feat(llm): 在 compaction 中按路由为图片请求压力计价

Closes #2848. - dsh-llm 新增 LlmAdapter.imageRequestPricing 同步钩子与 LlmImageRequestPricing/LlmImageRequestPrice 词汇，ctx.llm 按路由解析 - llm-deepseek 用官方公布的 v4 视觉计算器逐句移植（14px patch、3:1 降采样、384 上限、最坏对齐 pad）实现该钩子，复现请求投影的最旧优先 offload 与像素预算缩放；纯几何 requestImageDimensions 上移到 dsh-attachment - token-meter 表层 fold 存储与路由无关的节点事实，measure() 按生效 envelope 的路由为图片出现处定价；锚点存快照并按同一路由重定价；TokenSurfaceNode 同时携带路由价 tokens 与固定启发式 heuristicTokens - compaction 触发、保留与选段读取同一套路由价，记录的 shadowedTokenCount 保持启发式以维持 O(1) 投影 fold 一致 - llm-replay 支持按模型的 imageRequestTokens 声明；新增 keyless 的 image-compaction ACP 快照场景端到端验证装配应用
2026-09-09 04:02:35 +00:00 · 2026-08-24 19:15:30 +08:00
parent de6d83a0fa
commit 42164508c8
76 changed files with 1845 additions and 278 deletions
@@ -1878,3 +1878,119 @@ describe('automatic listener and loader composition', () => {
    expect(await recover(ctx, agent(session, MODEL), overflow())).toBe(false)
  })
 })
+
+describe('route-priced image pressure', () => {
+  const IMAGE_VISUAL_TOKENS = 300
+  const IMAGE_HANDLE_TEXT = 'request preview'
+
+  class PricedContextAdapter extends ContextAdapter {
+    override imageRequestPricing(): { priceImages: (images: readonly unknown[]) => Array<{ visualTokens: number; text: string }> } {
+      return {
+        priceImages: images => images.map(() => ({
+          visualTokens: IMAGE_VISUAL_TOKENS,
+          text: IMAGE_HANDLE_TEXT,
+        })),
+      }
+    }
+  }
+
+  function pricedContext(contextWindow = 1_000): Context {
+    const ctx = new Context()
+    void new LlmRuntime(ctx)
+    void new TokenMeter(ctx)
+    ctx.llm.registerAdapter([MODEL], new PricedContextAdapter(contextWindow))
+    return ctx
+  }
+
+  /** Closed short-text turns whose user messages each carry one image. */
+  function imageConversation(turns = 4): Session {
+    const session = Session.create(SessionId(`image-dense-${turns}`))
+    for (let turn = 1; turn <= turns; turn += 1) {
+      session.append('turn/start', { turn })
+      session.append('user/message', createUserMessage({
+        content: [
+          { type: 'text', text: `image turn ${turn}` },
+          {
+            type: 'image',
+            attachment: {
+              attachmentId: AttachmentId(`sha256:${String(turn).repeat(8)}`),
+              mediaType: 'image/png',
+              bytes: 2048,
+              width: 800,
+              height: 800,
+              name: `shot-${turn}`,
+            },
+          },
+        ],
+        source: { kind: 'user' },
+      }), { surfaceOp: 'append' })
+      session.append('step/start', { turn, step: 1 })
+      if (turn === 1) {
+        session.append('request/header', {
+          header: { config: { provider: MODEL, model: MODEL } },
+          reason: 'initial',
+        })
+      }
+      session.append('assistant/message', {
+        turn,
+        step: 1,
+        message: createMessage({
+          role: 'assistant',
+          content: [{ type: 'text', text: `ok ${turn}` }],
+          source: {
+            kind: 'model',
+            ...{ provider: MODEL, model: MODEL },
+          },
+        }),
+      }, { surfaceOp: 'append' })
+      session.append('step/end', { turn, step: 1 })
+      session.append('turn/end', { turn, reason: { kind: 'completed' } })
+    }
+    session.append('turn/start', { turn: turns + 1 })
+    return session
+  }
+
+  it('selects an image-dense range only when the routed price counts visual tokens', () => {
+    const session = imageConversation()
+    const routed = pricedContext().tokenMeter.measure(session)
+    const neutral = createContext().tokenMeter.measure(session)
+
+    expect(routed.surfaceTokens).toBeGreaterThan(neutral.surfaceTokens + 4 * IMAGE_VISUAL_TOKENS - 200)
+    expect(routed.nodes.map(node => node.seq)).toEqual(neutral.nodes.map(node => node.seq))
+    expect(routed.nodes.map(node => node.heuristicTokens)).toEqual(neutral.nodes.map(node => node.tokens))
+
+    // The same verbatim tail budget retains almost everything under the
+    // neutral heuristic but forces a cut once visual tokens are counted.
+    expect(selectCompactableRange(session, neutral, 350)).toBeNull()
+    const range = selectCompactableRange(session, routed, 350)
+    expect(range).not.toBeNull()
+  })
+
+  it('triggers pressure compaction from routed visual tokens and logs heuristic shadow prices', async () => {
+    const ctx = pricedContext(1_000)
+    const session = imageConversation()
+    const before = ctx.tokenMeter.measure(session)
+    const compact = new TestCompactionEngine(ctx, {
+      auto: false,
+      thresholdRatio: 0.8,
+      retainTokens: 350,
+    })
+
+    // The same history stays below the 800-token threshold without pricing.
+    const neutralResult = await compactIfNeeded(service({
+      auto: false,
+      thresholdRatio: 0.8,
+      retainTokens: 350,
+    }), session)
+    expect(neutralResult).toBeNull()
+
+    const result = await compact.compactIfNeeded(agent(session), 'pressure', SIGNAL)
+    expect(result).not.toBeNull()
+    const summaryEvent = session.events.find(event => event.type === 'compaction/summary')
+    expect(summaryEvent).toBeDefined()
+    const shadowedHeuristic = before.nodes
+      .filter(node => result?.shadowedSeqs.includes(node.seq))
+      .reduce((total, node) => total + node.heuristicTokens, 0)
+    expect(summaryEvent?.data.shadowedTokenCount).toBe(shadowedHeuristic)
+  })
+})