Merge remote-tracking branch 'origin/master' into xtr/react-loop-simplification
# Conflicts: # .agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml # .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml # .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md # .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md # .agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml # .agents/notes/implemented/feature/2026-07-06-sandbox.md # .agents/notes/implemented/feature/2026-07-06-sandbox.zh.md # .agents/notes/implemented/feature/2026-07-27-tmux-location-context.i18n.yaml # .agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.i18n.yaml # .agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.i18n.yaml # .agents/notes/implemented/simplification/2026-07-30-private-agent-send.i18n.yaml # docs/architecture.i18n.yaml # docs/architecture.md # docs/architecture.zh.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/compaction.i18n.yaml # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/core.md # docs/core-data-structures/core.zh.md # docs/core-data-structures/llm-streaming.i18n.yaml # docs/core-data-structures/llm-streaming.md # docs/core-data-structures/llm-streaming.zh.md # docs/core-data-structures/session.i18n.yaml # docs/event-producer-consumer.md # docs/module-graph.md # docs/persistence-catalog.md # examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl # examples/acp-agent/tests/snapshots/bash-spill/session.jsonl # examples/acp-agent/tests/snapshots/bash-tool-turn/session.jsonl # examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl # examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl # examples/acp-agent/tests/snapshots/cancel/session.jsonl # examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl # examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl # examples/acp-agent/tests/snapshots/error-finish/session.jsonl # examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl # examples/acp-agent/tests/snapshots/fs-edit/session.jsonl # examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl # examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl # examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl # examples/acp-agent/tests/snapshots/fs-read/session.jsonl # examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl # examples/acp-agent/tests/snapshots/fs-write/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-invalid-matcher/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-invalid-matcher/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl # examples/acp-agent/tests/snapshots/lsp-definition/session.jsonl # examples/acp-agent/tests/snapshots/multi-turn/session.jsonl # examples/acp-agent/tests/snapshots/packed-chunks/session.jsonl # examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl # examples/acp-agent/tests/snapshots/pty-tools/session.jsonl # examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl # examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl # examples/acp-agent/tests/snapshots/session-sandbox-root/session.jsonl # examples/acp-agent/tests/snapshots/session-title-after-turn/session.jsonl # examples/acp-agent/tests/snapshots/skill-load/session.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl # examples/acp-agent/tests/snapshots/text-turn/session.jsonl # examples/acp-agent/tests/snapshots/todo-write/session.jsonl # examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl # examples/acp-agent/tests/snapshots/web-fetch/session.jsonl # examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl # examples/acp-agent/tests/snapshots/workflow-run/session.jsonl # examples/acp-agent/tests/snapshots/workspace-context/session.jsonl # examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl # examples/headless-agent/tests/semantic-checkpoint-snapshots/tool-outcome-unknown/session.expected.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/missing-credential/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/provider-retry/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/pty-tools/session.jsonl # examples/headless-agent/tests/snapshots/pty-tools/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/ralph-loop/stream-json.expected.jsonl # examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl # examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/parent.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/bash-tool/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/bash-tool/session.jsonl # examples/jsonrpc-agent/tests/snapshots/persistent-tools/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/persistent-tools/session.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.1.