eve 0.78.0 → 0.79.0

package/dist/src/tracing/{local-trace-analysis.d.ts → local/trace-analysis.d.ts}

@@ -1,5 +1,5 @@
-import type { LocalTraceSpan } from "#tracing/local-trace-reader.js";
-import { type LocalTraceSummary } from "#tracing/local-trace-summary.js";
+import type { LocalTraceSpan } from "#tracing/local/trace-reader.js";
+import { type LocalTraceSummary } from "#tracing/local/trace-summary.js";
 interface TraceAnalysisSelector {
     readonly excludeSessionId?: string;
     readonly fromMs?: number;

package/dist/src/tracing/{local-trace-analysis.js → local/trace-analysis.js}

@@ -1 +1 @@
-import{summarizeLocalTrace}from"#tracing/local-trace-summary.js";import{localTraceOperations,traceModelName,traceSessionId,traceStringAttribute,traceToolName,uniqueLocalTraceSpans}from"#tracing/local-trace-operations.js";function analyzeLocalTrace(e,t,n={}){let r=uniqueLocalTraceSpans(t),i=new Map(localTraceOperations(r).map(({span:e})=>[e.spanId,e])),a=r.filter(e=>matches(i.get(e.spanId)??e,n)),o=a.reduce((e,t)=>t.startTimeNs<e?t.startTimeNs:e,a[0]?.startTimeNs??0n),s=localTraceOperations(a).map(e=>recordFor(e,o)).sort((e,t)=>e.startOffsetMs-t.startOffsetMs||e.endOffsetMs-t.endOffsetMs||e.spanId.localeCompare(t.spanId));return{summary:summarizeLocalTrace(e,a),groups:groups(s),modelWorkMs:sum(s,`model`),toolWorkMs:sum(s,`tool`),records:s}}function matches(e,t){let n=traceSessionId(e),r=traceStringAttribute(e,`agent.turn.id`);if(t.excludeSessionId!==void 0&&n===t.excludeSessionId||t.sessionId!==void 0&&n!==t.sessionId||t.turnId!==void 0&&r!==t.turnId)return!1;let i=Number(e.startTimeNs/1000000n);return(t.fromMs===void 0||i>=t.fromMs)&&(t.toMs===void 0||i<=t.toMs)}function recordFor(e,t){let{span:n,category:r}=e,i={category:r,durationMs:Number(n.endTimeNs-n.startTimeNs)/1e6,endOffsetMs:Number(n.endTimeNs-t)/1e6,outcome:n.statusCode===2?`failed`:`completed`,spanId:n.spanId,startOffsetMs:Number(n.startTimeNs-t)/1e6},a=traceStringAttribute(n,`gen_ai.tool.call.id`),o=traceModelName(n),s=traceSessionId(n),c=traceToolName(n),l=traceStringAttribute(n,`agent.turn.id`);if(a!==void 0&&(i.callId=a),n.statusMessage!==void 0&&(i.error=n.statusMessage),o!==void 0&&(i.model=o),n.parentSpanId!==void 0&&(i.parentSpanId=n.parentSpanId),s!==void 0&&(i.sessionId=s),c!==void 0&&r===`tool`&&(i.toolName=c),c!==void 0&&r===`other`&&(i.actionName=c),l!==void 0&&(i.turnId=l),e.actionDurationMs!==void 0&&(i.actionDurationMs=e.actionDurationMs),r===`model`){let e={};for(let[t,r]of Object.entries({inputTokens:`gen_ai.usage.input_tokens`,outputTokens:`gen_ai.usage.output_tokens`,cacheReadTokens:`gen_ai.usage.cache_read.input_tokens`,cacheWriteTokens:`gen_ai.usage.cache_write.input_tokens`})){let i=n.attributes[r];typeof i==`number`&&Number.isFinite(i)&&i>=0&&(e[t]=i)}Object.keys(e).length>0&&(i.usage=e)}return i}function groups(e){let t=new Map;for(let n of e){let e=JSON.stringify([n.sessionId,n.turnId]),r=t.get(e);r===void 0&&(r={modelCalls:0,modelWorkMs:0,toolCalls:0,toolWorkMs:0},n.sessionId!==void 0&&(r.sessionId=n.sessionId),n.turnId!==void 0&&(r.turnId=n.turnId),t.set(e,r)),n.category===`model`&&(r.modelCalls+=1,r.modelWorkMs+=n.durationMs),n.category===`tool`&&(r.toolCalls+=1,r.toolWorkMs+=n.durationMs)}return[...t.values()]}function sum(e,t){return e.reduce((e,n)=>e+(n.category===t?n.durationMs:0),0)}export{analyzeLocalTrace};
+import{summarizeLocalTrace}from"#tracing/local/trace-summary.js";import{localTraceOperations,traceModelName,traceSessionId,traceStringAttribute,traceToolName,uniqueLocalTraceSpans}from"#tracing/local/trace-operations.js";function analyzeLocalTrace(e,t,n={}){let r=uniqueLocalTraceSpans(t),i=new Map(localTraceOperations(r).map(({span:e})=>[e.spanId,e])),a=r.filter(e=>matches(i.get(e.spanId)??e,n)),o=a.reduce((e,t)=>t.startTimeNs<e?t.startTimeNs:e,a[0]?.startTimeNs??0n),s=localTraceOperations(a).map(e=>recordFor(e,o)).sort((e,t)=>e.startOffsetMs-t.startOffsetMs||e.endOffsetMs-t.endOffsetMs||e.spanId.localeCompare(t.spanId));return{summary:summarizeLocalTrace(e,a),groups:groups(s),modelWorkMs:sum(s,`model`),toolWorkMs:sum(s,`tool`),records:s}}function matches(e,t){let n=traceSessionId(e),r=traceStringAttribute(e,`agent.turn.id`);if(t.excludeSessionId!==void 0&&n===t.excludeSessionId||t.sessionId!==void 0&&n!==t.sessionId||t.turnId!==void 0&&r!==t.turnId)return!1;let i=Number(e.startTimeNs/1000000n);return(t.fromMs===void 0||i>=t.fromMs)&&(t.toMs===void 0||i<=t.toMs)}function recordFor(e,t){let{span:n,category:r}=e,i={category:r,durationMs:Number(n.endTimeNs-n.startTimeNs)/1e6,endOffsetMs:Number(n.endTimeNs-t)/1e6,outcome:n.statusCode===2?`failed`:`completed`,spanId:n.spanId,startOffsetMs:Number(n.startTimeNs-t)/1e6},a=traceStringAttribute(n,`gen_ai.tool.call.id`),o=traceModelName(n),s=traceSessionId(n),c=traceToolName(n),l=traceStringAttribute(n,`agent.turn.id`);if(a!==void 0&&(i.callId=a),n.statusMessage!==void 0&&(i.error=n.statusMessage),o!==void 0&&(i.model=o),n.parentSpanId!==void 0&&(i.parentSpanId=n.parentSpanId),s!==void 0&&(i.sessionId=s),c!==void 0&&r===`tool`&&(i.toolName=c),c!==void 0&&r===`other`&&(i.actionName=c),l!==void 0&&(i.turnId=l),e.actionDurationMs!==void 0&&(i.actionDurationMs=e.actionDurationMs),r===`model`){let e={};for(let[t,r]of Object.entries({inputTokens:`gen_ai.usage.input_tokens`,outputTokens:`gen_ai.usage.output_tokens`,cacheReadTokens:`gen_ai.usage.cache_read.input_tokens`,cacheWriteTokens:`gen_ai.usage.cache_write.input_tokens`})){let i=n.attributes[r];typeof i==`number`&&Number.isFinite(i)&&i>=0&&(e[t]=i)}Object.keys(e).length>0&&(i.usage=e)}return i}function groups(e){let t=new Map;for(let n of e){let e=JSON.stringify([n.sessionId,n.turnId]),r=t.get(e);r===void 0&&(r={modelCalls:0,modelWorkMs:0,toolCalls:0,toolWorkMs:0},n.sessionId!==void 0&&(r.sessionId=n.sessionId),n.turnId!==void 0&&(r.turnId=n.turnId),t.set(e,r)),n.category===`model`&&(r.modelCalls+=1,r.modelWorkMs+=n.durationMs),n.category===`tool`&&(r.toolCalls+=1,r.toolWorkMs+=n.durationMs)}return[...t.values()]}function sum(e,t){return e.reduce((e,n)=>e+(n.category===t?n.durationMs:0),0)}export{analyzeLocalTrace};

package/dist/src/tracing/{local-trace-operations.d.ts → local/trace-operations.d.ts}

@@ -1,4 +1,4 @@
-import type { LocalTraceSpan } from "#tracing/local-trace-reader.js";
+import type { LocalTraceSpan } from "#tracing/local/trace-reader.js";
 export interface LocalTraceOperation {
     readonly span: LocalTraceSpan;
     readonly category: "model" | "other" | "tool";

package/dist/src/tracing/{local-trace-query.d.ts → local/trace-query.d.ts}

@@ -1,4 +1,4 @@
-import type { LocalTraceSummary } from "#tracing/local-trace-summary.js";
+import type { LocalTraceSummary } from "#tracing/local/trace-summary.js";
 export type LocalTraceSortBy = "duration" | "failures" | "inputTokens" | "latest";
 interface LocalTraceQueryFilter {
     readonly agentName?: string;

