Add skill governance and runtime routing

This commit is contained in:
dahyeon committed 2026-05-14 14:28:59 -07:00
1 parent a900016be4
commit 221e9391e0
71 files changed
+7057 -102

No files matched your search

+129 -7
View File
@@ -1,8 +1,11 @@
import { getContext, getRequestLogger } from "@obs/context";
import type { AgentRequest } from "@agent/types";
import type { LlmClient } from "@llm/llm-client";
import type { ChatMessage } from "@llm/types";
import type { Tool, ToolContext } from "@tools/tool";
import {
getAgentCriticMaxIterations,
getAgentProgrammaticToolCalling,
getLlmTemperature,
getPlannerMaxTokens,
getTier0EstimatedCallMs,
@@ -16,14 +19,17 @@ import {
getTier2MaxTokens,
} from "../../../config.js";
import type { DerivedState } from "../state/onboarding-state.js";
import { buildSkillResourceAddendum } from "../prompts/builder.js";
import { OnboardingCritic } from "./critic.js";
import type { PlannerOutput } from "./planner-schema.js";
import { PlannerOutputSchema } from "./planner-schema.js";
import { getActiveProcessTrace } from "./trace.js";
import { runToolPlan, type ToolPlanResult } from "./tool-plan-runner.js";
import { runWithTools } from "./tool-loop.js";
export interface OrchestratorRunOptions {
maxTokens?: number | undefined;
request?: AgentRequest | undefined;
temperature?: number | undefined;
toolContext: ToolContext;
tools?: readonly Tool<unknown, unknown>[] | undefined;
@@ -100,6 +106,7 @@ function getDefaultPlan(derived: DerivedState): PlannerOutput {
targetPhase: derived.phase.kind,
mustInclude: [],
mustAvoid: [],
requestResources: [],
suggestedTools:
derived.responseMode === "llm-with-tools" ? ["validate-nickname"] : [],
tone: derived.allowShortResponse ? "concise" : "friendly",
@@ -154,6 +161,22 @@ function buildPlannerMessages(
suggestedTools: [
"validate-nickname | check-onboarding-progress | lookup-community-rule | get-room-context | verify-discord-nickname",
],
requestResources: [
"nickname-format | heart-rule | discord-format | age-policy",
],
toolPlan: {
composeWith: "all-then-llm",
steps: [
{
id: "step-id",
tool: "validate-nickname",
argsLiteral: { nickname: "value" },
argsFromContext: { chatroomId: "$request.chatroomId" },
dependsOn: [],
on: { error: "fallback-llm" },
},
],
},
tone: "friendly | concise | encouraging | neutral | apologetic",
targetLengthChars: 150,
rationale: "short reason",
@@ -184,6 +207,23 @@ function buildResponderAddendum(plan: PlannerOutput): string {
return lines.join("\n");
}
function buildToolPlanAddendum(result: ToolPlanResult): string {
return [
"[TOOL_PLAN_RESULTS]",
JSON.stringify({
durationMs: result.durationMs,
failures: result.failures.map((failure) => ({
kind: failure.kind,
message: failure.message,
retryable: failure.retryable,
toolName: failure.toolName,
})),
results: result.results,
}),
"위 toolPlan 결과를 사실 정보로 사용하고, 실패한 도구 결과는 추측으로 메우지 마세요.",
].join("\n");
}
function pickToolsForPlan(
plan: PlannerOutput,
tools: readonly Tool<unknown, unknown>[],
@@ -237,6 +277,7 @@ export class OnboardingOrchestrator {
messages,
modelOverride,
role: "responder",
routingDecision: derived.routingDecision,
tier: derived.tier,
temperature: options.temperature ?? getLlmTemperature(),
toolContext: options.toolContext,
@@ -249,6 +290,7 @@ export class OnboardingOrchestrator {
maxTokens,
modelOverride,
role: "responder",
routingDecision: derived.routingDecision,
temperature: options.temperature ?? getLlmTemperature(),
tier: derived.tier,
});
@@ -267,8 +309,10 @@ export class OnboardingOrchestrator {
approach: plan.approach,
mustAvoid: plan.mustAvoid,
mustInclude: plan.mustInclude,