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.jsonl # examples/jsonrpc-agent/tests/snapshots/text-turn/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/text-turn/session.jsonl # packages/client/runtime/README.i18n.yaml # packages/client/runtime/src/client/sessions/request-inspection.ts # packages/compact/compact-basic/README.i18n.yaml # packages/compact/compact-basic/README.md # packages/compact/compact-basic/README.zh.md # packages/compact/compact-basic/src/index.ts # packages/context/time-context/tests/time-context.spec.ts # packages/context/tmux-context/README.i18n.yaml # packages/context/tmux-context/tests/tmux-context.spec.ts # packages/context/workspace-context/tests/workspace-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/README.i18n.yaml # packages/core/agent-loop/README.md # packages/core/agent-loop/README.zh.md # packages/core/agent-loop/src/agent.ts # packages/core/agent/README.i18n.yaml # packages/core/agent/README.md # packages/core/agent/README.zh.md # packages/core/agent/src/types.ts # packages/core/session/README.i18n.yaml # packages/core/session/README.md # packages/core/session/README.zh.md # packages/fs/tool-str-replace-editor/tests/tools.spec.ts # packages/goal/command-goal/tests/command-goal.spec.ts # packages/goal/goal/tests/goal.spec.ts # packages/host/apiproxy/README.i18n.yaml # packages/host/apiproxy/README.md # packages/host/apiproxy/README.zh.md # packages/host/apiproxy/src/api/index.ts # packages/host/apiproxy/tests/api-proxy-workspace.spec.ts # packages/llm/llm/README.i18n.yaml # packages/llm/llm/README.md # packages/llm/llm/README.zh.md # packages/llm/llm/src/index.ts # packages/pty/pty-local/tests/index.spec.ts # packages/pty/pty-local/tests/local.spec.ts # packages/pty/pty/tests/service.spec.ts # packages/pty/tool-bash-persistent/tests/loader-composition.spec.ts # packages/pty/tool-bash-persistent/tests/tools.spec.ts # packages/pty/tool-pty/tests/loader-composition.spec.ts # packages/pty/tool-pty/tests/tools.spec.ts # packages/session-persistence/session-checkpoint-policy/tests/crash-recovery.e2e.ts # packages/skill/tool-skill/tests/tool-skill.spec.ts # packages/tasks/tasks-local/tests/tasks.spec.ts # packages/ui/tui/README.i18n.yaml # packages/ui/tui/tests/tui.spec.ts # packages/ui/user-approval/src/index.ts # packages/ui/user-approval/tests/approval.spec.ts
This commit is contained in:
_Kerman
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/llm/llm/README.md
|
||||
README.md: 31daf348430d6bf5ee241f5b32ff4c2458defae2
|
||||
README.zh.md: a9dd24fdd7c62c01a5e924539afdaa0e6086f013
|
||||
README.md: 5d74ed647f4de3c8ed65554dff736eb8aec9eef9
|
||||
README.zh.md: 354dd754145e38551646b709d467533d3f4d42a8
|
||||
|
||||
@@ -18,7 +18,7 @@ An adapter registry plus a single streaming call surface, interceptable via a wa
|
||||
- `ctx.llm.listModels(provider: string): Promise<LlmModelInfo[]>` Discover the models one registered provider currently advertises.
|
||||
- `ctx.llm.resolveModelInfo(provider: string, model: string, signal?: AbortSignal): Promise<LlmResolvedModelInfo>` Resolve validated exact-model identity plus available context, output-default, and reasoning metadata from the owning adapter, with optional cancellation for asynchronous adapters.
|
||||
- `ctx.llm.resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<LlmCallConfig>` Validate an explicit effort and materialize adapter-configured call defaults without clamping.
|
||||
- `ctx.llm.prepareCall(config: LlmCallConfig, signal?: AbortSignal): Promise<PreparedLlmCall>` Resolve a config and capture its current adapter registration plus immutable retry policy as one cancellable, one-shot call.
|
||||
- `ctx.llm.prepareCall(config: LlmCallConfig, signal?: AbortSignal): Promise<PreparedLlmCall>` Resolve a config plus detached context metadata and adapter-default provenance in one exact-model lookup, then capture its current adapter registration and immutable retry policy as one cancellable, one-shot call.
|
||||
- `ctx.llm.stream(options: GenerateOptions): AsyncIterable<StreamChunk>` Stream one model call as raw chunks (token-level deltas). Consumers assemble the chunks into blocks/messages with `BlockAssembler`.
|
||||
|
||||
`LlmService` normalizes failures from final adapter selection, synchronous dispatch, iterator construction, and iteration into the stream protocol's single terminal form: `finish { kind: 'error' | 'aborted', failure }`. A failure after partial deltas may leave content blocks open; consumers discard that incomplete output. Errors from `llm/stream` middleware, nested calls, adapter cleanup, and downstream consumers remain thrown because they are plugin or consumer failures rather than model-request outcomes. A prepared call exposes the immutable retry policy captured with its exact adapter registration; a route handled entirely by middleware has no serving policy.