package/dist/src/tracing/local/trace-reader.js

@@ -0,0 +1 @@
+import{readFile,readdir,stat}from"node:fs/promises";import{join}from"node:path";import{isAgentActivationSpan}from"#tracing/local/inspection.js";import{resolveLocalTraceSchemaDirectory,resolveLocalTraceSegmentsDirectory}from"#tracing/local/trace-span-processor.js";const TRACE_ID_PATTERN=/^[0-9a-f]{32}$/u,SPAN_FILE_PATTERN=/^[0-9a-f]{16}\.otlp\.json$/u;async function listLocalTraceIds(e){let t;try{t=await readdir(resolveLocalTraceSchemaDirectory(e),{withFileTypes:!0})}catch(e){if(isMissing(e))return[];throw e}return t.filter(e=>e.isDirectory()&&TRACE_ID_PATTERN.test(e.name)).map(e=>e.name)}async function readLocalTraceActivityMs(e,t){try{return(await stat(resolveLocalTraceSegmentsDirectory(e,t))).mtimeMs}catch(e){if(isMissing(e))return;throw e}}async function listLocalTraceSegments(e,t){let n;try{n=await readdir(resolveLocalTraceSegmentsDirectory(e,t),{withFileTypes:!0})}catch(e){if(isMissing(e))return;throw e}return n.filter(e=>e.isFile()&&SPAN_FILE_PATTERN.test(e.name)).map(e=>e.name).sort((e,t)=>e.localeCompare(t))}async function readLocalTraceSegment(e,t,n){let r=join(resolveLocalTraceSegmentsDirectory(e,t),n),i;try{if((await stat(r)).size>8388608)return[];i=await readFile(r,`utf8`)}catch{return[]}return parseLocalTraceSegment(i,t)}async function listLocalTraces(e){let t=[];for(let n of await listLocalTraceIds(e)){let r=await readLocalTrace(e,n).catch(()=>void 0);r!==void 0&&t.push(r)}return t.sort((e,t)=>e.startTimeNs===t.startTimeNs?e.traceId.localeCompare(t.traceId):e.startTimeNs>t.startTimeNs?-1:1)}async function readLocalTrace(e,t){let n=await listLocalTraceSegments(e,t);if(n===void 0)return;let r=new Map;for(let i of n)for(let n of await readLocalTraceSegment(e,t,i))r.has(n.spanId)||r.set(n.spanId,n);if(r.size!==0)return assembleLocalTrace(t,[...r.values()])}function compareLocalTraceSpans(e,t){return e.startTimeNs===t.startTimeNs?e.endTimeNs===t.endTimeNs?e.name.localeCompare(t.name)||e.spanId.localeCompare(t.spanId):e.endTimeNs<t.endTimeNs?-1:1:e.startTimeNs<t.startTimeNs?-1:1}function assembleLocalTrace(e,t){let n=[...t].sort(compareLocalTraceSpans),r=n.map(e=>e.attributes),i=distinctAttributes(r,`gen_ai.conversation.id`);return{agentName:firstAttribute(r,`agent.name`),endTimeNs:n.reduce((e,t)=>t.endTimeNs>e?t.endTimeNs:e,0n),conversationId:i[0],conversationIds:i,spans:n,startTimeNs:n.reduce((e,t)=>t.startTimeNs<e?t.startTimeNs:e,n[0].startTimeNs),traceId:e}}function describeLocalTraceSpan(e){let t=[],n=stringSpanAttribute(e,`agent.turn.id`),r=valueSpanAttribute(e,`agent.step.index`),i=valueSpanAttribute(e,`agent.step.attempt`),a=stringSpanAttribute(e,`agent.action.kind`),o=stringSpanAttribute(e,`agent.action.name`),s=stringSpanAttribute(e,`agent.model.id`)??stringSpanAttribute(e,`gen_ai.request.model`);return isAgentTurnSpan(e)&&n!==void 0&&t.push(n),e.name===`agent.step`&&r!==void 0&&t.push(`step ${String(r)}${i===void 0?``:`, attempt ${String(i)}`}`),e.name===`agent.action`&&o!==void 0&&t.push(`${a??`action`}: ${o}`),s!==void 0&&e.name.includes(`do`)&&t.push(`model ${s}`),t}function isAgentTurnSpan(e){return isAgentActivationSpan(e)}function parseLocalTraceSegment(e,t){try{let n=JSON.parse(e);if(!isRecord(n)||!Array.isArray(n.resourceSpans))return[];let r=[];for(let e of n.resourceSpans)if(isRecord(e)&&Array.isArray(e.scopeSpans))for(let n of e.scopeSpans){if(!isRecord(n)||!Array.isArray(n.spans))continue;let e=isRecord(n.scope)&&typeof n.scope.name==`string`?n.scope.name:void 0;for(let i of n.spans){let n=parseLocalTraceSpan(i,t,e);n!==void 0&&r.push(n)}}return r}catch{return[]}}function parseLocalTraceSpan(e,t,n){if(!isRecord(e)||e.traceId!==t||typeof e.spanId!=`string`||!/^[0-9a-f]{16}$/u.test(e.spanId)||typeof e.name!=`string`)return;let r=parseNanos(e.startTimeUnixNano),i=parseNanos(e.endTimeUnixNano);if(!(r===void 0||i===void 0||i<r))return{attributes:parseAttributes(e.attributes),endTimeNs:i,events:parseEvents(e.events),kind:typeof e.kind==`number`?e.kind:void 0,name:e.name,parentSpanId:typeof e.parentSpanId==`string`&&/^[0-9a-f]{16}$/u.test(e.parentSpanId)?e.parentSpanId:void 0,scope:n,spanId:e.spanId,startTimeNs:r,statusCode:parseStatusCode(e.status),statusMessage:parseStatusMessage(e.status),traceId:t}}function parseEvents(e){if(!Array.isArray(e))return[];let t=[];for(let n of e){if(!isRecord(n)||typeof n.name!=`string`)continue;let e=parseNanos(n.timeUnixNano);e!==void 0&&t.push({attributes:parseAttributes(n.attributes),name:n.name,timeNs:e})}return t.sort((e,t)=>e.timeNs===t.timeNs?e.name.localeCompare(t.name):e.timeNs<t.timeNs?-1:1)}function parseAttributes(e){if(!Array.isArray(e))return{};let t={};for(let n of e){if(!isRecord(n)||typeof n.key!=`string`||!isRecord(n.value))continue;let e=parseAnyValue(n.value);e!==void 0&&(t[n.key]=e)}return t}function parseAnyValue(e){for(let t of[`stringValue`,`boolValue`,`intValue`,`doubleValue`])if(t in e)return e[t];if(isRecord(e.arrayValue)&&Array.isArray(e.arrayValue.values))return e.arrayValue.values.filter(isRecord).map(e=>parseAnyValue(e))}function parseNanos(e){if(typeof e==`string`||typeof e==`number`)try{let t=BigInt(e);return t>=0n&&t<=18446744073709551615n?t:void 0}catch{return}}function parseStatusCode(e){return isRecord(e)?typeof e.code==`number`?e.code:e.code===`STATUS_CODE_ERROR`?2:0:0}function parseStatusMessage(e){if(isRecord(e)&&typeof e.message==`string`)return e.message.length===0?void 0:e.message}function firstAttribute(e,t){for(let n of e){let e=n[t];if(typeof e==`string`&&e.length>0)return e}}function distinctAttributes(e,t){let n=new Set;for(let r of e){let e=r[t];typeof e==`string`&&e.length>0&&n.add(e)}return[...n]}function stringSpanAttribute(e,t){let n=e.attributes[t];return typeof n==`string`?n:void 0}function valueSpanAttribute(e,t){let n=e.attributes[t];return typeof n==`string`||typeof n==`number`?n:void 0}function isMissing(e){return e.code===`ENOENT`}function isRecord(e){return typeof e==`object`&&!!e&&!Array.isArray(e)}export{assembleLocalTrace,compareLocalTraceSpans,describeLocalTraceSpan,isAgentTurnSpan,listLocalTraceIds,listLocalTraceSegments,listLocalTraces,parseLocalTraceSegment,readLocalTraceActivityMs,readLocalTraceSegment};