requestResources: plan.requestResources,
suggestedTools: plan.suggestedTools,
targetLengthChars: plan.targetLengthChars,
toolPlanStepCount: plan.toolPlan?.steps.length,
});
return plan;
};
@@ -279,6 +323,7 @@ export class OnboardingOrchestrator {
maxTokens: getPlannerMaxTokens(),
modelOverride: getTier1PlannerModel(),
role: "planner",
routingDecision: derived.routingDecision,
temperature: 0,
tier: 1,
});
@@ -313,6 +358,7 @@ export class OnboardingOrchestrator {
maxTokens: getPlannerMaxTokens(),
modelOverride: getTier1PlannerModel(),
role: "planner",
routingDecision: derived.routingDecision,
temperature: 0,
tier: 1,
});
@@ -372,11 +418,32 @@ export class OnboardingOrchestrator {
buildResponderAddendum(plan),
);
const forceTools = derived.responseMode === "llm-with-tools";
const responderTools = pickToolsForPlan(plan, options.tools ?? [], forceTools);
let finalResponderMessages = responderMessages;
let responderTools = pickToolsForPlan(plan, options.tools ?? [], forceTools);
const resourceAddendum = buildSkillResourceAddendum(plan.requestResources);
if (resourceAddendum) {
finalResponderMessages = injectSystemAddendum(
finalResponderMessages,
resourceAddendum,
);
}
const toolPlanResult = await this.runProgrammaticToolPlan(
plan,
finalResponderMessages,
options,
);
if (toolPlanResult && !toolPlanResult.fallbackToLlm) {
finalResponderMessages = injectSystemAddendum(
finalResponderMessages,
buildToolPlanAddendum(toolPlanResult),
);
responderTools = [];
}
return this.runDirect(
derived,
responderMessages,
finalResponderMessages,
options,
responderTools,
options.maxTokens ?? getTier1MaxTokens(),
@@ -395,11 +462,32 @@ export class OnboardingOrchestrator {
buildResponderAddendum(plan),
);
const forceTools = derived.responseMode === "llm-with-tools";
const responderTools = pickToolsForPlan(plan, options.tools ?? [], forceTools);
let finalResponderMessages = responderMessages;
let responderTools = pickToolsForPlan(plan, options.tools ?? [], forceTools);
const resourceAddendum = buildSkillResourceAddendum(plan.requestResources);
if (resourceAddendum) {
finalResponderMessages = injectSystemAddendum(
finalResponderMessages,
resourceAddendum,
);
}
const toolPlanResult = await this.runProgrammaticToolPlan(
plan,
finalResponderMessages,
options,
);
if (toolPlanResult && !toolPlanResult.fallbackToLlm) {
finalResponderMessages = injectSystemAddendum(
finalResponderMessages,
buildToolPlanAddendum(toolPlanResult),
);
responderTools = [];
}
const draft = await this.runDirect(
derived,
responderMessages,
finalResponderMessages,
options,
responderTools,
options.maxTokens ?? getTier2MaxTokens(),
@@ -410,12 +498,46 @@ export class OnboardingOrchestrator {
return null;
}
const critique = await this.critic.critique(draft, derived, responderMessages, {
deadlineMs: getRemainingDeadlineMs(),
});
const maxIterations = getAgentCriticMaxIterations();
const critique =
maxIterations > 1
? await this.critic.critiqueIterative(
draft,
derived,
finalResponderMessages,
{
deadlineMs: getRemainingDeadlineMs(),
maxIterations,
},
)
: await this.critic.critique(draft, derived, finalResponderMessages, {
deadlineMs: getRemainingDeadlineMs(),
});
return critique.text;
}
private async runProgrammaticToolPlan(
plan: PlannerOutput,
_messages: ChatMessage[],
options: OrchestratorRunOptions,
): Promise<ToolPlanResult | null> {
if (
!getAgentProgrammaticToolCalling() ||
!plan.toolPlan ||
!options.request ||
!options.tools?.length
) {
return null;
}
return runToolPlan(
plan.toolPlan,
options.tools,
options.toolContext,
options.request,
);
}
async run(
derived: DerivedState,
messages: ChatMessage[],