|
||||
@@ -29,7 +29,7 @@ Every topology commit point — adapter routes registering or disposing, directo
|
||||
|
||||
Exact-model metadata is a separate correctness query, not a catalog decoration or global LLM setting. `resolveModelInfo()` asks the adapter that owns the exact provider/model route once; an adapter can describe an unlisted dynamic model, and absent `context`, `defaultMaxTokens`, or `reasoning` fields preserve unknown capacity, provider-owned output defaults, or unavailable reasoning capability. Invalid identity, context, output default, or reasoning metadata fails with `INVALID_MODEL_INFO`, `INVALID_MODEL_CONTEXT`, `INVALID_MODEL_MAX_TOKENS`, or `INVALID_MODEL_REASONING`.
|
||||
|
||||
`defaultMaxTokens` is an adapter-configured per-request output cap, not a model hard limit. `resolveCallConfig()` materializes it only when the request omits `maxTokens`; an explicit cap wins. Reasoning identifiers are opaque adapter-owned strings rather than a core enum: the same resolution accepts only an exact advertised identifier, materializes `defaultEffort` when present, and otherwise preserves the provider default. Asynchronous model resolvers receive the caller's signal and must settle promptly after cancellation. `prepareCall()` additionally reports which `maxTokens` and `reasoningEffort` fields it materialized in `adapterDefaults` and retains the exact adapter registration through header logging and terminal dispatch, so HMR cannot combine one adapter's capability result with another adapter's request; reusing its one-shot handle or changing its call-config fields fails with `INVALID_PREPARED_CALL`. An unsupported explicit or configured effort fails with `UNSUPPORTED_REASONING_EFFORT` before provider I/O.
|
||||
`defaultMaxTokens` is an adapter-configured per-request output cap, not a model hard limit. `resolveCallConfig()` materializes it only when the request omits `maxTokens`; an explicit cap wins. Reasoning identifiers are opaque adapter-owned strings rather than a core enum: the same resolution accepts only an exact advertised identifier, materializes `defaultEffort` when present, and otherwise preserves the provider default. Asynchronous model resolvers receive the caller's signal and must settle promptly after cancellation. `prepareCall()` additionally exposes detached context metadata from the same lookup, reports which `maxTokens` and `reasoningEffort` fields it materialized in `adapterDefaults`, and retains the exact adapter registration through header logging and terminal dispatch, so HMR cannot combine one adapter's capability result with another adapter's request; reusing its one-shot handle or changing its call-config fields fails with `INVALID_PREPARED_CALL`. An unsupported explicit or configured effort fails with `UNSUPPORTED_REASONING_EFFORT` before provider I/O.
|
||||
|
||||
### Events
|
||||
|
||||
|
||||
@@ -18,7 +18,7 @@
|
||||
- `ctx.llm.listModels(provider: string): Promise<LlmModelInfo[]>` 发现某个已注册提供方当前公布的模型。
|
||||
- `ctx.llm.resolveModelInfo(provider: string, model: string, signal?: AbortSignal): Promise<LlmResolvedModelInfo>` 从拥有精确路由的适配器解析经校验的确切模型身份，以及可用上下文、输出默认值和推理（reasoning）元数据；异步适配器可选地支持取消。