package/dist/src/tracing/{local-trace-retention.js → local/trace-retention.js}

@@ -1 +1 @@
-import{readdir,rm,stat}from"node:fs/promises";import{createLogger,formatError}from"#internal/logging.js";import{join}from"node:path";import{resolveLocalTraceSchemaDirectory,resolveLocalTraceSegmentsDirectory}from"#tracing/local-trace-span-processor.js";const log=createLogger(`harness.local-trace-retention`),LOCAL_TRACE_QUIESCENCE_MS=3e5,LOCAL_TRACE_MAX_AGE_MS=6048e5,LOCAL_TRACE_MAX_TOTAL_BYTES=536870912;function resolveLocalTraceRetentionSettings(e=process.env){return{enabled:!isDisabled(e.EVE_TRACES),maxAgeMs:readBound(e,`EVE_TRACES_MAX_AGE_MS`,LOCAL_TRACE_MAX_AGE_MS),maxTotalBytes:readBound(e,`EVE_TRACES_MAX_TOTAL_BYTES`,LOCAL_TRACE_MAX_TOTAL_BYTES),retainCount:readBound(e,`EVE_TRACES_RETAIN_COUNT`,20)}}async function pruneLocalTraceStore(e){let t=e.now??Date.now(),n=clampBound(e.maxAgeMs??LOCAL_TRACE_MAX_AGE_MS),r=clampBound(e.maxTotalBytes??LOCAL_TRACE_MAX_TOTAL_BYTES),i=clampCount(e.retainCount??20),a=await readStoredTraces(e.appRoot,t),o=[...a].sort((e,t)=>t.modifiedAtMs-e.modifiedAtMs),s=new Set(o.slice(0,i===!1?0:i)),c=new Set,l=a.reduce((e,t)=>e+t.byteSize,0),u=0,d=0,f=0;for(let i of o.toReversed()){let a=t-i.modifiedAtMs,o=e.activeTraceIds.has(i.traceId)||s.has(i)||a<=LOCAL_TRACE_QUIESCENCE_MS?void 0:n!==!1&&a>n?`maxAgeMs`:r!==!1&&l>r?`maxTotalBytes`:void 0;if(o===void 0){f+=1;continue}await rm(i.path,{force:!0,recursive:!0}),l-=i.byteSize,u+=i.byteSize,d+=1,c.add(o)}return{reasons:[...c],reclaimedBytes:u,removedTraces:d,retainedTraces:f}}const pruneRequest={input:{activeTraceIds:new Set,appRoot:``},requested:!1,running:void 0};function requestLocalTraceStorePrune(e){pruneRequest.input=e,pruneRequest.requested=!0,pruneRequest.running===void 0&&startPruning()}function startPruning(){pruneRequest.running=(async()=>{for(;pruneRequest.requested;)pruneRequest.requested=!1,report(await pruneLocalTraceStore(pruneRequest.input))})().catch(e=>{log.warn(`local trace retention failed`,{error:formatError(e)})}).finally(()=>{pruneRequest.running=void 0,pruneRequest.requested&&startPruning()})}function report(e){e.removedTraces!==0&&log.info(`pruned local traces`,{reasons:e.reasons.join(`,`),reclaimedBytes:e.reclaimedBytes,removedTraces:e.removedTraces,retainedTraces:e.retainedTraces})}async function readStoredTraces(e,t){let n=resolveLocalTraceSchemaDirectory(e),r=await readDirectoryEntries(n);return r===void 0?[]:(await Promise.all(r.filter(e=>e.isDirectory()).map(async r=>{let i=join(n,r.name),a=resolveLocalTraceSegmentsDirectory(e,r.name);await reapAbandonedTemporaryFiles(a,t);let o=await directoryMtime(a)??await directoryMtime(i);if(o!==void 0)return{byteSize:await directorySize(i),modifiedAtMs:o,path:i,traceId:r.name}}))).filter(e=>e!==void 0)}async function reapAbandonedTemporaryFiles(e,t){let n=await readDirectoryEntries(e);if(n!==void 0)for(let r of n){if(!r.isFile()||!r.name.includes(`.tmp-`))continue;let n=join(e,r.name);try{if(t-(await stat(n)).mtimeMs<=LOCAL_TRACE_QUIESCENCE_MS)continue;await rm(n,{force:!0})}catch{}}}async function directoryMtime(e){try{return(await stat(e)).mtimeMs}catch{return}}async function directorySize(e){let t=await readDirectoryEntries(e);if(t===void 0)return 0;let n=0;for(let r of t){let t=join(e,r.name);if(r.isDirectory()){n+=await directorySize(t);continue}try{n+=(await stat(t)).size}catch{}}return n}async function readDirectoryEntries(e){try{return await readdir(e,{withFileTypes:!0})}catch(e){if(e instanceof Error&&`code`in e&&(e.code===`ENOENT`||e.code===`ENOTDIR`))return;throw e}}function isDisabled(e){if(e===void 0)return!1;let t=e.trim().toLowerCase();return t===`off`||t===`false`||t===`0`}function readBound(e,t,n){let r=e[t];if(r===void 0)return n;let i=r.trim().toLowerCase();if(i===`off`||i===`false`)return!1;let a=Number(i);return!Number.isFinite(a)||a<0?(log.warn(`ignoring invalid local trace retention value`,{fallback:n,name:t,value:r}),n):a}function clampBound(e){return e!==!1&&Math.max(0,e)}function clampCount(e){return e!==!1&&Math.max(0,Math.trunc(e))}export{pruneLocalTraceStore,requestLocalTraceStorePrune,resolveLocalTraceRetentionSettings};
+import{readdir,rm,stat}from"node:fs/promises";import{createLogger,formatError}from"#internal/logging.js";import{join}from"node:path";import{resolveLocalTraceSchemaDirectory,resolveLocalTraceSegmentsDirectory}from"#tracing/local/trace-span-processor.js";const log=createLogger(`harness.local-trace-retention`),LOCAL_TRACE_QUIESCENCE_MS=3e5,LOCAL_TRACE_MAX_AGE_MS=6048e5,LOCAL_TRACE_MAX_TOTAL_BYTES=536870912;function resolveLocalTraceRetentionSettings(e=process.env){return{enabled:!isDisabled(e.EVE_TRACES),maxAgeMs:readBound(e,`EVE_TRACES_MAX_AGE_MS`,LOCAL_TRACE_MAX_AGE_MS),maxTotalBytes:readBound(e,`EVE_TRACES_MAX_TOTAL_BYTES`,LOCAL_TRACE_MAX_TOTAL_BYTES),retainCount:readBound(e,`EVE_TRACES_RETAIN_COUNT`,20)}}async function pruneLocalTraceStore(e){let t=e.now??Date.now(),n=clampBound(e.maxAgeMs??LOCAL_TRACE_MAX_AGE_MS),r=clampBound(e.maxTotalBytes??LOCAL_TRACE_MAX_TOTAL_BYTES),i=clampCount(e.retainCount??20),a=await readStoredTraces(e.appRoot,t),o=[...a].sort((e,t)=>t.modifiedAtMs-e.modifiedAtMs),s=new Set(o.slice(0,i===!1?0:i)),c=new Set,l=a.reduce((e,t)=>e+t.byteSize,0),u=0,d=0,f=0;for(let i of o.toReversed()){let a=t-i.modifiedAtMs,o=e.activeTraceIds.has(i.traceId)||s.has(i)||a<=LOCAL_TRACE_QUIESCENCE_MS?void 0:n!==!1&&a>n?`maxAgeMs`:r!==!1&&l>r?`maxTotalBytes`:void 0;if(o===void 0){f+=1;continue}await rm(i.path,{force:!0,recursive:!0}),l-=i.byteSize,u+=i.byteSize,d+=1,c.add(o)}return{reasons:[...c],reclaimedBytes:u,removedTraces:d,retainedTraces:f}}const pruneRequest={input:{activeTraceIds:new Set,appRoot:``},requested:!1,running:void 0};function requestLocalTraceStorePrune(e){pruneRequest.input=e,pruneRequest.requested=!0,pruneRequest.running===void 0&&startPruning()}function startPruning(){pruneRequest.running=(async()=>{for(;pruneRequest.requested;)pruneRequest.requested=!1,report(await pruneLocalTraceStore(pruneRequest.input))})().catch(e=>{log.warn(`local trace retention failed`,{error:formatError(e)})}).finally(()=>{pruneRequest.running=void 0,pruneRequest.requested&&startPruning()})}function report(e){e.removedTraces!==0&&log.info(`pruned local traces`,{reasons:e.reasons.join(`,`),reclaimedBytes:e.reclaimedBytes,removedTraces:e.removedTraces,retainedTraces:e.retainedTraces})}async function readStoredTraces(e,t){let n=resolveLocalTraceSchemaDirectory(e),r=await readDirectoryEntries(n);return r===void 0?[]:(await Promise.all(r.filter(e=>e.isDirectory()).map(async r=>{let i=join(n,r.name),a=resolveLocalTraceSegmentsDirectory(e,r.name);await reapAbandonedTemporaryFiles(a,t);let o=await directoryMtime(a)??await directoryMtime(i);if(o!==void 0)return{byteSize:await directorySize(i),modifiedAtMs:o,path:i,traceId:r.name}}))).filter(e=>e!==void 0)}async function reapAbandonedTemporaryFiles(e,t){let n=await readDirectoryEntries(e);if(n!==void 0)for(let r of n){if(!r.isFile()||!r.name.includes(`.tmp-`))continue;let n=join(e,r.name);try{if(t-(await stat(n)).mtimeMs<=LOCAL_TRACE_QUIESCENCE_MS)continue;await rm(n,{force:!0})}catch{}}}async function directoryMtime(e){try{return(await stat(e)).mtimeMs}catch{return}}async function directorySize(e){let t=await readDirectoryEntries(e);if(t===void 0)return 0;let n=0;for(let r of t){let t=join(e,r.name);if(r.isDirectory()){n+=await directorySize(t);continue}try{n+=(await stat(t)).size}catch{}}return n}async function readDirectoryEntries(e){try{return await readdir(e,{withFileTypes:!0})}catch(e){if(e instanceof Error&&`code`in e&&(e.code===`ENOENT`||e.code===`ENOTDIR`))return;throw e}}function isDisabled(e){if(e===void 0)return!1;let t=e.trim().toLowerCase();return t===`off`||t===`false`||t===`0`}function readBound(e,t,n){let r=e[t];if(r===void 0)return n;let i=r.trim().toLowerCase();if(i===`off`||i===`false`)return!1;let a=Number(i);return!Number.isFinite(a)||a<0?(log.warn(`ignoring invalid local trace retention value`,{fallback:n,name:t,value:r}),n):a}function clampBound(e){return e!==!1&&Math.max(0,e)}function clampCount(e){return e!==!1&&Math.max(0,Math.trunc(e))}export{pruneLocalTraceStore,requestLocalTraceStorePrune,resolveLocalTraceRetentionSettings};

package/dist/src/tracing/{local-trace-span-processor.js → local/trace-span-processor.js}

@@ -1 +1 @@
-import{mkdir}from"node:fs/promises";import{createLogger,formatError}from"#internal/logging.js";import{join}from"node:path";import{atomicWriteFile}from"#shared/atomic-write-file.js";import{indexLocalTraceConversation}from"#tracing/local-trace-discovery-index.js";import{JsonTraceSerializer}from"#compiled/@opentelemetry/otlp-transformer/index.js";const log=createLogger(`harness.local-trace-span-processor`);function resolveLocalTraceStoreDirectory(e){return join(e,`.eve`,`traces`)}function resolveLocalTraceSchemaDirectory(e){return join(resolveLocalTraceStoreDirectory(e),`v1`)}function resolveLocalTraceDirectory(e,t){return join(resolveLocalTraceSchemaDirectory(e),t)}function resolveLocalTraceSegmentsDirectory(e,t){return join(resolveLocalTraceDirectory(e,t),`segments`)}var LocalTraceSpanProcessor=class{#e;#t=Promise.resolve();#n=!1;constructor(e){this.#e=e}forceFlush(){return this.#t}onStart(){}onEnd(e){if(!isReadableSpan(e))return;let{spanId:t,traceId:n}=e.spanContext();if(!isHexId(n,32)||!isHexId(t,16))return;let r=JsonTraceSerializer.serializeRequest([e]);if(r===void 0)return;let i=e.attributes[`gen_ai.conversation.id`],a=typeof i==`string`&&i.length>0?i:void 0;this.#t=this.#t.then(async()=>{let e=resolveLocalTraceDirectory(this.#e,n),i=resolveLocalTraceSegmentsDirectory(this.#e,n);await mkdir(i,{recursive:!0}),await atomicWriteFile(join(i,`${t}.otlp.json`),r),a!==void 0&&await indexLocalTraceConversation({conversationId:a,traceDirectory:e})}).catch(e=>{this.#n||(this.#n=!0,log.warn(`local trace persistence failed`,{error:formatError(e)}))})}shutdown(){return this.forceFlush()}};function isReadableSpan(e){return typeof e==`object`&&!!e&&`attributes`in e&&`spanContext`in e&&typeof e.spanContext==`function`}function isHexId(e,t){return e.length===t&&/^[0-9a-f]+$/u.test(e)}export{LocalTraceSpanProcessor,resolveLocalTraceSchemaDirectory,resolveLocalTraceSegmentsDirectory};
+import{mkdir}from"node:fs/promises";import{createLogger,formatError}from"#internal/logging.js";import{join}from"node:path";import{atomicWriteFile}from"#shared/atomic-write-file.js";import{indexLocalTraceConversation}from"#tracing/local/trace-discovery-index.js";import{JsonTraceSerializer}from"#compiled/@opentelemetry/otlp-transformer/index.js";const log=createLogger(`harness.local-trace-span-processor`);function resolveLocalTraceStoreDirectory(e){return join(e,`.eve`,`traces`)}function resolveLocalTraceSchemaDirectory(e){return join(resolveLocalTraceStoreDirectory(e),`v1`)}function resolveLocalTraceDirectory(e,t){return join(resolveLocalTraceSchemaDirectory(e),t)}function resolveLocalTraceSegmentsDirectory(e,t){return join(resolveLocalTraceDirectory(e,t),`segments`)}var LocalTraceSpanProcessor=class{#e;#t=Promise.resolve();#n=!1;constructor(e){this.#e=e}forceFlush(){return this.#t}onStart(){}onEnd(e){if(!isReadableSpan(e))return;let{spanId:t,traceId:n}=e.spanContext();if(!isHexId(n,32)||!isHexId(t,16))return;let r=JsonTraceSerializer.serializeRequest([e]);if(r===void 0)return;let i=e.attributes[`gen_ai.conversation.id`],a=typeof i==`string`&&i.length>0?i:void 0;this.#t=this.#t.then(async()=>{let e=resolveLocalTraceDirectory(this.#e,n),i=resolveLocalTraceSegmentsDirectory(this.#e,n);await mkdir(i,{recursive:!0}),await atomicWriteFile(join(i,`${t}.otlp.json`),r),a!==void 0&&await indexLocalTraceConversation({conversationId:a,traceDirectory:e})}).catch(e=>{this.#n||(this.#n=!0,log.warn(`local trace persistence failed`,{error:formatError(e)}))})}shutdown(){return this.forceFlush()}};function isReadableSpan(e){return typeof e==`object`&&!!e&&`attributes`in e&&`spanContext`in e&&typeof e.spanContext==`function`}function isHexId(e,t){return e.length===t&&/^[0-9a-f]+$/u.test(e)}export{LocalTraceSpanProcessor,resolveLocalTraceSchemaDirectory,resolveLocalTraceSegmentsDirectory};

package/dist/src/tracing/{local-trace-summary.d.ts → local/trace-summary.d.ts}

@@ -1,4 +1,4 @@
-import type { LocalTraceSpan } from "#tracing/local-trace-reader.js";
+import type { LocalTraceSpan } from "#tracing/local/trace-reader.js";
 /** Structural metadata and totals for one retained trace, not its final outcome. */
 export interface LocalTraceSummary {
     readonly traceId: string;

