' ? 'end' : choice.finish_reason;
-      }
-
-      const delta = choice.delta;
-      if (delta?.content) {
-        snapshot += delta.content;
-        yield { type: 'text', text: delta.content, snapshot };
-      }
-      if (delta?.reasoning_content) {
-        yield { type: 'thinking', text: delta.reasoning_content };
-      }
-    }
-
-    yield { type: 'done', text: snapshot, usage, stopReason };
-  },
-};

package/llm/adapters/sse.js

@@ -1,50 +0,0 @@
-/**
- * SSE Parser — shared by Anthropic, OpenAI, and Gemini adapters.
- * Handles partial line buffering, double-newline splitting, and [DONE] detection.
- */
-
-export async function* readSSE(body) {
-  const reader = body.getReader();
-  const decoder = new TextDecoder();
-  let buffer = '';
-  try {
-    while (true) {
-      const { done, value } = await reader.read();
-      if (done) break;
-      buffer += decoder.decode(value, { stream: true });
-      const { events, remainder } = parse(buffer);
-      buffer = remainder;
-      for (const event of events) yield event;
-    }
-    if (buffer.trim()) {
-      const { events } = parse(buffer + '\n\n');
-      for (const event of events) yield event;
-    }
-  } finally {
-    reader.releaseLock();
-  }
-}
-
-function parse(text) {
-  const events = [];
-  const parts = text.split(/\n\n|\r\n\r\n/);
-  const remainder = parts.pop() ?? '';
-  for (const part of parts) {
-    const trimmed = part.trim();
-    if (!trimmed) continue;
-    let eventType;
-    const dataLines = [];
-    for (const line of trimmed.split(/\r?\n/)) {
-      if (line.startsWith(':')) continue;
-      if (line.startsWith('event:')) eventType = line.slice(6).trim();
-      else if (line.startsWith('data:')) {
-        const v = line.slice(5);
-        dataLines.push(v.startsWith(' ') ? v.slice(1) : v);
-      }
-    }
-    if (!dataLines.length) continue;
-    const data = dataLines.join('\n');
-    events.push({ event: eventType, data, done: data === '[DONE]' });
-  }
-  return { events, remainder };
-}

