Add two DeepSeek LLM adapters: dsh-llm-deepseek and dsh-llm-pi-ai

The first real LlmAdapter implementations, shipped as a deliberate pair:
same models and wire protocol, completely different internals, so the
StreamChunk protocol is verified across independent implementations.

- dsh-llm-deepseek: hand-rolled fetch + SSE parser + chunk-translation
  state machine against the official chat-completions format (thinking
  mode via top-level thinking/reasoning_effort; the empty-string
  reasoning_content first chunk; usage attached to the finish chunk or
  trailing; reasoning_content passback on tool-call turns; disjoint
  cache-token accounting).
- dsh-llm-pi-ai: the same endpoint through @earendil-works/pi-ai,
  mapping its event vocabulary (parsed tool arguments, in-stream error
  events, folded reasoning tokens) onto the same chunks.

The agent loop now honors the in-band error path: an adapter that ends
its stream with finish {kind:error|aborted} (the only option for
adapters that can't throw mid-stream, like pi-ai) is translated into a
step error, so the turn ends error/aborted with a logged error event
instead of a normal completed assistant message. This makes the
StreamChunk error contract real for both adapters; docs/architecture.md
and the StreamChunk doc are updated accordingly.

New yarn test:e2e (vitest.e2e.config.ts, *.e2e.ts) runs key-gated
real-API matrices for both adapters across V4 Flash/Pro and all
thinking/effort levels; it self-skips without DEEPSEEK_API_KEY. Unit
suites run against local node:http mock SSE servers at 100% per-file
coverage.

packages/llm-pi-ai/tests/adapter.e2e.ts

@@ -0,0 +1,130 @@
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import LlmService, { CallId } from '@deepseek-ai/dsh-llm'
+import type { GenerateResult, Message, ToolSchema } from '@deepseek-ai/dsh-llm'
+import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai'
+import type { Config } from '@deepseek-ai/dsh-llm-pi-ai'
+import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
+
+/**
+ * Real-API e2e for the pi-ai-backed adapter: V4 Flash + V4 Pro across all
+ * reasoning levels the adapter exposes (off / high / xhigh→wire 'max').
+ * Mirrors the llm-deepseek matrix so the two independent implementations
+ * verify the same StreamChunk contract. Key-gated.
+ */
+
+const FLASH = 'deepseek-v4-flash'
+const PRO = 'deepseek-v4-pro'
+
+async function harness(model: string, config: Partial<Config> = {}) {
+  const ctx = new Context()
+  await ctx.plugin(LlmService)
+  await ctx.plugin(LlmPiAi, { models: [model], ...config })
+  return ctx
+}
+
+function ask(text: string): Message[] {
+  return [{ role: 'user', content: [{ type: 'text', text }] }]
+}
+
+function textOf(result: GenerateResult): string {
+  return result.message.content
+    .filter(block => block.type === 'text')
+    .map(block => block.text)
+    .join('')
+}
+
+function blockKinds(result: GenerateResult): string[] {
+  return result.message.content.map(block => block.type)
+}
+
+const weatherTool: ToolSchema = {
+  name: 'get_weather',
+  description: 'Get the current weather for a city.',
+  parameters: {
+    type: 'object',
+    properties: { city: { type: 'string', description: 'City name' } },
+    required: ['city'],
+  },
+}
+
+describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () => {
+  it.each([FLASH, PRO])('%s + reasoning off: plain text generation', async (model) => {
+    const ctx = await harness(model, { reasoning: 'off' })
+    const result = await ctx.llm.generate({
+      model,
+      messages: ask('Reply with exactly the word: pong'),
+      maxTokens: 50,
+    })
+    expect(result.finish.kind).toBe('stop')
+    expect(textOf(result).toLowerCase()).toContain('pong')
+    expect(result.message.content.some(block => block.type === 'reasoning')).toBe(false)
+  })
+
+  it.each([FLASH, PRO])('%s + reasoning high: reasoning blocks present', async (model) => {
+    const ctx = await harness(model, { reasoning: 'high' })
+    const result = await ctx.llm.generate({
+      model,
+      messages: ask('Which is larger, 9.11 or 9.8? Answer with just the number.'),
+      maxTokens: 2000,
+    })
+    expect(result.finish.kind).toBe('stop')
+    expect(result.message.content.some(block => block.type === 'reasoning')).toBe(true)
+    expect(textOf(result)).toContain('9.8')
+  })
+
+  it('pro + reasoning xhigh (wire max): tool-call round trip', async () => {
+    const ctx = await harness(PRO, { reasoning: 'xhigh' })
+
+    const first = await ctx.llm.generate({
+      model: PRO,
+      messages: ask('What is the weather in Paris right now? Use the get_weather tool.'),
+      tools: [weatherTool],
+      maxTokens: 2000,
+    })
+    expect(first.finish.kind).toBe('tool-calls')
+    const call = first.message.content.find(block => block.type === 'tool-call')
+    expect(call).toBeDefined()
+    expect(call!.name).toBe('get_weather')
+    expect(JSON.parse(call!.arguments)).toMatchObject({ city: expect.stringMatching(/paris/i) as string })
+
+    const second = await ctx.llm.generate({
+      model: PRO,
+      messages: [
+        ...ask('What is the weather in Paris right now? Use the get_weather tool.'),
+        { role: 'assistant', content: first.message.content },
+        {
+          role: 'user',
+          content: [{
+            type: 'tool-result',
+            toolCallId: CallId(call!.id),
+            content: [{ type: 'text', text: 'Sunny, 22°C' }],
+          }],
+        },
+      ],
+      tools: [weatherTool],
+      maxTokens: 2000,
+    })
+    expect(second.finish.kind).toBe('stop')
+    expect(textOf(second).toLowerCase()).toMatch(/sunny|22/)
+  })
+
+  it('produces the same block structure as llm-deepseek for the same prompt', async () => {
+    // Loose structural equivalence between the two independent adapters:
+    // same block KINDS in the same order for a deterministic prompt — the
+    // cross-implementation check that the StreamChunk design holds.
+    const deepseekCtx = new Context()
+    await deepseekCtx.plugin(LlmService)
+    await deepseekCtx.plugin(LlmDeepSeek, { models: [FLASH], thinking: 'disabled' })
+
+    const piCtx = await harness(FLASH, { reasoning: 'off' })
+
+    const prompt = ask('Reply with exactly the word: pong')
+    const [fromDeepSeek, fromPiAi] = await Promise.all([
+      deepseekCtx.llm.generate({ model: FLASH, messages: prompt, maxTokens: 50 }),
+      piCtx.llm.generate({ model: FLASH, messages: prompt, maxTokens: 50 }),
+    ])
+    expect(blockKinds(fromPiAi)).toEqual(blockKinds(fromDeepSeek))
+    expect(fromPiAi.finish.kind).toBe(fromDeepSeek.finish.kind)
+  })
+})