package/dist/src/tracing/local/trace-summary.js

@@ -0,0 +1 @@
+import{localTraceOperations,traceModelName,traceSessionId,traceStringAttribute,traceToolName,uniqueLocalTraceSpans}from"#tracing/local/trace-operations.js";import{USAGE_FIELDS}from"#compiled/@eve/tracing/otel.js";function summarizeLocalTrace(e,t){let n=uniqueLocalTraceSpans(t),r=new Set,i=new Set,a=new Set,o=new Set,s=n[0]?.startTimeNs??0n,c=s,l=0,u=0,d,f=0,p=0,m=0;for(let e of n){if(e.startTimeNs<s&&(s=e.startTimeNs),e.endTimeNs>c&&(c=e.endTimeNs),add(r,traceModelName(e)),add(i,traceStringAttribute(e,`agent.name`)),add(a,traceStringAttribute(e,`gen_ai.conversation.id`)),add(o,traceSessionId(e)),e.statusCode===2&&(f+=1),e.name!==`agent.step`)continue;p+=numberAttribute(e,`agent.usage.input_tokens`)??0,m+=numberAttribute(e,`agent.usage.output_tokens`)??0,l+=numberAttribute(e,USAGE_FIELDS.cacheReadTokens)??numberAttribute(e,`gen_ai.usage.cache_read.input_tokens`)??0,u+=numberAttribute(e,USAGE_FIELDS.cacheWriteTokens)??numberAttribute(e,`gen_ai.usage.cache_creation.input_tokens`)??0;let t=localTraceSpanCostUsd(e);t!==void 0&&(d=(d??0)+t)}let h=new Set,g=0,_=0;for(let e of localTraceOperations(n))e.category===`model`&&(g+=1),e.category===`tool`&&(_+=1,add(h,traceToolName(e.span)));return{traceId:e,startedAt:new Date(Number(s/1000000n)).toISOString(),durationMs:Number(c-s)/1e6,spanCount:n.length,agentNames:[...i].sort(),conversationIds:[...a].sort(),sessionIds:[...o].sort(),models:[...r].sort(),toolNames:[...h].sort(),modelCalls:g,toolCalls:_,errorSpanCount:f,cacheReadTokens:l,cacheWriteTokens:u,costUsd:d,inputTokens:p,outputTokens:m}}function localTraceSpanCostUsd(e){return numberAttribute(e,`gen_ai.usage.gateway_cost`)??numberAttribute(e,`gen_ai.usage.cost`)}function numberAttribute(e,t){let n=e.attributes[t];if(typeof n==`number`)return Number.isFinite(n)&&n>=0?n:void 0;if(typeof n==`string`&&n.trim()!==``){let e=Number(n);return Number.isFinite(e)&&e>=0?e:void 0}}function add(e,t){t!==void 0&&e.add(t)}export{localTraceSpanCostUsd,summarizeLocalTrace};

package/dist/src/tracing/{local-traces.d.ts → local/traces.d.ts}

@@ -1,5 +1,5 @@
 import type { SpanProcessor } from "#compiled/@vercel/otel/index.js";
-import { type SpanExportPolicy } from "#tracing/span-export-policy.js";
+import { type SpanExportPolicy } from "#tracing/eve/span-export-policy.js";
 /**
  * The local spool, as a span processor.
  *

package/dist/src/tracing/local/traces.js

@@ -0,0 +1 @@
+import{normalizeSpanExportPolicies}from"#tracing/eve/span-export-policy.js";import{LocalTraceSpanProcessor}from"#tracing/local/trace-span-processor.js";import{AgentTraceSpanProcessor}from"#tracing/local/agent-trace-span-processor.js";import{requestLocalTraceStorePrune,resolveLocalTraceRetentionSettings}from"#tracing/local/trace-retention.js";function hasConversationRelease(e){return typeof e.releaseConversation==`function`}function createLocalTracesProcessor(e={}){let t=e.appRoot??process.env.EVE_DEV_WORKER_APP_ROOT;if(t===void 0)return inertLocalTracesProcessor();let n=resolveLocalTraceRetentionSettings(),r=new AgentTraceSpanProcessor(n.enabled?[new LocalTraceSpanProcessor(t)]:[]),requestPrune=()=>{n.enabled&&requestLocalTraceStorePrune({activeTraceIds:r.activeTraceIds(),appRoot:t,maxAgeMs:n.maxAgeMs,maxTotalBytes:n.maxTotalBytes,retainCount:n.retainCount})};requestPrune();let forceFlush=async()=>{await r.forceFlush(),r.releaseCompletedTraces()&&requestPrune()};return{forceFlush,onEnd:e=>r.onEnd(e),onStart:(e,t)=>r.onStart(e,t),async releaseConversation(e){return await forceFlush(),r.releaseConversation(e)?(requestPrune(),!0):!1},shutdown:()=>r.shutdown()}}function resolveLocalTracesExportPolicy(e){return process.env.EVE_TRACES_CONTENT===`off`?[{span:()=>({redact:!0,inputs:!0,outputs:!0})},...normalizeSpanExportPolicies(e)]:e}function inertLocalTracesProcessor(){return{forceFlush:async()=>void 0,onEnd:()=>void 0,onStart:()=>void 0,releaseConversation:async()=>!1,shutdown:async()=>void 0}}export{createLocalTracesProcessor,hasConversationRelease,resolveLocalTracesExportPolicy};

package/docs/connections/mcp.mdx

@@ -115,7 +115,7 @@ Use the shared `approval` option to gate every tool served by an MCP connection.
 
 ### Gate specific tools by name or input
 
-A remote MCP server usually mixes read tools with destructive or publishing ones, so a blanket `always()` would prompt on every harmless call. Pass a custom policy instead — the same [`Approval`](/docs/human-in-the-loop#approvals) shape authored tools use — to gate only the calls that matter. The policy receives `{ session, toolName, toolInput, approvedTools, callId, abortSignal }` and returns an approval status, synchronously or as a promise.
+A remote MCP server usually mixes read tools with destructive or publishing ones, so a blanket `always()` would prompt on every harmless call. Pass a custom policy instead — the same [`Approval`](/docs/human-in-the-loop#approvals) shape authored tools use — to gate only the calls that matter. The policy receives `{ session, toolName, toolInput, toolAnnotations, approvedTools, callId, abortSignal }` and returns an approval status, synchronously or as a promise.
 
 This connection always gates deletes, gates a publish only when the call actually schedules a post, and lets everything else through:
 
@@ -157,6 +157,27 @@ Two details are specific to connection tools:
 
 Return `"user-approval"` (or `true`) to pause for a person and `"not-applicable"` (or `false`) to run without a prompt; return `"approved"` or `"denied"` to decide automatically without involving anyone.
 
+### Gate by the server's tool annotations
+
+Many MCP servers declare [tool annotations](https://modelcontextprotocol.io/specification/2025-06-18/server/tools#tool) such as `readOnlyHint` and `destructiveHint` for each tool. eve passes what the server declared for the called tool as `toolAnnotations`, typed as `ConnectionToolAnnotations` from `eve/tools/approval`. It is `undefined` when the server declares none, so keep a fallback:
+
+```ts title="agent/connections/linear.ts"
+import { connect } from "@vercel/connect/eve";
+import { defineMcpClientConnection } from "eve/connections";
+
+export default defineMcpClientConnection({
+  url: "https://mcp.linear.app/mcp",
+  description: "Linear issues and projects.",
+  auth: connect("mcp.linear.app/linear"),
+  approval: ({ toolAnnotations }) => {
+    if (toolAnnotations?.readOnlyHint === true) return "not-applicable";
+    return "user-approval";
+  },
+});
+```
+
+Annotations are hints from the server, not guarantees. Trust them only as far as you trust the server that sent them.
+
 [Human-in-the-loop](/docs/human-in-the-loop#approvals) covers the full set of statuses, how `approvedTools` and `session.auth` factor in, and how a gated call pauses and resumes durably.
 
 ## Forward the caller to an eve agent

package/docs/evals/assertions.mdx

@@ -3,7 +3,7 @@ title: "Assertions"
 description: "Scoped methods, value assertions, the matcher mini-language, and gate vs soft severity."
 ---
 
-Assertions are how an eval grades what its `test(t)` function produced. Each one records a result and returns a chainable handle. The runner reads every recorded result to compute the verdict, so a single run reports every failing assertion rather than dying on the first. There are two deterministic surfaces: scoped methods and `t.check` for grading a specific value. For model-graded assertions, see [Judge](./judge).
+Assertions are how an eval grades what its `test(t)` function produced. Each one records a result and returns a chainable handle. The runner reads every recorded result to compute the verdict, so a single run reports every failing assertion rather than dying on the first. There are three deterministic surfaces: scoped methods, `t.check` for grading a specific value, and `t.score` for recording a measurement you computed yourself. For model-graded assertions, see [Judge](./judge).
 
 ## Scoped assertions
 
@@ -83,6 +83,53 @@ For example, a failed labeled equality check prints:
 
 Pick the cheapest builder that captures what "correct" means. When exact match is too strict but a judge model is overkill, `similarity` is the middle ground. For nuanced grading, reach for the [judge](./judge).
 
+## Scores with `t.score`
+
+`t.score(evaluation)` records a score from 0 to 1. The evaluation is the number or `{ score, message?, metadata? }`, or a promise of either. Chain `.label(key)` to name it; reporters and artifacts expose the label as `key`. Without a label the score reports as `score`, and several unlabeled scores share that name.
+
+```ts
+const reply = turn.message ?? "";
+t.score({
+  score: Math.max(0, 1 - reply.length / 400),
+  metadata: { length: reply.length },
+}).label("reply-brevity");
+t.score(gradeFaithfulness(reply, reference)).label("faithfulness"); // async
+```
+
+On its own a score has no verdict and does not affect the eval's outcome. Chain a rule when it should:
+
+```ts
+t.score(gradeFaithfulness(reply, reference)).label("faithfulness").gate(0.9); // fails below 0.9
+t.score(brevity).label("reply-brevity").atLeast(0.5); // marks the eval `scored`, fatal under --strict
+```
+
+The score is reported as measured. A `0.82` gated at `0.9` is reported as `score: 0.82`, `threshold: 0.9`, `passed: false`. An evaluator that throws or returns a score outside 0 to 1 records an errored outcome with the error message and no score, and fails the eval.
+
+Every [reporter](./reporters#custom-reporters) receives the entries in `onEvalComplete` and can read them by `key`:
+
+```ts
+onEvalComplete(result) {
+  for (const { key, score, threshold, passed } of result.assertions) {
+    if (key === undefined) continue;
+    store.write({ evalId: result.id, key, score, threshold, passed });
+  }
+}
+```
+
+The same entries land in the [run artifacts](./running#artifacts) under `.eve/evals/`, in `summary.json` and one line per eval in `results.jsonl`:
+
+```json
+{
+  "name": "score [reply-brevity]",
+  "key": "reply-brevity",
+  "score": 0.84,
+  "severity": "soft",
+  "errored": false
+}
+```
+
+`threshold` and `passed` are present only when a rule was chained.
+
 ## The matcher mini-language
 
 `t.calledTool` and `t.calledSubagent` take matcher objects. Tools accept `{ input, output, status, count }`; subagents accept `{ callId, childSessionId, remoteUrl, output, status, count }`. Calls match `status: "completed"` by default. Tool lifecycle checks also accept `"pending"`, `"failed"`, and `"rejected"`. Subagent checks accept `"working"`, `"completed"`, `"failed"`, and `"cancelled"`. A numeric `count` requires an exact number of calls matching every supplied constraint. Use a predicate for ranges or other custom count requirements; it receives the observed number of matching calls.
@@ -164,9 +211,9 @@ const request = session.requireInputRequest({ toolName: "guarded" });
 Every assertion returns a chainable handle. Severity rides on the assertion, so there is no separate thresholds map to keep in sync.
 