package/llm/llm-bridge.js

@@ -1,214 +0,0 @@
-/**
- * LLM Bridge — Wraps AdiaUI's llm module into the AdiaUI createAdapter() API.
- *
- * This is the single integration point between the AdiaUI pipeline and the
- * LLM module. It handles:
- *   - Env var reading (VITE_* in browser, process.env in Node)
- *   - CORS proxy routing in browser (Vite dev server at /api/llm/*)
- *   - API translation (AdiaUI's simple { messages, systemPrompt } → llm module's interface)
- *
- * Consumers call createAdapter() and get an object with .complete() and .stream()
- * matching the AdiaUI pipeline interface.
- */
-
-import { StubLLMAdapter } from './llm-stub.js';
-
-// Lazy-loaded — ../llm/index.js uses Vite aliases that don't resolve in Node
-let _createClient = null;
-async function getCreateClient() {
-  if (!_createClient) {
-    try {
-      const mod = await import('./adapters/index.js');
-      _createClient = mod.createClient;
-    } catch {
-      _createClient = null;
-    }
-  }
-  return _createClient;
-}
-
-// ── Environment ──────────────────────────────────────────────────────────
-
-function getEnv(key) {
-  try {
-    const env = import.meta.env;
-    if (env) {
-      const val = env[`VITE_${key}`] || env[key];
-      if (val) return val;
-    }
-  } catch {}
-  if (typeof process !== 'undefined' && process.env) {
-    return process.env[key] || '';
-  }
-  return '';
-}
-
-const IS_BROWSER = typeof window !== 'undefined';
-
-function resolveBaseUrl(provider) {
-  if (!IS_BROWSER) return undefined; // Let the module use its defaults
-  const proxyMap = {
-    anthropic: '/api/llm/anthropic/v1/messages',
-    openai: '/api/llm/openai/v1/chat/completions',
-    google: '/api/llm/google',
-  };
-  return proxyMap[provider];
-}
-
-// ── Factory ──────────────────────────────────────────────────────────────
-
-/**
- * Create an LLM adapter for the AdiaUI pipeline.
- *
- * Auto-detects provider from env vars. Returns an object with .complete()
- * and .stream() that match the AdiaUI interface (simple messages + systemPrompt).
- *
- * @param {object} [opts]
- * @param {string} [opts.provider] — 'anthropic' | 'openai' | 'google' | 'stub'
- * @param {string} [opts.apiKey] — explicit API key (overrides env)
- * @param {string} [opts.model] — model override
- * @returns {StubLLMAdapter | AdiaUILLMBridge}
- */
-export async function createAdapter(opts = {}) {
-  const provider = opts.provider || getEnv('LLM_PROVIDER') || detectProvider();
-  const model = opts.model || getEnv('LLM_MODEL') || undefined;
-
-  if (provider === 'stub') return new StubLLMAdapter();
-
-  // Resolve API key for the detected provider
-  const apiKey = opts.apiKey || getEnv(`${provider.toUpperCase()}_API_KEY`) || getEnv('ANTHROPIC_API_KEY') || getEnv('OPENAI_API_KEY') || getEnv('GOOGLE_API_KEY');
-
-  // No key found → fall back to stub
-  if (!apiKey) {
-    console.warn('LLM Bridge: No API keys found. Using stub adapter.');
-    return new StubLLMAdapter();
-  }
-
-  const createClient = await getCreateClient();
-  if (!createClient) {
-    console.warn('LLM Bridge: LLM module not available. Using stub adapter.');
-    return new StubLLMAdapter();
-  }
-
-  const proxyUrl = resolveBaseUrl(provider);
-  const client = createClient({
-    provider,
-    apiKey,
-    model: model || DEFAULT_MODELS[provider] || 'claude-sonnet-4-20250514',
-    ...(proxyUrl ? { proxyUrl } : {}),
-  });
-
-  return new AdiaUILLMBridge(client, model || DEFAULT_MODELS[provider] || 'claude-sonnet-4-20250514', provider);
-}
-
-function detectProvider() {
-  if (getEnv('ANTHROPIC_API_KEY')) return 'anthropic';
-  if (getEnv('OPENAI_API_KEY')) return 'openai';
-  if (getEnv('GOOGLE_API_KEY')) return 'google';
-  return 'stub';
-}
-
-// ── Bridge class ─────────────────────────────────────────────────────────
-
-/** Default models per provider */
-const DEFAULT_MODELS = {
-  anthropic: 'claude-sonnet-4-20250514',
-  openai: 'gpt-4o',
-  google: 'gemini-2.0-flash',
-};
-
-/**
- * Wraps the AdiaUI llm client to match the AdiaUI pipeline's simpler interface.
- *
- * AdiaUI calls: adapter.complete({ messages, systemPrompt })
- * LLM module expects: client.chat({ model, messages, system, ... })
- */
-class AdiaUILLMBridge {
-  #client;
-  #model;
-  #provider;
-
-  constructor(client, model, provider) {
-    this.#client = client;
-    this.#model = model;
-    this.#provider = provider;
-  }
-
-  /**
-   * Non-streaming completion. Matches AdiaUI interface.
-   *
-   * 32k max_tokens: A2UI JSON for moderately complex UIs (kanban, dashboard,
-   * pricing table) routinely exceeds 8k. Truncation produced silent fallbacks
-   * that the validator rubber-stamped at ~89/100 — see diagnosis report
-   * 2026-04-19. Modern Claude/GPT/Gemini all support ≥32k output cleanly.
-   *
-   * @param {{ messages: { role: string, content: string }[], systemPrompt?: string }} opts
-   * @returns {Promise<{ content: string, stopReason: string, usage: { inputTokens: number, outputTokens: number } }>}
-   */
-  async complete({ messages, systemPrompt }) {
-    const response = await this.#client.chat({
-      model: this.#model,
-      messages,
-      system: systemPrompt,
-      maxTokens: 32768,
-      // Anthropic-only: mark the system prompt as a cache breakpoint. No-op
-      // on other providers (unknown opt silently ignored) and no-op below the
-      // model's minimum cacheable size.
-      cache: this.#provider === 'anthropic',
-    });
-    return {
-      content: response.text,
-      // 'max_tokens' / 'length' / 'MAX_TOKENS' (Gemini) signal truncation;
-      // downstream parser uses this to refuse silent fallback rendering.
-      stopReason: response.stopReason ?? 'end',
-      usage: {
-        inputTokens: response.usage?.input ?? 0,
-        outputTokens: response.usage?.output ?? 0,
-        cacheCreationTokens: response.usage?.cacheCreation ?? 0,
-        cacheReadTokens: response.usage?.cacheRead ?? 0,
-      },
-    };
-  }
-
-  /**
-   * Streaming completion. Matches AdiaUI interface.
-   *
-   * @param {{ messages: { role: string, content: string }[], systemPrompt?: string }} opts
-   * @yields {{ type: 'text', content: string } | { type: 'done', stopReason: string, usage: { inputTokens: number, outputTokens: number, cacheCreationTokens: number, cacheReadTokens: number } }}
-   */
-  async *stream({ messages, systemPrompt }) {
-    for await (const chunk of this.#client.stream({
-      model: this.#model,
-      messages,
-      system: systemPrompt,
-      maxTokens: 32768,
-      cache: this.#provider === 'anthropic',
-    })) {
-      if (chunk.type === 'text') {
-        yield { type: 'text', content: chunk.text };
-      } else if (chunk.type === 'done') {
-        // Surface the terminal stopReason + cache telemetry so the consumer
-        // can detect max_tokens truncation and the dialog recorder can log
-        // cache hit-rate per turn.
-        yield {
-          type: 'done',
-          stopReason: chunk.stopReason ?? 'end',
-          usage: {
-            inputTokens: chunk.usage?.input ?? 0,
-            outputTokens: chunk.usage?.output ?? 0,
-            cacheCreationTokens: chunk.usage?.cacheCreation ?? 0,
-            cacheReadTokens: chunk.usage?.cacheRead ?? 0,
-          },
-        };
-      }
-      // Other chunk types (thinking, error) are still available on the
-      // underlying adapter but the AdiaUI pipeline doesn't consume them yet.
-    }
-  }
-
-  /** Expose the underlying client for advanced use. */
-  get adapter() { return this.#client; }
-
-  /** Expose provider name for detection. */
-  get provider() { return this.#provider; }
-}