|
||||
- `ctx.llm.resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<LlmCallConfig>` 校验显式推理强度，并填入适配器配置的调用默认值，但不自动调整。
|
||||
- `ctx.llm.prepareCall(config: LlmCallConfig, signal?: AbortSignal): Promise<PreparedLlmCall>` 解析配置，并将当前适配器注册及不可变重试策略捕获为一次可取消、一次性调用。
|
||||
- `ctx.llm.prepareCall(config: LlmCallConfig, signal?: AbortSignal): Promise<PreparedLlmCall>` 在一次精确模型查询中解析配置、脱耦的上下文元数据与适配器默认值溯源，再将当前适配器注册和不可变重试策略捕获为一次可取消、一次性调用。
|
||||
- `ctx.llm.stream(options: GenerateOptions): AsyncIterable<StreamChunk>` 将一次模型调用流式输出为原始分片（token 级增量）。消费方使用 `BlockAssembler` 将分片组装为块／消息。
|
||||
|
||||
`LlmService` 将最终适配器选择、同步 dispatch、iterator 构造与迭代中的失败规范化为流协议唯一的终止形式：`finish { kind: 'error' | 'aborted', failure }`。部分增量输出后发生失败时，内容块可能仍未闭合；消费方会丢弃这些不完整输出。`llm/stream` middleware、嵌套调用、适配器清理和下游消费方的错误仍会抛出，因为它们属于插件或消费方失败，而非模型请求结果。已准备调用会暴露随其确切适配器注册一同捕获的不可变重试策略；完全由 middleware 处理的路由没有服务策略。
|
||||
@@ -29,7 +29,7 @@
|
||||
|
||||
确切模型元数据是独立的正确性查询，不是 catalog 装饰或全局 LLM 设置。`resolveModelInfo()` 会向拥有精确提供方／模型路由的适配器查询一次；适配器可以描述未列出的动态模型，缺少 `context`、`defaultMaxTokens` 或 `reasoning` 字段会分别保留未知容量、提供方持有的输出默认值或不可用的推理能力。无效的身份、上下文、输出默认值或推理元数据会以 `INVALID_MODEL_INFO`、`INVALID_MODEL_CONTEXT`、`INVALID_MODEL_MAX_TOKENS` 或 `INVALID_MODEL_REASONING` 失败。
|
||||
|
||||
`defaultMaxTokens` 是适配器配置的单次请求输出上限，不是模型硬上限。仅当请求省略 `maxTokens` 时，`resolveCallConfig()` 才会填入该值；显式上限优先。推理标识符是由适配器持有的不透明字符串，而非核心枚举：同一次解析只接受与已公布标识符完全一致的值，在存在 `defaultEffort` 时填入它，否则保留提供方默认值。异步模型解析器会接收调用方的 signal，并且必须在取消后迅速结束。`prepareCall()` 还会通过 `adapterDefaults` 报告它填入了哪些 `maxTokens` 和 `reasoningEffort` 字段，并让精确适配器注册跨越请求头记录和最终分派，因此 HMR（热模块替换）不会将一个适配器的能力结果与另一个适配器的请求混用；复用其一次性句柄或更改调用配置字段会以 `INVALID_PREPARED_CALL` 失败。不支持的显式或配置推理强度会在提供方 I/O 前以 `UNSUPPORTED_REASONING_EFFORT` 失败。
|
||||
`defaultMaxTokens` 是适配器配置的单次请求输出上限，不是模型硬上限。仅当请求省略 `maxTokens` 时，`resolveCallConfig()` 才会填入该值；显式上限优先。推理标识符是由适配器持有的不透明字符串，而非核心枚举：同一次解析只接受与已公布标识符完全一致的值，在存在 `defaultEffort` 时填入它，否则保留提供方默认值。异步模型解析器会接收调用方的 signal，并且必须在取消后迅速结束。`prepareCall()` 还会公开同一次查询得到的脱耦上下文元数据，通过 `adapterDefaults` 报告它填入了哪些 `maxTokens` 和 `reasoningEffort` 字段，并让精确适配器注册跨越请求头记录和最终分派，因此 HMR（热模块替换）不会将一个适配器的能力结果与另一个适配器的请求混用；复用其一次性句柄或更改调用配置字段会以 `INVALID_PREPARED_CALL` 失败。不支持的显式或配置推理强度会在提供方 I/O 前以 `UNSUPPORTED_REASONING_EFFORT` 失败。
|
||||
|
||||
### 事件
|
||||
|
||||
|
||||
@@ -11,6 +11,7 @@ import type {
|
||||
GenerateOptions,
|
||||
LlmConfigurableProvider,
|
||||
LlmFailure,
|
||||
LlmModelContext,
|
||||
LlmModelInfo,
|
||||
LlmResolvedModelInfo,
|
||||
LlmProviderInfo,
|
||||
@@ -125,6 +126,8 @@ export interface PreparedLlmCall {
|
||||
readonly config: LlmCallConfig
|
||||
/** Immutable retry policy captured with the adapter registration. */
|
||||
readonly retryPolicy: ResolvedRetryPolicy
|
||||
/** Detached context metadata resolved with the registration-bound call. */
|
||||
readonly context?: LlmModelContext
|
||||
/** Config fields materialized by the captured adapter rather than proposed by the caller. */
|
||||
readonly adapterDefaults: LlmCallConfigAdapterDefaults
|
||||
/**
|
||||
@@ -564,20 +567,21 @@ export class LlmService extends Service {
|
||||
* @returns a detached config only when a default must be materialized.