 - `.gate(threshold?)` is hard. A miss marks the eval `failed` and `eve eval` exits non-zero.
-- `.soft(threshold?)` is tracked data. A below-threshold miss marks the eval `scored`, fatal only under `--strict`. With no threshold, it is tracked-only and never fails.
+- `.soft(threshold?)` is tracked data. A below-threshold miss marks the eval `scored`, fatal only under `--strict`. With no threshold it records no verdict and never fails.
 - `.atLeast(threshold)` is soft with a bar (equivalent to `.soft(threshold)`).
-- `.label(name)` adds a stable name when an eval records several assertions from the same family.
+- `.label(key)` adds a stable name when an eval records several assertions from the same family. Reporters and artifacts expose it as `key`. Braintrust and Datadog keep one score per name, so `eve eval` warns when soft assertions in one eval share a name with different scores.
 
 The defaults are chosen so you rarely set severity. Run-level methods and `includes`/`equals`/`matches` are gates; `similarity` and every `t.judge(...)` assertion are soft. Annotate only when you deviate:
 

package/docs/evals/overview.mdx

@@ -154,6 +154,7 @@ Each surface matches a genuinely different kind of judgment:
 
 - **Scoped methods** read the final whole run on `t`, snapshot one independent session when invoked there, or inspect one immutable `EveEvalTurn`. See [Assertions](./assertions).
 - **`t.check(value, assertion)`** grades an explicit value with a deterministic builder from `eve/evals/expect`, such as `t.check(turn.message, includes("sunny"))`. Grade `turn.message`, an intermediate draft, parsed JSON, or anything else. See [Assertions](./assertions).
+- **`t.score(evaluation)`** records a score, such as a length ratio or an evaluator's result. Chain `.label(key)` to name it, and `.gate(threshold)` or `.atLeast(threshold)` to let it decide the eval. See [Assertions](./assertions#scores-with-tscore).
 - **`t.judge(...)`** is the LLM-as-judge surface, like `t.judge("cites a source")`. It grades the most recently settled turn’s assistant message by default; pass `{ on: turn.session.transcript }` to grade a multi-turn conversation. The judge uses the configured judge model, never the agent under test. See [Judge](./judge).
 
 ## Gate vs soft
@@ -161,7 +162,7 @@ Each surface matches a genuinely different kind of judgment:
 Every assertion returns a chainable handle, so severity rides on the assertion itself. There is no separate thresholds map.
 
 - **Gates** are hard. A failed gate marks the eval `failed` and `eve eval` exits non-zero. Run-level methods, `includes`, `equals`, and `matches` are gates by default.
-- **Soft** assertions are tracked data. They land in reports and artifacts, and a below-threshold soft assertion marks the eval `scored` (visible but not fatal, unless you pass `--strict`). `similarity` and every `t.judge(...)` assertion are soft by default. A soft assertion with no threshold is tracked-only and never fails.
+- **Soft** assertions are tracked data. They land in reports and artifacts, and a below-threshold soft assertion marks the eval `scored` (visible but not fatal, unless you pass `--strict`). `similarity`, every `t.judge(...)` assertion, and every `t.score(...)` are soft by default. A soft assertion with no threshold records no verdict and never fails.
 
 Override per assertion: `.gate(threshold?)` promotes to a hard gate, `.soft(threshold?)` demotes to tracked, and `.atLeast(threshold)` is a soft assertion with a bar.
 

package/docs/evals/reporters.mdx

@@ -38,7 +38,7 @@ export default defineEval({
 });
 ```
 
-The reporter config takes an optional `projectName` and `experimentName`, plus a base experiment (by name or id) to diff against. Gate assertions log as binary scores under a `gate:` prefix so experiments diff gate regressions the same way they diff soft-score regressions. Assertions that share a name, such as several unlabeled judges, log one score: the lowest. Use `.label(name)` to group or separate them. Each assertion's score is stored in the Braintrust metadata under `eveAssertionScores` and failed assertion details under `eveFailedAssertions`; observed traces are stored under `eveTraceIds` and `eveTraceContexts`.
+The reporter config takes an optional `projectName` and `experimentName`, plus a base experiment (by name or id) to diff against. Gate assertions log as binary scores under a `gate:` prefix so experiments diff gate regressions the same way they diff soft-score regressions. Assertions that share a name, such as several unlabeled judges, log one score: the lowest. The console warns under the eval when merged soft scores differ; use `.label(name)` to group or separate them. Errored assertions log no score. Each assertion's score is stored in the Braintrust metadata under `eveAssertionScores` and failed assertion details under `eveFailedAssertions`; observed traces are stored under `eveTraceIds` and `eveTraceContexts`.
 
 A reporter instance observes the evals that reference it. Share one instance across several evals (the config, a `shared.ts` export, or every entry of a dataset array) and their results land in a single experiment. Listing the same config reporter on an eval too does not double-report it.
 
@@ -97,6 +97,8 @@ interface EvalReporter {
 - `onSessionStart` fires once for each session after eve receives its first trace context. It includes `sessionId`, `primary`, and `traceContext` with `traceId`, `spanId`, and `traceFlags`.
 - `onEvalComplete` fires with the checks, scores, and verdict. The runner also supplies `context`, including every distinct trace context collected across the eval's sessions. The same list is available as `result.result.traceContexts`.
 
+Each entry in `result.assertions` is an `AssertionResult`. `name` is the display label, `key` the identifier set by `.label(key)`, and `score` the measurement. `threshold` and `passed` describe the rule and are absent when no rule applies. When a scorer threw, `errored` is `true`, `message` carries the error, and `score` is absent. The `.eve/evals/` artifacts write the same fields.
+
 An eval can create several sessions, and a long session can produce several traces, so completion exposes a list instead of a single trace id. `onEvalStart` does not include a trace because the agent session has not started yet. If the target has no tracing configured, `onSessionStart` does not fire and the completed trace list is empty.
 
 `result.result.derived` holds the facts the runner derived from the eval's sessions, such as tool calls and `models`: the distinct ids of the models the steps started with, in session order. Each entry in `result.result.sessions` holds the same facts for one session, in first-use order, so a reporter can tell the primary session's models from those of the other sessions the eval created or attached. A delegated subagent runs in its own session, so its models appear only when the eval attaches that session with `t.target.attachSession`. Compaction and `auto` routing calls are not included.

package/docs/tools/human-in-the-loop.md

@@ -64,7 +64,29 @@ approval: auto({
 
 A reusable approval grant applies only after every matching request that is already pending has been resolved. If several calls to a `once()`-gated tool have each produced an approval prompt, approving one does not authorize the others; each visible prompt remains an independent decision. After those pending requests are resolved, later calls in the session are allowed automatically.
 
-When the decision depends on the input, pass your own policy instead of a helper. It receives the same session context as tool execution, plus `{ toolName, toolInput, approvedTools, callId, abortSignal }`, and returns an AI SDK 7 approval status synchronously or as a promise. Use `abortSignal` for asynchronous policy work so cancellation stops it with the turn. Use `ctx.session.auth.current` to guard by the caller of the current turn and `ctx.session.auth.initiator` to guard by the caller that created the session. Return `"user-approval"` to pause for a person or `"not-applicable"` to continue without a prompt. `toolInput` can be undefined, so guard the access. This policy denies cross-tenant calls, then requires approval only when an amount crosses a threshold:
+Use the object form of `approval` to replace the default `Approve <tool label>?` text with a tool-specific summary. The `prompt` callback receives the validated `input`, final `toolName`, and `callId`:
+
+```ts title="agent/tools/refund_charge.ts"
+import { defineTool } from "eve/tools";
+import { always } from "eve/tools/approval";
+import { z } from "zod";
+
+export default defineTool({
+  description: "Refund a charge.",
+  inputSchema: z.object({ chargeId: z.string(), amount: z.number() }),
+  approval: {
+    request: always(),
+    prompt: ({ input }) => `Refund $${input.amount.toFixed(2)} for charge ${input.chargeId}?`,
+  },
+  async execute(input) {
+    return refund(input);
+  },
+});
+```
+
+Channels render this prompt in their approval UI. Slack also includes the complete tool input in a collapsed **Tool input** block so an approver can inspect the original structured value.
+
+When the decision depends on the input, pass your own policy instead of a helper. It receives the same session context as tool execution, plus `{ toolName, toolInput, approvedTools, callId, abortSignal }` (connection tools also get `toolAnnotations`), and returns an AI SDK 7 approval status synchronously or as a promise. Use `abortSignal` for asynchronous policy work so cancellation stops it with the turn. Use `ctx.session.auth.current` to guard by the caller of the current turn and `ctx.session.auth.initiator` to guard by the caller that created the session. Return `"user-approval"` to pause for a person or `"not-applicable"` to continue without a prompt. `toolInput` can be undefined, so guard the access. This policy denies cross-tenant calls, then requires approval only when an amount crosses a threshold:
 
 ```ts
 approval: ({ session, toolInput }) => {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "eve",
-  "version": "0.78.0",
+  "version": "0.79.0",
   "private": false,
   "description": "Filesystem-first framework for durable backend AI agents that run anywhere.",
   "keywords": [
@@ -574,6 +574,7 @@
     "@chat-adapter/twilio": "4.41.0",
     "@clack/core": "1.3.1",
     "@eve/catalog": "0.0.1",
+    "@eve/tracing": "0.0.0",
     "@linqapp/chat-sdk-adapter": "^0.5.1",
     "@modelcontextprotocol/server": "2.0.0",
     "@nuxt/kit": "^4.0.0",

package/dist/src/tracing/agent-approval-instrumentation.d.ts

@@ -1,11 +0,0 @@
-import { type Tracer } from "#compiled/@opentelemetry/api/index.js";
-import type { InstrumentationProviderDefinition } from "#instrumentation/lifecycle.js";
-import type { AgentToolContext } from "#tracing/agent-tool-instrumentation.js";
-import type { AgentSpanIdGenerator } from "#tracing/agent-span-id-generator.js";
-/** Builds durable approval wait spans under their originating runtime action. */
-export declare function createAgentApprovalInstrumentation(input: {
-    readonly actionContextFor: (sessionId: string, turnId: string, callId: string) => Promise<AgentToolContext | undefined>;
-    readonly frameworkVersion: string;
-    readonly idGenerator: AgentSpanIdGenerator;
-    readonly tracer: Tracer;
-}): Pick<NonNullable<InstrumentationProviderDefinition["events"]>, "input.requested" | "input.resolved">;