package/llm/llm-stub.js

@@ -1,69 +0,0 @@
-/**
- * StubLLMAdapter — Deterministic LLM adapter for testing.
- *
- * Returns canned A2UI responses for known prompts. Implements the same
- * interface that a real LLM adapter would (complete, stream) so pipeline
- * code can develop against it without API keys.
- */
-
-export class StubLLMAdapter {
-  /**
-   * Complete a prompt and return a full A2UI response.
-   *
-   * @param {object} opts
-   * @param {object[]} opts.messages — Chat messages (system + user turns)
-   * @param {string} [opts.systemPrompt] — System prompt override
-   * @returns {Promise<{ content: string, usage: { inputTokens: number, outputTokens: number } }>}
-   */
-  async complete({ messages, systemPrompt }) {
-    const lastMessage = messages?.[messages.length - 1]?.content || '';
-    const components = this.#buildResponse(lastMessage);
-
-    return {
-      content: JSON.stringify([
-        {
-          type: 'updateComponents',
-          surfaceId: 'default',
-          components,
-        },
-      ]),
-      usage: {
-        inputTokens: estimateTokens(JSON.stringify(messages)),
-        outputTokens: estimateTokens(JSON.stringify(components)),
-      },
-    };
-  }
-
-  /**
-   * Stream a response as an async iterable of chunks.
-   *
-   * @param {object} request — Same shape as complete()
-   * @yields {{ type: 'text', content: string }}
-   */
-  async *stream(request) {
-    const result = await this.complete(request);
-    // Simulate progressive streaming by yielding the full response
-    yield { type: 'text', content: result.content };
-  }
-
-  /**
-   * Build a canned component tree from the intent text.
-   * @param {string} intent
-   * @returns {object[]}
-   */
-  #buildResponse(intent) {
-    return [
-      { id: 'root', component: 'Card', children: ['hdr', 'sec'] },
-      { id: 'hdr', component: 'Header', children: ['title'] },
-      { id: 'title', component: 'Text', variant: 'h3', textContent: 'Generated UI' },
-      { id: 'sec', component: 'Section', children: ['col'] },
-      { id: 'col', component: 'Column', children: ['desc'] },
-      { id: 'desc', component: 'Text', variant: 'body', textContent: intent || 'No intent provided' },
-    ];
-  }
-}
-
-/** Rough token estimate (~4 chars per token) */
-function estimateTokens(text) {
-  return Math.ceil((text?.length || 0) / 4);
-}