refactor(llm): resolve model metadata together

2026-07-26 13:07:27 +08:00
parent baea5018e5
commit 73e7e27799
55 changed files with 607 additions and 460 deletions
--- a/packages/ui/tui/tests/harness.ts
+++ b/packages/ui/tui/tests/harness.ts
@@ -10,10 +10,9 @@ import AgentRegistry, {
 } from '@deepseek-ai/dsh-agent'
 import type {
  ContentBlock,
-  LlmModelContext,
  LlmModelInfo,
-  LlmModelReasoningInfo,
  LlmProviderInfo,
+  LlmResolvedModelInfo,
 } from '@deepseek-ai/dsh-llm'
 import CommandService from '@deepseek-ai/dsh-commands'
 import SessionStore, { SessionId, type Session, type SessionHeader } from '@deepseek-ai/dsh-session'
@@ -53,11 +52,10 @@ export interface TuiHarnessOptions {
    providers: LlmProviderInfo[]
    models: LlmModelInfo[]
    listModels?: (provider: string) => Promise<LlmModelInfo[]>
-    resolveModelContext?: (provider: string, model: string) => Promise<LlmModelContext | undefined>
-    resolveModelReasoning?: (
+    resolveModelInfo?: (
      provider: string,
      model: string,
-    ) => Promise<LlmModelReasoningInfo | undefined>
+    ) => Promise<Pick<LlmResolvedModelInfo, 'context' | 'reasoning'>>
  }
  /** Provide a fake `sessionPersistence` service so resume surfaces can list sessions. */
  sessionPersistence?: {
@@ -128,12 +126,20 @@ export async function createTuiTestHarness<TerminalType extends Terminal, Exit e
        return catalog.listModels?.(provider)
          ?? Promise.resolve(catalog.models.filter(model => model.provider === provider).map(model => ({ ...model })))
      },
-      resolveModelContext(provider: string, model: string) {
-        return catalog.resolveModelContext?.(provider, model)
-          ?? Promise.resolve({ contextWindow: options.contextWindow ?? 128_000 })
-      },
-      resolveModelReasoning(provider: string, model: string) {
-        return catalog.resolveModelReasoning?.(provider, model) ?? Promise.resolve(undefined)
+      async resolveModelInfo(provider: string, model: string) {
+        const advertised = catalog.models.find(candidate =>
+          candidate.provider === provider && candidate.id === model)
+        const capabilities = await (catalog.resolveModelInfo?.(provider, model)
+          ?? Promise.resolve({
+            context: { contextWindow: options.contextWindow ?? 128_000 },
+          }))
+        return {
+          provider,
+          id: model,
+          name: advertised?.name ?? model,
+          ...advertised?.description === undefined ? {} : { description: advertised.description },
+          ...capabilities,
+        }
      },
    } as never)
  }
--- a/packages/ui/tui/tests/snapshots/model-effort-switching.expected.txt
+++ b/packages/ui/tui/tests/snapshots/model-effort-switching.expected.txt
@@ -26,7 +26,7 @@ buffer
  style 8-8 fg=bright-blue
  style 38-77 fg=bright-black
  style 83-83 fg=bright-blue
-15| "        │ → deepseek/deepseek-v4-pro        DeepSeek V4 Pro — Max                  │        "
+15| "        │ → deepseek/deepseek-v4-pro        DeepSeek V4 Pro — Off                  │        "
  style 8-8 fg=bright-blue
  style 10-64 fg=bright-blue inverse
  style 83-83 fg=bright-blue
--- a/packages/ui/tui/tests/snapshots/model-switching.expected.txt
+++ b/packages/ui/tui/tests/snapshots/model-switching.expected.txt
@@ -8,10 +8,10 @@ buffer
  style 10-16 bold
 1| " Snapshot agent ready."