package/dist/src/tracing/agent-approval-instrumentation.js

@@ -1 +0,0 @@
-import{normalizeChannelAudience}from"#shared/channel-audience.js";import{AGENT_SPAN_NAMES}from"#tracing/agent-span-contract.js";import{ROOT_CONTEXT,trace}from"#compiled/@opentelemetry/api/index.js";import{agentSpanNamingAttributes}from"#tracing/agent-span-naming.js";import{contentAttribute}from"#tracing/agent-otel-content.js";import{recordAgentSpanError}from"#tracing/agent-span-error.js";import{agentTraceIdentityAttributes,traceSessionIdOf}from"#tracing/agent-otel-attributes.js";import{decodeTraceSessionId}from"#tracing/agent-trace-context-codec.js";import{withChannelAudience}from"#tracing/channel-audience-context.js";function createAgentApprovalInstrumentation(e){return{"input.requested":async(t,n)=>{if(t.kind!==`tool-approval`||readState(n.state.get())!==void 0)return;let r=await e.actionContextFor(t.scope.sessionId,t.scope.turnId,t.action.callId);if(r===void 0)return;let i={actionCallId:t.action.callId,actionName:t.action.name,attemptIndex:t.scope.attemptIndex,channelAudience:normalizeChannelAudience(t.scope.channelAudience),parent:{spanId:r.spanContext.spanId,traceFlags:r.spanContext.traceFlags,traceId:r.spanContext.traceId},requestId:t.requestId,rootSessionId:t.scope.rootSessionId??t.scope.sessionId,traceSessionId:traceSessionIdOf(t.scope),sessionId:t.scope.sessionId,startTimeMs:Date.now(),stepIndex:t.scope.stepIndex,turnId:t.scope.turnId},a=contentAttribute(t.request);a!==void 0&&(i.requestAttribute=a),n.state.set(i)},"input.resolved":(t,n)=>{let r=readState(n.state.get());if(r===void 0)return;let i=e.idGenerator.withSpanId(e.idGenerator.deriveSpanId(`approval:${t.idempotencyKey}`),()=>e.tracer.startSpan(AGENT_SPAN_NAMES.approval,{attributes:{"gen_ai.tool.call.id":r.actionCallId,"agent.action.name":r.actionName,"agent.approval.kind":`tool-approval`,"agent.approval.outcome":t.outcome,"agent.approval.request_id":r.requestId,"agent.framework.name":`eve`,"agent.framework.version":e.frameworkVersion,"agent.step.attempt":r.attemptIndex,"agent.step.index":r.stepIndex,"agent.turn.id":r.turnId,"gen_ai.operation.name":`workflow`,...agentSpanNamingAttributes(`agent.approval`,`workflow`),...agentTraceIdentityAttributes({rootSessionId:r.rootSessionId,traceSessionId:r.traceSessionId,sessionId:r.sessionId})},startTime:r.startTimeMs},withChannelAudience(trace.setSpan(ROOT_CONTEXT,trace.wrapSpanContext({...r.parent,isRemote:!1})),r.channelAudience)));if(r.requestAttribute!==void 0&&i.setAttribute(`agent.approval.request`,r.requestAttribute),t.response!==void 0){let e=contentAttribute(t.response);e!==void 0&&i.setAttribute(`agent.approval.response`,e)}t.outcome===`failed`&&recordAgentSpanError(i,t.error),i.end()}}}function readState(e){if(typeof e!=`object`||!e||Array.isArray(e))return;let t=e,n=t.parent;if(typeof n!=`object`||!n||Array.isArray(n))return;let r=n;if(typeof t.actionCallId!=`string`||typeof t.actionName!=`string`||typeof t.attemptIndex!=`number`||typeof r.spanId!=`string`||typeof r.traceFlags!=`number`||typeof r.traceId!=`string`||typeof t.requestId!=`string`||typeof t.rootSessionId!=`string`||typeof t.sessionId!=`string`||typeof t.startTimeMs!=`number`||typeof t.stepIndex!=`number`||typeof t.turnId!=`string`)return;let i=t.requestAttribute;if(i===void 0||typeof i==`string`)return{actionCallId:t.actionCallId,actionName:t.actionName,attemptIndex:t.attemptIndex,channelAudience:normalizeChannelAudience(t.channelAudience),parent:{isRemote:!1,spanId:r.spanId,traceFlags:r.traceFlags,traceId:r.traceId},requestAttribute:i,requestId:t.requestId,rootSessionId:t.rootSessionId,traceSessionId:decodeTraceSessionId(t),sessionId:t.sessionId,startTimeMs:t.startTimeMs,stepIndex:t.stepIndex,turnId:t.turnId}}export{createAgentApprovalInstrumentation};

package/dist/src/tracing/agent-invocation-coordinator.js

@@ -1 +0,0 @@
-import{applyLiveDeliveryAudienceCeiling,readForwardedTraceAssertion}from"#shared/forwarded-trace-policy.js";import{ConversationIdKey}from"#context/keys.js";import{readConversationId}from"#shared/conversation-identity.js";import{readActionTraceContext,readTurnTraceContext}from"#tracing/agent-trace-context-store.js";function resolveToolCallAgentTrace(e){let{serializedContext:t,sessionId:n,turnId:r}=e;return toChildTraceDispatch({conversation:e.conversation,conversationId:readConversationId(t[ConversationIdKey.name]),stored:readActionTraceContext(t,n,r,e.callId)??readTurnTraceContext(t,n,r)})}function toChildTraceDispatch(e){let{stored:t}=e,n=e.conversation?.audience??`unknown`,r=e.conversation?.environment??`production`,i=readForwardedTraceAssertion(t?.forwardedTracePolicy),a=t?.decision===void 0?t:{...t,decision:applyLiveDeliveryAudienceCeiling(t.decision,n,i,r)};return{conversationId:e.conversationId,originAudience:i?.originAudience??n,parentTraceContext:a}}export{resolveToolCallAgentTrace};

package/dist/src/tracing/agent-memory-instrumentation.d.ts

@@ -1,16 +0,0 @@
-import { type Tracer } from "#compiled/@opentelemetry/api/index.js";
-import type { InstrumentationProviderDefinition } from "#instrumentation/lifecycle.js";
-import type { InstrumentationMemoryExecutionOperation } from "#instrumentation/memory.js";
-import type { AgentTraceStateStore } from "#tracing/agent-trace-state.js";
-import type { ConversationEnvironment } from "#shared/conversation-context.js";
-interface AgentMemoryInstrumentation {
-    readonly events: Pick<NonNullable<InstrumentationProviderDefinition["events"]>, "memory.operation.completed" | "memory.operation.failed" | "memory.operation.started">;
-    runInContext<T>(operation: InstrumentationMemoryExecutionOperation, execute: () => PromiseLike<T>): Promise<T>;
-}
-export declare function createAgentMemoryInstrumentation(input: {
-    readonly environment: ConversationEnvironment;
-    readonly recordOutputs?: boolean;
-    readonly stateStore: AgentTraceStateStore;
-    readonly tracer: Tracer;
-}): AgentMemoryInstrumentation;
-export {};

package/dist/src/tracing/agent-memory-instrumentation.js

@@ -1 +0,0 @@
-import{normalizeChannelAudience}from"#shared/channel-audience.js";import{applyLiveDeliveryAudienceCeiling,resolveForwardedTraceSeed}from"#shared/forwarded-trace-policy.js";import{contextStorage}from"#context/container.js";import{SessionTraceSeedKey}from"#context/keys.js";import{withOperationConversation}from"#tracing/conversation-context.js";import{isSampledTrace}from"#tracing/sampled-trace.js";import{ROOT_CONTEXT,SpanKind,context,trace}from"#compiled/@opentelemetry/api/index.js";import{isAgentTraceContext,markAgentTraceContext}from"#tracing/agent-trace-context.js";import{withErrorContent}from"#tracing/error-content-context.js";import{agentSpanNamingAttributes}from"#tracing/agent-span-naming.js";import{genAiMemoryRecordsAttribute}from"#tracing/agent-otel-content.js";import{recordAgentSpanError}from"#tracing/agent-span-error.js";import{agentTraceIdentityAttributes,traceSessionIdOf}from"#tracing/agent-otel-attributes.js";import{withChannelAudience}from"#tracing/channel-audience-context.js";import{suppressTracing}from"#tracing/suppress-tracing.js";function createAgentMemoryInstrumentation(e){let t=e.recordOutputs??!1,n=new Map,parentContext=async t=>{let n=context.active();if(isAgentTraceContext(n))return n;let r=await e.stateStore.getSession(t.sessionId);if(t.turnId!==void 0){let n=await e.stateStore.getTurn(t.sessionId,t.turnId);if(n!==void 0)return withChannelAudience(contextFromSpanContext(n.context),r?.channelAudience)}return r===void 0?void 0:withChannelAudience(contextFromSpanContext(r.context),r.channelAudience)},onStarted=async t=>{if(n.has(t.idempotencyKey))return;let r=await parentContext(t),i=r===void 0?void 0:trace.getSpan(r)?.spanContext();if(r===void 0||i===void 0||!isSampledTrace(i))return;let a=e.tracer.startSpan(t.operationName,{attributes:memorySpanAttributes(t),kind:SpanKind.CLIENT},r);n.set(t.idempotencyKey,{context:trace.setSpan(r,a),span:a})},onTerminal=e=>{let t=n.get(e.idempotencyKey);t!==void 0&&(n.delete(e.idempotencyKey),updateMemorySpan(t.span,e),t.span.end())};return{events:{"memory.operation.completed":onTerminal,"memory.operation.failed":onTerminal,"memory.operation.started":onStarted},async runInContext(r,i){let a=await e.stateStore.getSession(r.sessionId),o=n.get(r.idempotencyKey)?.context;if(o===void 0&&r.turnId!==void 0){let t=await e.stateStore.getTurn(r.sessionId,r.turnId);t!==void 0&&(o=withChannelAudience(contextFromSpanContext(t.context),a?.channelAudience),isSampledTrace(t.context)||(o=suppressTracing(o)))}o===void 0&&a!==void 0&&(o=withChannelAudience(contextFromSpanContext(a.context),a.channelAudience),isSampledTrace(a.context)||(o=suppressTracing(o)));let s=resolveForwardedTraceSeed(contextStorage.getStore()?.get(SessionTraceSeedKey)),c=s?.decision??a?.decision,l=c===void 0?void 0:applyLiveDeliveryAudienceCeiling(c,normalizeChannelAudience(a?.channelAudience),s?.forwardedTracePolicy,e.environment);return o===void 0?await i():await context.with(markAgentTraceContext(withErrorContent(withOperationConversation(o,{rootSessionId:a?.rootSessionId,sessionId:r.sessionId}),t&&l?.action===`record`&&l.recordOutputs)),i)}}}function memorySpanAttributes(e){let t={"agent.memory.phase":e.phase,"agent.memory.slot":e.slot,"gen_ai.memory.store.id":e.storeId,"gen_ai.operation.name":e.operationName,...agentSpanNamingAttributes(e.operationName,e.operationName),...agentTraceIdentityAttributes({rootSessionId:e.rootSessionId,traceSessionId:traceSessionIdOf(e),sessionId:e.sessionId})};return e.turnId!==void 0&&(t[`agent.turn.id`]=e.turnId),t}function updateMemorySpan(e,t){if(t.type===`memory.operation.failed`)recordAgentSpanError(e,t.error);else{t.recordCount!==void 0&&e.setAttribute(`gen_ai.memory.record.count`,t.recordCount);let n=genAiMemoryRecordsAttribute(t.outputRecords??[]);n!==void 0&&t.outputRecords!==void 0&&e.setAttribute(`gen_ai.memory.records`,n)}}function contextFromSpanContext(e){return trace.setSpan(ROOT_CONTEXT,trace.wrapSpanContext(e))}export{createAgentMemoryInstrumentation};

package/dist/src/tracing/agent-otel-attributes.d.ts

@@ -1,10 +0,0 @@
-export declare function traceSessionIdOf(scope: {
-    readonly traceSessionId?: string;
-    readonly rootSessionId?: string;
-    readonly sessionId: string;
-}): string;
-export declare function agentTraceIdentityAttributes(input: {
-    readonly rootSessionId: string;
-    readonly sessionId: string;
-    readonly traceSessionId: string;
-}): Record<string, string | number>;

