Merge remote-tracking branch 'origin/master' into worktree/web-multimodal-image-input
# Conflicts: # docs/architecture.i18n.yaml # docs/architecture.md # docs/architecture.zh.md # docs/config-catalog.md # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/llm-streaming.i18n.yaml # docs/module-graph.md # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # packages/README.i18n.yaml # packages/client/connection/src/client/fixture.ts # packages/client/connection/src/index.ts # packages/client/runtime/README.i18n.yaml # packages/client/runtime/README.md # packages/client/runtime/README.zh.md # packages/client/runtime/src/client/sessions/conversation.ts # packages/client/ui-conversation/README.i18n.yaml # packages/client/ui-conversation/src/client/apply.ts # packages/client/ui-conversation/src/client/chat/ChatView.tsx # packages/client/ui-conversation/src/client/chat/MessageItem.tsx # packages/client/ui-conversation/src/client/contract/slots.ts # packages/client/ui-trajectory/tests/views.spec.tsx # packages/compact/compact-basic/README.i18n.yaml # packages/cordis/tool-cordis/src/api-catalog.ts # packages/host/apiproxy/src/api-proxy.ts # packages/host/apiproxy/src/api/index.ts # packages/host/apiproxy/src/api/sessions.ts # packages/host/apiproxy/src/index.ts # packages/host/apiproxy/tests/fetch-carrier.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-deepseek/tests/adapter.spec.ts # packages/llm/llm-deepseek/tests/serialize.spec.ts # packages/llm/llm-pi-ai/README.i18n.yaml # packages/llm/llm-pi-ai/src/adapter.ts # packages/llm/llm-pi-ai/src/index.ts # packages/llm/llm-pi-ai/tests/adapter.spec.ts # packages/llm/llm/src/types.ts # packages/ui/tui/README.i18n.yaml # packages/ui/tui/src/index.ts # packages/ui/tui/tests/tui.spec.ts
This commit is contained in:
Yichen Jiang
@@ -7,14 +7,29 @@
|
||||
import { streamSimple } from '@earendil-works/pi-ai/compat'
|
||||
import { getBuiltinModels } from '@earendil-works/pi-ai/providers/all'
|
||||
import type { BuiltinProvider } from '@earendil-works/pi-ai/providers/all'
|
||||
import { getSupportedThinkingLevels } from '@earendil-works/pi-ai'
|
||||
import type {
|
||||
Api,
|
||||
Model,
|
||||
ModelThinkingLevel,
|
||||
SimpleStreamOptions,
|
||||
ThinkingLevel,
|
||||
} from '@earendil-works/pi-ai'
|
||||
import type { AttachmentStore } from '@deepseek-ai/dsh-attachment'
|
||||
import { attributionHeaders, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm'
|
||||
import type { GenerateOptions, LlmModelContext, LlmModelInfo, StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import {
|
||||
attributionHeaders,
|
||||
LlmAdapter,
|
||||
LlmError,
|
||||
ReasoningEffortId,
|
||||
} from '@deepseek-ai/dsh-llm'
|
||||
import type {
|
||||
GenerateOptions,
|
||||
LlmModelInfo,
|
||||
LlmResolvedModelInfo,
|
||||
ReasoningEffortId as ReasoningEffortIdType,
|
||||
ResolvedRetryPolicy,
|
||||
StreamChunk,
|
||||
} from '@deepseek-ai/dsh-llm'
|
||||
import { idleWatchdog, timeoutOf } from '@deepseek-ai/dsh-timeout'
|
||||
import { resolveProfiles } from './config.ts'
|
||||
import type { PiAiProviderProfile, ResolvedPiAiProviderProfile } from './config.ts'
|
||||
@@ -33,7 +48,10 @@ export interface PiAiAdapterOptions {
|
||||
* Resolve a catalog model dynamically and apply only the configured endpoint
|
||||
* override, preserving the catalog's API/capability/compatibility metadata.