  style 1-21 fg=bright-black
-2| " deepseek-v4-pro max  •  main-session"
+2| " deepseek-v4-pro off  •  main-session"
  style 1-36 dim
 3| <blank>
-4| " Model selected: deepseek/deepseek-v4-pro. Reasoning effort: Max. New steps will use it.    "
+4| " Model selected: deepseek/deepseek-v4-pro. Reasoning effort: Off. New steps will use it.    "
  style 1-87 fg=bright-black
 5| "────────────────────────────────────────────────────────────────────────────────────────────"
  style 0-91 dim
@@ -19,7 +19,7 @@ buffer
  style 1-1 inverse
 7| "────────────────────────────────────────────────────────────────────────────────────────────"
  style 0-91 dim
-8| "deepseek-v4-pro max  /workspace/project  ↑0 ↓0                   0% context  tools:collapsed"
+8| "deepseek-v4-pro off  /workspace/project  ↑0 ↓0                   0% context  tools:collapsed"
  style 0-45 dim
  style 65-91 dim
 9-31| <blank>
--- a/packages/ui/tui/tests/tui.snapshot.ts
+++ b/packages/ui/tui/tests/tui.snapshot.ts
@@ -640,12 +640,16 @@ describe('TUI terminal-state snapshots', () => {
          { provider: 'deepseek', id: 'deepseek-v4-flash', name: 'DeepSeek V4 Flash' },
          { provider: 'deepseek', id: 'deepseek-v4-pro', name: 'DeepSeek V4 Pro' },
        ],
-        resolveModelReasoning: () => Promise.resolve({
-          efforts: [
-            { id: ReasoningEffortId('high'), name: 'High' },
-            { id: ReasoningEffortId('max'), name: 'Max' },
-          ],
-          defaultEffort: ReasoningEffortId('high'),
+        resolveModelInfo: () => Promise.resolve({
+          context: { contextWindow: 128_000 },
+          reasoning: {
+            efforts: [
+              { id: ReasoningEffortId('off'), name: 'Off' },
+              { id: ReasoningEffortId('high'), name: 'High' },
+              { id: ReasoningEffortId('max'), name: 'Max' },
+            ],
+            defaultEffort: ReasoningEffortId('high'),
+          },
        }),
      },
    }, { columns: 92, rows: 32 })
@@ -657,6 +661,7 @@ describe('TUI terminal-state snapshots', () => {
    await renderAfter(harness, () => {
      harness.terminal.send('\x1b[B')
      harness.terminal.send('\x1b[Z')
+      harness.terminal.send('\x1b[Z')
    })
    await checkpoint('model-effort-switching', harness.terminal, { includeScrollback: true })
    await renderAfter(harness, () => {
--- a/packages/ui/tui/tests/tui.spec.ts
+++ b/packages/ui/tui/tests/tui.spec.ts
@@ -5,7 +5,11 @@ import { describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
 import { CombinedAutocompleteProvider, type Terminal } from '@earendil-works/pi-tui'
 import AgentRegistry, { agentEvents, assembleContextFor, AgentMessageId, type Agent } from '@deepseek-ai/dsh-agent'
-import { ReasoningEffortId, type LlmCallConfig } from '@deepseek-ai/dsh-llm'
+import {
+  ReasoningEffortId,
+  type LlmCallConfig,
+  type LlmModelReasoningInfo,
+} from '@deepseek-ai/dsh-llm'
 import { GOAL_CHANGE_VERSION, GoalId, renderGoalChange, type GoalSnapshotChangeMeta } from '@deepseek-ai/dsh-goal'
 import CommandService, { type CommandInvocation } from '@deepseek-ai/dsh-commands'
 import SessionStore, { SessionId, type JsonValue, type SessionEvent, type SessionHeader, type TurnEndReason } from '@deepseek-ai/dsh-session'
@@ -143,7 +147,11 @@ function provideLlmCatalog(ctx: Context): void {
  ctx.provide('llm', {
    listProviders: () => [],
    listModels: () => Promise.resolve([]),
-    resolveModelContext: () => Promise.resolve(undefined),
+    resolveModelInfo: (provider: string, model: string) => Promise.resolve({
+      provider,
+      id: model,
+      name: model,
+    }),
  } as never)
 }

@@ -1155,7 +1163,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
    expect(result.terminal.output).toContain('restored answer')
    expect(result.terminal.output).toContain('write tests')
    expect(result.terminal.output).toContain('↑1.3k ↓42')
-    // Context resolution is async (resolveModelContext); settle before reading.
