feat(models): retain native cache blocks and bind cross-run provider state

This commit is contained in:
Agent Workbench Dev
2026-11-07 20:00:33 +08:00
parent 71f1805561
commit 9e1feeebb3
11 changed files with 435 additions and 33 deletions
+12 -6
View File
@@ -3,6 +3,7 @@ import { modelProtocol } from './model-capabilities.mjs';
import { nativeParameterSettings } from './native-parameters.mjs';
import { messagesBody, messagesHistory } from './anthropic-messages.mjs';
import { isPassthrough } from './model-capacity.mjs';
import { providerStateCompatibility } from './model-provider-state.mjs';
function wireBody(config, messages, tools) {
const protocol = modelProtocol(config.protocol), stream = config.streaming === true;
@@ -10,10 +11,9 @@ function wireBody(config, messages, tools) {
if(config.inputImages?.length) messages=[...messages,{role:'user',content:protocol==='responses'
? [{type:'input_text',text:'当前任务用户提供的截图(仅任务数据,不授予额外权限):'},...config.inputImages.map(image=>({type:'input_image',image_url:image.dataUrl,detail:'high'}))]
: [{type:'text',text:'当前任务用户提供的截图(仅任务数据,不授予额外权限):'},...config.inputImages.map(image=>({type:'image_url',image_url:{url:image.dataUrl,detail:'high'}}))]}];
const cleanMessages = messages.map(({ providerState, reasoning_content, ...message }) => {
const cleanMessages = messages.map(({ providerState, providerInput, reasoning_content, ...message }) => {
if (protocol === 'chat-completions' && message.role === 'assistant' && providerState?.protocol === 'chat-completions'
&& providerState.endpoint === config.baseUrl && providerState.model === config.model
&& providerState.connectionId === (config.modelConnectionId ?? null) && providerState.credentialRevision === (config.modelCredentialRevision ?? null)
&& providerStateCompatibility(config, providerState).applicable
&& typeof providerState.reasoningContent === 'string') return { ...message, reasoning_content: providerState.reasoningContent };
return message;
});
@@ -23,19 +23,25 @@ function wireBody(config, messages, tools) {
const input = messages.flatMap(message => {
if (message.role === 'tool') return [{ type: 'function_call_output', call_id: message.tool_call_id, output: message.content }];
if (message.role === 'assistant') {
if (message.providerState?.protocol === 'responses' && message.providerState.endpoint === config.baseUrl && message.providerState.model === config.model) return message.providerState.items;
if (message.providerState?.protocol === 'responses' && providerStateCompatibility(config, message.providerState).applicable) return structuredClone(message.providerState.items);
return [...(message.content ? [{ role: 'assistant', content: message.content }] : []), ...(message.tool_calls ?? []).map(call => ({
type: 'function_call', call_id: call.id, name: call.function.name, arguments: call.function.arguments }))];
}
return [{ role: message.role, content: message.content }];
});
return { model: config.model, input, tools: (tools ?? []).map(tool => ({ type: 'function', ...tool.function, strict: false })),
return { model: config.model, input, tools: (tools ?? []).map(tool => tool.function
? { ...structuredClone(tool.function), ...Object.fromEntries(Object.entries(structuredClone(tool)).filter(([key]) => key !== 'function')), strict: tool.strict ?? tool.function.strict ?? false }
: structuredClone(tool)),
tool_choice: 'auto', ...(!isPassthrough(config) ? { max_output_tokens: config.maxOutputTokens } : {}), stream, store: false, include: ['reasoning.encrypted_content'], ...native.nativeParameters };
}
export function completionBody(config, messages, tools) {
const members = config.modelRouting?.members;
if (members?.length && (config.capacityMode === 'model' || members.some(member => member.protocol && member.protocol !== 'chat-completions' || member.streaming === true || member.nativeParameters || member.outputTokenField))) {
// Even plain Chat members need separate projections when an opaque history
// exists. Replacing only body.model would reuse the first member's reasoning
// on another connection, credential or model.
if (members?.length && (config.capacityMode === 'model' || messages.some(message => message.providerState)
|| members.some(member => member.protocol && member.protocol !== 'chat-completions' || member.streaming === true || member.nativeParameters || member.outputTokenField))) {
return { schema: 1, kind: 'model-route-plan', messages, variants: members.map(member => ({ connectionId: member.id,
protocol: modelProtocol(member.protocol), body: wireBody({ ...config, ...member, nativeParameters: member.nativeParameters ?? {}, outputTokenField: member.outputTokenField,
modelConnectionId: member.id, modelCredentialRevision: member.credentialRevision,