|
||||
*/
|
||||
async resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<LlmCallConfig> {
|
||||
return this.resolveCallConfigFor(this.registration(config.provider), config, signal)
|
||||
return (await this.resolveCallFor(this.registration(config.provider), config, signal)).config
|
||||
}
|
||||
|
||||
private async resolveCallConfigFor(
|
||||
private async resolveCallFor(
|
||||
registration: AdapterRegistration,
|
||||
config: LlmCallConfig,
|
||||
signal?: AbortSignal,
|
||||
): Promise<LlmCallConfig> {
|
||||
): Promise<{ config: LlmCallConfig; context?: LlmModelContext }> {
|
||||
const info = await this.resolveModelInfoFor(registration, config.model, signal)
|
||||
const defaulted = config.maxTokens === undefined && info.defaultMaxTokens !== undefined
|
||||
? { ...config, maxTokens: info.defaultMaxTokens }
|
||||
: config
|
||||
const reasoning = info.reasoning
|
||||
const requested = defaulted.reasoningEffort
|
||||
let resolvedConfig = defaulted
|
||||
if (reasoning === undefined) {
|
||||
if (requested !== undefined) {
|
||||
throw new LlmError(
|
||||
@@ -585,17 +589,22 @@ export class LlmService extends Service {
|
||||
'UNSUPPORTED_REASONING_EFFORT',
|
||||
)
|
||||
}
|
||||
return defaulted
|
||||
} else {
|
||||
const effective = requested ?? reasoning.defaultEffort
|
||||
if (effective !== undefined) {
|
||||
if (!reasoning.efforts.some(effort => effort.id === effective)) {
|
||||
throw new LlmError(
|
||||
`provider "${config.provider}" model "${config.model}" does not support reasoning effort "${effective}"`,
|
||||
'UNSUPPORTED_REASONING_EFFORT',
|
||||
)
|
||||
}
|
||||
if (requested !== effective) resolvedConfig = { ...defaulted, reasoningEffort: effective }
|
||||
}
|
||||
}
|
||||
const effective = requested ?? reasoning.defaultEffort
|
||||
if (effective === undefined) return defaulted
|
||||
if (!reasoning.efforts.some(effort => effort.id === effective)) {
|
||||
throw new LlmError(
|
||||
`provider "${config.provider}" model "${config.model}" does not support reasoning effort "${effective}"`,
|
||||
'UNSUPPORTED_REASONING_EFFORT',
|
||||
)
|
||||
return {
|
||||
config: resolvedConfig,
|
||||
...info.context === undefined ? {} : { context: info.context },
|
||||
}
|
||||
return requested === effective ? defaulted : { ...defaulted, reasoningEffort: effective }
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -608,13 +617,16 @@ export class LlmService extends Service {
|
||||
*/
|
||||
async prepareCall(config: LlmCallConfig, signal?: AbortSignal): Promise<PreparedLlmCall> {
|
||||
const registration = this.registration(config.provider)
|
||||
const resolved = await this.resolveCallConfigFor(registration, config, signal)
|
||||
const resolvedConfig = deepFreeze(structuredClone(resolved))
|
||||
const resolved = await this.resolveCallFor(registration, config, signal)
|
||||
const resolvedConfig = deepFreeze(structuredClone(resolved.config))
|
||||
const context = resolved.context === undefined
|
||||
? undefined
|
||||
: deepFreeze(structuredClone(resolved.context))
|
||||
const adapterDefaults = deepFreeze<LlmCallConfigAdapterDefaults>({
|
||||
...config.reasoningEffort === undefined && resolved.reasoningEffort !== undefined
|
||||
...config.reasoningEffort === undefined && resolvedConfig.reasoningEffort !== undefined
|
||||
? { reasoningEffort: true }
|
||||
: {},
|
||||
...config.maxTokens === undefined && resolved.maxTokens !== undefined
|
||||