package/dist/src/tracing/agent-otel-attributes.js

@@ -1 +0,0 @@
-import{AGENT_TRACE_SCHEMA_VERSION}from"#tracing/agent-span-contract.js";import{operationConversationId}from"#tracing/conversation-context.js";function traceSessionIdOf(e){return e.traceSessionId??e.rootSessionId??e.sessionId}function agentTraceIdentityAttributes(e){let t=operationConversationId(e),n={"agent.run.id":e.sessionId,"agent.trace.schema.version":AGENT_TRACE_SCHEMA_VERSION,"gen_ai.conversation.id":t};return process.env.VERCEL_ENV!==void 0&&(n[`vercel.session_id`]=e.traceSessionId),n}export{agentTraceIdentityAttributes,traceSessionIdOf};

package/dist/src/tracing/agent-otel-content.js

@@ -1,4 +0,0 @@
-import{isUserMessageKind}from"#harness/messages.js";const CONTENT_ATTRIBUTE_LIMIT=32768;function contentAttribute(e){if(e===void 0)return;let t;try{t=JSON.stringify(e)}catch{return}if(t!==void 0)return textContentAttribute(t)}function genAiInputMessagesAttribute(e){if(!Array.isArray(e))return;let t=e.flatMap(e=>{if(!isRecord(e)||e.role===`system`||typeof e.role!=`string`)return[];let t=semanticParts(e.content);if(t.length===0)return[];let n=e.role===`user`&&isUserMessageKind(e.kind)?e.kind:void 0;return[n===void 0?{parts:t,role:e.role}:{kind:n,parts:t,role:e.role}]});for(let e=0;e<t.length;e+=1){let n=semanticJsonAttribute(t.slice(e));if(n!==void 0)return n}return truncateSingleSemanticMessage(t)??semanticJsonAttribute([])}function genAiSystemInstructionsAttribute(e){let t=systemPromptText(e);if(t!==void 0)return fitSemanticText(t,e=>[{content:e,type:`text`}])}function genAiToolDefinitionsAttribute(e){if(!Array.isArray(e))return;let t=e.flatMap(e=>{if(!isRecord(e)||typeof e.name!=`string`)return[];let t={name:e.name};return typeof e.description==`string`&&(t.description=e.description),e.inputSchema!==void 0&&(t.parameters=e.inputSchema),[t]});if(t.length===0)return;let n=[],r=2;for(let e of t){let t=stringifyContent(e);if(t===void 0)break;let i=r+(n.length===0?0:1)+t.length;if(i>32768)break;n.push(t),r=i}return`[${n.join(`,`)}]`}function genAiOutputMessagesAttribute(e,t){let n=semanticParts(e);return semanticJsonAttribute([{finish_reason:t===`tool-calls`?`tool_call`:t,parts:n,role:`assistant`}])}function genAiMemoryRecordsAttribute(e){return semanticJsonAttribute(e)}function toolResultsContentAttribute(e){if(e.length===0)return;let t=stringifyContent(e);if(t!==void 0&&t.length<=32768)return t;for(let t=CONTENT_ATTRIBUTE_LIMIT;t>=0;t=t>=256?Math.floor(t/2):-1){let n=stringifyContent(e.map(e=>cappedToolResult(e,t)));if(n!==void 0&&n.length<=32768)return n}}function cappedToolResult(e,t){let n={toolName:e.toolName};for(let r of[`input`,`output`,`error`]){if(!(r in e))continue;let i=e[r],a=typeof i==`string`?i:stringifyContent(i)??``;n[r]=a.length<=t?a:`${a.slice(0,t)}… [truncated]`}return n}function systemPromptText(e){if(typeof e==`string`)return e.length===0?void 0:e;if(!isRecord(e)&&!Array.isArray(e))return;let t=Array.isArray(e)?e:[e],n=[];for(let e of t)if(isRecord(e)){if(typeof e.content==`string`)n.push(e.content);else if(Array.isArray(e.content))for(let t of e.content)isRecord(t)&&t.type===`text`&&typeof t.text==`string`&&n.push(t.text)}let r=n.join(`
-
-`).trim();return r.length===0?void 0:r}function textContentAttribute(e){if(e.length!==0)return e.length<=32768?e:`${e.slice(0,CONTENT_ATTRIBUTE_LIMIT)}… [truncated]`}function stringifyContent(e){try{return JSON.stringify(e)}catch{return}}function semanticJsonAttribute(e){let t=stringifyContent(e);return t!==void 0&&t.length<=32768?t:void 0}function truncateSingleSemanticMessage(e){let t=e.at(-1);if(t===void 0||typeof t.role!=`string`)return;let n=semanticMessageText(t.parts),r=typeof t.kind==`string`?{kind:t.kind,role:t.role}:{role:t.role};return fitSemanticText(n,e=>[{...r,parts:[{content:e,type:`text`}]}],!0)}function fitSemanticText(e,t,n=!1){if(!n&&e.length<=32768){let n=semanticJsonAttribute(t(e));if(n!==void 0)return n}for(let n=Math.min(e.length,CONTENT_ATTRIBUTE_LIMIT);n>0;n-=256){let r=semanticJsonAttribute(t(`${e.slice(0,n)}… [truncated]`));if(r!==void 0)return r}return semanticJsonAttribute(t(`… [truncated]`))}function semanticMessageText(e){if(!Array.isArray(e))return``;let t=``;for(let n of e){if(!isRecord(n)||n.type!==`text`||typeof n.content!=`string`)continue;let e=t.length===0?``:`
-`,r=32769-t.length-e.length;if(r<=0)break;t+=e+n.content.slice(0,r)}return t}function semanticParts(e){if(typeof e==`string`)return[{content:e,type:`text`}];if(!Array.isArray(e))return[];let t=[];for(let n of e){let e=semanticPart(n);e!==void 0&&t.push(e)}return t}function semanticPart(e){if(isRecord(e)&&typeof e.type==`string`)switch(e.type){case`text`:case`reasoning`:{let t=typeof e.text==`string`?e.text:e.content;return typeof t==`string`?{content:t,type:e.type}:void 0}case`tool-call`:return{arguments:e.input,id:stringValue(e.toolCallId)??stringValue(e.callId)??null,name:e.toolName,type:`tool_call`};case`tool-result`:return{id:stringValue(e.toolCallId)??stringValue(e.callId)??null,response:toolResponse(e.output),type:`tool_call_response`};case`tool-error`:return{id:stringValue(e.toolCallId)??stringValue(e.callId)??null,response:e.error instanceof Error?e.error.message:e.error,type:`tool_call_response`};default:return{type:e.type}}}function toolResponse(e){return isRecord(e)?(e.type===`text`||e.type===`error-text`||e.type===`json`||e.type===`error-json`)&&`value`in e?e.value:e.type===`execution-denied`?{denied:!0,reason:e.reason}:e:e}function stringValue(e){return typeof e==`string`?e:void 0}function isRecord(e){return typeof e==`object`&&!!e&&!Array.isArray(e)}export{CONTENT_ATTRIBUTE_LIMIT,contentAttribute,genAiInputMessagesAttribute,genAiMemoryRecordsAttribute,genAiOutputMessagesAttribute,genAiSystemInstructionsAttribute,genAiToolDefinitionsAttribute,textContentAttribute,toolResultsContentAttribute};