+    // Exact model resolution is async; settle before reading.
    await tick()
    expect(result.terminal.output).toContain('42% context  tools:collapsed')
    // Narrow terminals clip the right-hand context/tools segment first; the
@@ -1741,7 +1749,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
      catalog: {
        providers: [],
        models: [],
-        resolveModelContext: () => Promise.resolve(undefined),
+        resolveModelInfo: () => Promise.resolve({}),
      },
    })
    result.terminal.send('/status')
@@ -2288,6 +2296,7 @@ describe('pi-tui chat lifecycle and transcript', () => {

  it('opens a keyboard selector and switches the session model without sending slash text to the agent', async () => {
    const initialContext = Promise.withResolvers<{ contextWindow: number }>()
+    let deferInitialContext = true
    const result = await setup({
      agentOptions: { provider: 'alpha', model: 'a1' },
      contextTokens: 50,
@@ -2299,37 +2308,41 @@ describe('pi-tui chat lifecycle and transcript', () => {
          { provider: 'beta', id: 'b1', name: 'Beta One' },
          { provider: 'beta', id: 'shared', name: 'Beta Shared' },
        ],
-        resolveModelContext: (provider, model) => provider === 'alpha' && model === 'a1'
-          ? initialContext.promise
-          : Promise.resolve({ contextWindow: 200 }),
-        resolveModelReasoning: (provider, model) => {
+        async resolveModelInfo(provider, model) {
+          const shouldDeferContext = provider === 'alpha' && model === 'a1' && deferInitialContext
+          if (shouldDeferContext) deferInitialContext = false
+          const context = shouldDeferContext
+            ? await initialContext.promise
+            : { contextWindow: 200 }
+          let reasoning: LlmModelReasoningInfo | undefined
          if (model === 'a1') {
-            return Promise.resolve({
+            reasoning = {
              efforts: [
                { id: ReasoningEffortId('low'), name: 'Low' },
                { id: ReasoningEffortId('high'), name: 'High' },
              ],
              defaultEffort: ReasoningEffortId('low'),
-            })
-          }
-          if (model === 'b1') {
-            return Promise.resolve({
+            }
+          } else if (model === 'b1') {
+            reasoning = {
              efforts: [
                { id: ReasoningEffortId('high'), name: 'High' },
                { id: ReasoningEffortId('max'), name: 'Max' },
              ],
              defaultEffort: ReasoningEffortId('high'),
-            })
-          }
-          if (provider === 'alpha' && model === 'shared') {
-            return Promise.resolve({
+            }
+          } else if (provider === 'alpha' && model === 'shared') {
+            reasoning = {
              efforts: [
                { id: ReasoningEffortId('standard'), name: 'Standard' },
                { id: ReasoningEffortId('ultra'), name: 'Ultra' },
              ],
-            })
+            }
+          }
+          return {
+            context,
+            ...reasoning === undefined ? {} : { reasoning },
          }
-          return Promise.resolve(undefined)
        },
      },
    })
@@ -2522,7 +2535,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
      catalog: {
        providers: [{ id: 'alpha', name: 'Alpha' }],
        models: [{ provider: 'alpha', id: 'a1', name: 'Alpha One' }],
-        resolveModelContext: () => Promise.resolve(undefined),
+        resolveModelInfo: () => Promise.resolve({}),
      },
    })
    unset.terminal.send('/model')
@@ -2554,7 +2567,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
        providers: [{ id: 'deepseek', name: 'DeepSeek' }],
        models: [],
        listModels: () => Promise.reject(new Error('catalog offline')),
-        resolveModelContext: () => Promise.reject(new Error('capacity offline')),
+        resolveModelInfo: () => Promise.reject(new Error('capacity offline')),
      },
    })
    failed.terminal.send('/model')
@@ -2569,7 +2582,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
      catalog: {
        providers: [{ id: 'deepseek', name: 'DeepSeek' }],
        models: [{ provider: 'deepseek', id: 'model-1', name: 'Model One' }],
-        resolveModelReasoning: () => Promise.reject(new Error('reasoning metadata offline')),
+        resolveModelInfo: () => Promise.reject(new Error('reasoning metadata offline')),
      },
    })
    reasoningFailed.terminal.send('/model')
@@ -2619,7 +2632,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
      catalog: {
        providers: [{ id: 'deepseek', name: 'DeepSeek' }],
        models: [],
-        resolveModelContext: () => context.promise,
+        resolveModelInfo: () => context.promise.then(value => ({ context: value })),
      },
    })
    await contextResult.controller.dispose()