...config.maxTokens === undefined && resolvedConfig.maxTokens !== undefined
|
||||
? { maxTokens: true }
|
||||
: {},
|
||||
})
|
||||
@@ -623,6 +635,7 @@ export class LlmService extends Service {
|
||||
config: resolvedConfig,
|
||||
retryPolicy: registration.retryPolicy,
|
||||
adapterDefaults,
|
||||
...context === undefined ? {} : { context },
|
||||
stream: (options: GenerateOptions): AsyncIterable<StreamChunk> => {
|
||||
if (dispatched) {
|
||||
throw new LlmError('a prepared LLM call can only be dispatched once', 'INVALID_PREPARED_CALL')
|
||||
@@ -674,9 +687,15 @@ export class LlmService extends Service {
|
||||
try {
|
||||
const registration = prepared?.registration ?? this.registration(options.provider)
|
||||
const resolvedConfig = prepared === undefined
|
||||
? await this.resolveCallConfigFor(registration, options, options.signal)
|
||||
? (await this.resolveCallFor(registration, options, options.signal)).config
|
||||
: prepared.config
|
||||
const resolvedOptions = prepared !== undefined || callConfigEquals(options, resolvedConfig)
|
||||
if (prepared !== undefined && !callConfigEquals(options, resolvedConfig)) {
|
||||
throw new LlmError(
|
||||
'prepared LLM call config changed before adapter dispatch',
|
||||
'INVALID_PREPARED_CALL',
|
||||
)
|
||||
}
|
||||
const resolvedOptions = callConfigEquals(options, resolvedConfig)
|
||||
? options
|
||||
: Object.isFrozen(options)
|
||||
? deepFreeze({ ...options, ...resolvedConfig })
|
||||
|
||||
@@ -837,6 +837,48 @@ describe('LlmService', () => {
|
||||
})).toThrow(expect.objectContaining({ code: 'INVALID_PREPARED_CALL' }))
|
||||
})
|
||||
|
||||
it('reuses one exact-model lookup for prepared config and context metadata', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
let resolutions = 0
|
||||
const source = { contextWindow: 128_000 }
|
||||
const adapter = new class extends ScriptedAdapter {
|
||||
override resolveModel(provider: string, model: string): Promise<LlmResolvedModelInfo> {
|
||||
resolutions += 1
|
||||
return Promise.resolve({
|
||||
provider,
|
||||
id: model,
|
||||
name: model,
|
||||
description: 'Resolved model',
|
||||
context: source,
|
||||
reasoning: model === 'no-default'
|
||||
? { efforts: [{ id: ReasoningEffortId('high'), name: 'High' }] }
|
||||
: {
|
||||
efforts: [{ id: ReasoningEffortId('high'), name: 'High' }],
|
||||
defaultEffort: ReasoningEffortId('high'),
|
||||
},
|
||||
})
|
||||
}
|
||||
}(SCRIPT)
|
||||
ctx.llm.registerAdapter(['route'], adapter)
|
||||
|
||||
const prepared = await ctx.llm.prepareCall({ provider: 'route', model: 'model' })
|
||||
source.contextWindow = 64_000
|
||||
expect(prepared.config.reasoningEffort).toBe(ReasoningEffortId('high'))
|
||||
expect(prepared.context).toEqual({ contextWindow: 128_000 })
|
||||
expect(Object.isFrozen(prepared.context)).toBe(true)
|
||||
for await (const _chunk of prepared.stream({
|
||||
...prepared.config,
|
||||
messages: [],
|
||||
})) { /* drain */ }
|
||||
expect(resolutions).toBe(1)
|
||||
|
||||
const noDefault = await ctx.llm.prepareCall({ provider: 'route', model: 'no-default' })
|
||||
expect(noDefault.config).toEqual({ provider: 'route', model: 'no-default' })
|
||||
expect(noDefault.context).toEqual({ contextWindow: 64_000 })
|
||||
expect(resolutions).toBe(2)
|
||||
})
|
||||
|
||||
it('passes cancellation through exact-model resolution', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
|
||||
Reference in New Issue
Block a user