|
||||
*/
|
||||
function resolveModel(profile: PiAiProviderProfile, modelId: string): Model<Api> {
|
||||
function resolvePiModel(
|
||||
profile: Omit<PiAiProviderProfile, 'retryPolicy'>,
|
||||
modelId: string,
|
||||
): Model<Api> {
|
||||
const model = getBuiltinModels(profile.provider as BuiltinProvider).find(candidate => candidate.id === modelId) as Model<Api> | undefined
|
||||
if (model === undefined) {
|
||||
throw new LlmError(`pi-ai provider "${profile.provider}" has no catalog model "${modelId}"`, 'UNKNOWN_MODEL')
|
||||
@@ -42,10 +60,14 @@ function resolveModel(profile: PiAiProviderProfile, modelId: string): Model<Api>
|
||||
}
|
||||
|
||||
/** Copy profile stream knobs into pi-ai's common option vocabulary. */
|
||||
function profileOptions(profile: PiAiProviderProfile): SimpleStreamOptions {
|
||||
function profileOptions(
|
||||
profile: Omit<PiAiProviderProfile, 'retryPolicy'>,
|
||||
reasoning: ModelThinkingLevel | undefined,
|
||||
): SimpleStreamOptions {
|
||||
const enabledReasoning: ThinkingLevel | undefined = reasoning === 'off' ? undefined : reasoning
|
||||
return {
|
||||
...profile.apiKey === undefined ? {} : { apiKey: profile.apiKey },
|
||||
...profile.reasoning === undefined ? {} : { reasoning: profile.reasoning },
|
||||
...enabledReasoning === undefined ? {} : { reasoning: enabledReasoning },
|
||||
...profile.thinkingBudgets === undefined ? {} : { thinkingBudgets: profile.thinkingBudgets },
|
||||
...profile.cacheRetention === undefined ? {} : { cacheRetention: profile.cacheRetention },
|
||||
...profile.transport === undefined ? {} : { transport: profile.transport },
|
||||
@@ -56,6 +78,20 @@ function profileOptions(profile: PiAiProviderProfile): SimpleStreamOptions {
|
||||
}
|
||||
}
|
||||
|
||||
/** Validate an explicit Harness/profile effort without invoking pi-ai's clamp. */
|
||||
function resolveReasoningLevel(
|
||||
model: Model<Api>,
|
||||
effort: ReasoningEffortIdType | ModelThinkingLevel | undefined,
|
||||
): ModelThinkingLevel | undefined {
|
||||
if (effort === undefined) return undefined
|
||||
const supported = getSupportedThinkingLevels(model)
|
||||
if (supported.some(level => level === effort)) return effort as ModelThinkingLevel
|
||||
throw new LlmError(
|
||||
`pi-ai provider "${model.provider}" model "${model.id}" does not support reasoning effort "${effort}"`,
|
||||
'UNSUPPORTED_REASONING_EFFORT',
|
||||
)
|
||||
}
|
||||
|
||||
/** Merge deployment headers while removing case-insensitive attribution collisions. */
|
||||
function requestHeaders(headers: Readonly<Record<string, string>> | undefined): Record<string, string> {
|
||||
const attribution = attributionHeaders()
|
||||
@@ -80,6 +116,10 @@ export class PiAiAdapter extends LlmAdapter {
|
||||
this.resolveAttachments = options.resolveAttachments ?? (() => undefined)
|
||||
}
|
||||
|
||||
override providerRetryPolicy(provider: string): ResolvedRetryPolicy | undefined {
|
||||
return this.profiles.get(provider)?.retryPolicy
|
||||
}
|
||||
|
||||
override listModels(provider: string): Promise<readonly LlmModelInfo[]> {
|
||||
const profile = this.profiles.get(provider)
|
||||
if (profile === undefined) {
|
||||
@@ -94,10 +134,11 @@ export class PiAiAdapter extends LlmAdapter {
|
||||
})))
|
||||
}
|
||||
|
||||
override resolveModelContext(
|
||||
override resolveModel(
|
||||
provider: string,
|
||||
model: string,
|
||||
): Promise<LlmModelContext | undefined> {
|
||||
_signal?: AbortSignal,
|
||||
): Promise<LlmResolvedModelInfo> {
|
||||
const profile = this.profiles.get(provider)
|
||||
if (profile === undefined) {
|
||||
return Promise.reject(new LlmError(
|
||||
@@ -105,9 +146,28 @@ export class PiAiAdapter extends LlmAdapter {
|
||||
'NO_ADAPTER',
|
||||
))
|
||||
}
|
||||
return Promise.resolve().then(() => ({
|
||||
contextWindow: resolveModel(profile, model).contextWindow,
|
||||
}))
|
||||
return Promise.resolve().then(() => {
|
||||
const resolvedModel = resolvePiModel(profile, model)
|
||||
const levels = getSupportedThinkingLevels(resolvedModel)
|
||||
const defaultLevel = resolveReasoningLevel(resolvedModel, profile.reasoning)
|
||||
return {
|
||||
provider,
|
||||
id: model,
|
||||
name: resolvedModel.name,
|
||||
inputModalities: [...resolvedModel.input],
|
||||
outputModalities: ['text'],
|
||||
context: { contextWindow: resolvedModel.contextWindow },
|
||||
reasoning: {
|
||||
efforts: levels.map(level => ({
|
||||
id: ReasoningEffortId(level),
|
||||
name: `${level.charAt(0).toUpperCase()}${level.slice(1)}`,
|
||||
})),
|
||||
...defaultLevel === undefined
|
||||
? {}
|
||||
: { defaultEffort: ReasoningEffortId(defaultLevel) },
|
||||
},
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
@@ -118,7 +178,11 @@ export class PiAiAdapter extends LlmAdapter {
|
||||
if (profile === undefined) {
|
||||
throw new LlmError(`pi-ai adapter does not own provider "${options.provider}"`, 'NO_ADAPTER')
|
||||
}
|
||||
const model = resolveModel(profile, options.model)
|
||||
const model = resolvePiModel(profile, options.model)
|
||||
const reasoning = resolveReasoningLevel(
|
||||
model,
|
||||
options.reasoningEffort ?? profile.reasoning,
|
||||
)
|
||||
const consumer = new AbortController()
|
||||
const upstream = options.signal === undefined
|
||||
? consumer.signal
|
||||
@@ -144,7 +208,7 @@ export class PiAiAdapter extends LlmAdapter {
|
||||
? toPiContext(options)
|
||||
: await toPiContext(options, attachments)
|
||||
const events = streamSimple(model, context, {
|
||||
...profileOptions(profile),
|
||||
...profileOptions(profile, reasoning),
|
||||
...options.temperature === undefined ? {} : { temperature: options.temperature },
|
||||
...options.maxTokens === undefined ? {} : { maxTokens: options.maxTokens },
|
||||
...options.sessionId === undefined ? {} : { sessionId: String(options.sessionId) },
|
||||
|
||||
Reference in New Issue
Block a user