package/dist/src/tracing/agent-otel-provider.js

@@ -1,2 +0,0 @@
-import{normalizeChannelAudience}from"#shared/channel-audience.js";import{applyLiveDeliveryAudienceCeiling,resolveForwardedTraceSeed}from"#shared/forwarded-trace-policy.js";import{contextStorage}from"#context/container.js";import{SessionTraceSeedKey}from"#context/keys.js";import{AGENT_SPAN_NAMES,agentInvocationSpanName,modelSpanName}from"#tracing/agent-span-contract.js";import{resolveInstrumentationEnvironment}from"#internal/application/dev-environment.js";import{withOperationConversation}from"#tracing/conversation-context.js";import{isSampledTrace,resolveTracePolicyDecision}from"#tracing/sampled-trace.js";import{ROOT_CONTEXT,SpanKind,context,trace}from"#compiled/@opentelemetry/api/index.js";import{markAgentTraceContext}from"#tracing/agent-trace-context.js";import{attemptIdempotencyKey}from"#instrumentation/lifecycle.js";import{withoutInstrumentationContent}from"#instrumentation/content.js";import{withErrorContent}from"#tracing/error-content-context.js";import{readInstrumentationDecision}from"#shared/instrumentation-decision.js";import{agentSpanNamingAttributes}from"#tracing/agent-span-naming.js";import{contentAttribute,genAiInputMessagesAttribute,genAiOutputMessagesAttribute,genAiSystemInstructionsAttribute,genAiToolDefinitionsAttribute,textContentAttribute,toolResultsContentAttribute}from"#tracing/agent-otel-content.js";import{recordAgentSpanError}from"#tracing/agent-span-error.js";import{withAgentToolContentPolicy}from"#tracing/agent-tool-span-context.js";import{agentTraceIdentityAttributes,traceSessionIdOf}from"#tracing/agent-otel-attributes.js";import{withChannelAudience}from"#tracing/channel-audience-context.js";import{suppressTracing}from"#tracing/suppress-tracing.js";import{instrumentationEventForTraceDecision}from"#instrumentation/content-policy.js";import{createAgentApprovalInstrumentation}from"#tracing/agent-approval-instrumentation.js";import{createAgentChannelDeliveryInstrumentation}from"#tracing/agent-channel-delivery-instrumentation.js";import{createAgentToolInstrumentation}from"#tracing/agent-tool-instrumentation.js";import*as runtimeAttributes from"#tracing/agent-otel-runtime-context.js";import{createAgentMemoryInstrumentation}from"#tracing/agent-memory-instrumentation.js";import{readGatewayCost,setAgentInvocationUsage,setAgentUsage,setGenAiUsage}from"#tracing/agent-otel-usage.js";import{createAgentOtelSessionContext}from"#tracing/agent-otel-session-context.js";import{rememberTurnInputMessages,rememberTurnOutputMessages}from"#tracing/agent-otel-turn-state.js";function createAgentOtelInstrumentation(e){let t=e.environment??resolveInstrumentationEnvironment(),n=e.recordInputs??!1,r=e.recordOutputs??!1,i=new WeakMap,a=new Map,o=new WeakMap,s=new WeakMap,c=createAgentToolInstrumentation({frameworkVersion:e.frameworkVersion,idGenerator:e.idGenerator,recordInputs:n,recordOutputs:r,resolveTraceContext:async t=>(await e.stateStore.getTurn(t.scope.sessionId,t.scope.turnId))?.context,stateStore:e.stateStore,resolveFallback:e=>{let t=a.get(e.scope.attemptId)??e.scope,n=o.get(t);return n===void 0?void 0:{context:n.context,spanContext:n.span.spanContext()}},tracer:e.tracer}),l=createAgentApprovalInstrumentation({actionContextFor:c.dispatchContextFor,frameworkVersion:e.frameworkVersion,idGenerator:e.idGenerator,tracer:e.tracer}),u=createAgentMemoryInstrumentation({...e,environment:t}),{prepareSessionTrace:d,prepareTurnTrace:f}=createAgentOtelSessionContext({...e,environment:t}),projectEvent=async i=>{let a=await e.stateStore.getSession(sessionIdForEvent(i)),o=audienceForEvent(i,a?.channelAudience),s=`traceSeed`in i?i.traceSeed:void 0,c=contextStorage.getStore()?.get(SessionTraceSeedKey),l=resolveForwardedTraceSeed(c),u=resolveForwardedTraceSeed(s,l?.forwardedTracePolicy),decisionForTrace=e=>e===void 0?void 0:resolveTracePolicyDecision(isSampledTrace(e),{audience:o,environment:t}),d=u?.decision??l?.decision??readInstrumentationDecision(a?.decision)??decisionForTrace(s)??decisionForTrace(c)??decisionForTrace(a?.context);if(d===void 0)return withoutInstrumentationContent(i);let f=u===void 0||!(`traceSeed`in i)||i.traceSeed===void 0?i:{...i,traceSeed:{...i.traceSeed,decision:u.decision,traceFlags:u.traceFlags}};return instrumentationEventForTraceDecision(f,applyLiveDeliveryAudienceCeiling(d.action===`drop`?d:{action:`record`,recordInputs:n&&d.recordInputs,recordOutputs:r&&d.recordOutputs},o,u?.forwardedTracePolicy??l?.forwardedTracePolicy,t),{audience:o,environment:t},{applyAudienceCeiling:!1})},onSessionStarted=async e=>{await d(e)},onTurnStarted=async e=>{await f(e)},onStepStarted=async t=>{let n=await e.stateStore.getTurn(t.scope.sessionId,t.scope.turnId);if(n===void 0||!isSampledTrace(n.context))return;let r=await e.stateStore.getSession(t.scope.sessionId),i=withChannelAudience(contextFromSpanContext(n.context),t.scope.channelAudience),s=trace.getSpan(context.active())?.spanContext(),c=e.idGenerator.withSpanId(e.idGenerator.deriveSpanId(attemptIdempotencyKey(t.scope)),()=>e.tracer.startSpan(AGENT_SPAN_NAMES.step,{attributes:runtimeAttributes.agentStepAttributes({event:t,frameworkVersion:e.frameworkVersion,session:r,turn:n}),links:s===void 0||s.traceId===n.context.traceId?void 0:[{attributes:{"eve.link.type":`workflow.delivery`},context:s}]},i));c.addEvent(`step.started`);let l=trace.setSpan(i,c);o.set(t.scope,{context:l,span:c}),a.set(t.scope.attemptId,t.scope)},onStepTerminal=async e=>{let t=a.get(e.scope.attemptId)??e.scope;i.delete(t),drainOpenSpans({...e,scope:t}),c.drain(e.scope.attemptId,e.type===`step.attempt.failed`?{error:e.error}:void 0),e.type===`step.attempt.failed`&&await c.failForAttempt(t,e.error),a.delete(e.scope.attemptId);let n=o.get(t);n!==void 0&&(n.span.addEvent(e.type===`step.attempt.completed`?`step.completed`:`step.failed`),e.type===`step.attempt.failed`&&recordAgentSpanError(n.span,e.error),n.span.end(),o.delete(t))},onTurnTerminal=async t=>{await e.stateStore.updateTurn(t.sessionId,t.turnId,e=>({...e,terminal:t.type===`turn.failed`?{error:t.error,type:t.type}:{type:t.type}}))},onSessionTransition=async t=>{if(t.type===`session.failed`&&t.turnId!==void 0&&await e.stateStore.updateTurn(t.sessionId,t.turnId,e=>({...e,terminal:e.terminal??{error:t.error,type:`turn.failed`}})),t.turnId!==void 0){let n=await e.stateStore.getTurn(t.sessionId,t.turnId);if(n!==void 0){let r=await e.stateStore.getSession(t.sessionId);if(isSampledTrace(n.context)){let i=r?.agentName??n.subagentName,a=withChannelAudience(n.caller===void 0||n.caller.isRemote===!0?ROOT_CONTEXT:contextFromSpanContext(n.caller),r?.channelAudience),startSpan=()=>e.tracer.startSpan(agentInvocationSpanName(i),{attributes:runtimeAttributes.agentActivationAttributes({agentName:i,frameworkVersion:e.frameworkVersion,session:r,sessionId:t.sessionId,turnId:t.turnId,turn:n}),kind:SpanKind.INTERNAL,links:agentActivationLinks(n),root:n.caller===void 0||n.caller.isRemote===!0,startTime:n.startTimeMs},a),o=e.idGenerator.withSpanId(n.context.spanId,()=>e.idGenerator.withTraceId(n.context.traceId,startSpan));setAgentInvocationUsage(o,n.modelUsage),o.addEvent(`turn.started`,void 0,n.startTimeMs),n.terminal!==void 0&&(o.setAttribute(`agent.turn.outcome`,n.terminal.type===`turn.completed`?`completed`:n.terminal.type===`turn.cancelled`?`cancelled`:`failed`),o.addEvent(n.terminal.type),n.terminal.type===`turn.failed`&&recordAgentSpanError(o,n.terminal.error)),o.end()}await e.stateStore.deleteTurn(t.sessionId,t.turnId)}}(t.type===`session.completed`||t.type===`session.failed`)&&(await c.deleteForSession(t.sessionId),await e.stateStore.deleteSession(t.sessionId))},onModelCallStarted=t=>{let r=o.get(t.scope);if(r===void 0)return;r.span.setAttribute(`agent.model.id`,t.model.modelId);let i=e.tracer.startSpan(modelSpanName(t.model.modelId),{attributes:{"gen_ai.agent.name":t.scope.functionId,"gen_ai.operation.name":`chat`,"gen_ai.provider.name":t.model.provider,"gen_ai.request.model":t.model.modelId,...agentSpanNamingAttributes(modelSpanName(t.model.modelId),`chat`),...agentTraceIdentityAttributes({rootSessionId:t.scope.rootSessionId??t.scope.sessionId,traceSessionId:traceSessionIdOf(t.scope),sessionId:t.scope.sessionId}),...runtimeAttributes.runtimeContextAttributes(t.runtimeContext)},kind:SpanKind.CLIENT},r.context),a;if(n&&t.input!==void 0){a=genAiInputMessagesAttribute(t.input.messages),a!==void 0&&i.setAttribute(`gen_ai.input.messages`,a);let e=genAiSystemInstructionsAttribute(t.input.instructions);e!==void 0&&i.setAttribute(`gen_ai.system_instructions`,e);let n=genAiToolDefinitionsAttribute(t.input.tools);n!==void 0&&i.setAttribute(`gen_ai.tool.definitions`,n)}let c={context:trace.setSpan(r.context,i),span:i};return getExecutionContexts(t.scope).set(t.idempotencyKey,c.context),getSpanStates(s,t.scope).set(t.idempotencyKey,c),rememberTurnInputMessages(e.stateStore,t.scope,a)},onModelCallTerminal=async t=>{i.get(t.scope)?.delete(t.idempotencyKey);let n=takeSpanState(s,t.scope,t.idempotencyKey);if(n!==void 0){if(t.type===`model.call.failed`)recordAgentSpanError(n.span,t.error);else{await recordTurnUsage(t),setGenAiUsage(n.span,t.usage),t.responseId!==void 0&&n.span.setAttribute(`gen_ai.response.id`,t.responseId),t.responseModelId!==void 0&&n.span.setAttribute(`gen_ai.response.model`,t.responseModelId),n.span.setAttribute(`gen_ai.response.finish_reasons`,[t.finishReason]);let i=o.get(t.scope);if(i!==void 0&&setAgentUsage(i.span,t.usage),r){n.span.setAttribute(`ai.response.finish_reason`,t.finishReason);let r=t.content;if(r===void 0){n.span.end();return}let i=genAiOutputMessagesAttribute(r,t.finishReason);i!==void 0&&(n.span.setAttribute(`gen_ai.output.messages`,i),await rememberTurnOutputMessages(e.stateStore,t.scope,i));let a=textContentAttribute(r.filter(e=>e.type===`reasoning`).map(e=>e.text).filter(e=>e.trim().length>0).join(`
-`));a!==void 0&&n.span.setAttribute(`ai.response.reasoning`,a);let o=textContentAttribute(r.filter(e=>e.type===`text`).map(e=>e.text).join(``));o!==void 0&&n.span.setAttribute(`ai.response.text`,o);let s=r.filter(e=>e.type===`tool-call`).map(e=>({callId:e.callId,input:e.input,toolName:e.toolName}));if(s.length>0){let e=contentAttribute(s);e!==void 0&&n.span.setAttribute(`ai.response.tool_calls`,e)}let c=r.filter(e=>e.type===`tool-result`||e.type===`tool-error`).map(e=>e.type===`tool-result`?{callId:e.callId,input:e.input,output:e.output,toolName:e.toolName}:{callId:e.callId,error:errorText(e.error),input:e.input,toolName:e.toolName});if(c.length>0){let e=toolResultsContentAttribute(c);e!==void 0&&n.span.setAttribute(`ai.response.tool_results`,e)}}}n.span.end()}},recordTurnUsage=async t=>{(t.usage.inputTokens!==void 0||t.usage.outputTokens!==void 0)&&await e.stateStore.updateTurn(t.scope.sessionId,t.scope.turnId,e=>({...e,modelUsage:{inputTokens:t.usage.inputTokens===void 0?e.modelUsage?.inputTokens:(e.modelUsage?.inputTokens??0)+t.usage.inputTokens,outputTokens:t.usage.outputTokens===void 0?e.modelUsage?.outputTokens:(e.modelUsage?.outputTokens??0)+t.usage.outputTokens}}))},p=createAgentChannelDeliveryInstrumentation({recordInputs:n,stateStore:e.stateStore}),onStepMetadata=e=>{let t=o.get(e.scope);if(t===void 0)return;let n=readGatewayCost(e.providerMetadata);if(n!==void 0)for(let[e,r]of Object.entries(n))t.span.setAttribute(e,r)};return{hook:{events:{...p,...l,...u.events,"step.attempt.completed":onStepTerminal,"step.attempt.failed":onStepTerminal,"step.attempt.metadata":onStepMetadata,"step.attempt.started":onStepStarted,"model.call.completed":onModelCallTerminal,"model.call.failed":onModelCallTerminal,"model.call.started":onModelCallStarted,"session.completed":onSessionTransition,"session.failed":onSessionTransition,"session.started":onSessionStarted,"session.waiting":onSessionTransition,...c.events,"turn.cancelled":onTurnTerminal,"turn.completed":onTurnTerminal,"turn.failed":onTurnTerminal,"turn.started":onTurnStarted},name:`eve.otel`,projectEvent,tracePolicy:()=>({emit:!0,recordInputs:n,recordOutputs:r})},prepareSessionTrace:d,prepareTurnTrace:f,async runInContext(o,s){if(o.type===`memory.operation`)return u.runInContext(o,s);let l=a.get(o.scope.attemptId)??o.scope,d=i.get(l),f=o.type===`model.call`?d?.get(o.idempotencyKey):c.contextFor(o.scope.attemptId,o.idempotencyKey);if(f===void 0){let t=await e.stateStore.getTurn(o.scope.sessionId,o.scope.turnId);t!==void 0&&(f=withChannelAudience(contextFromSpanContext(t.context),o.scope.channelAudience),isSampledTrace(t.context)||(f=suppressTracing(f)))}let p=await e.stateStore.getSession(o.scope.sessionId),m=resolveForwardedTraceSeed(contextStorage.getStore()?.get(SessionTraceSeedKey)),h=m?.decision??p?.decision,g=h===void 0?void 0:applyLiveDeliveryAudienceCeiling(h,normalizeChannelAudience(o.scope.channelAudience),m?.forwardedTracePolicy,t),_={recordInputs:n&&g?.action===`record`&&g.recordInputs,recordOutputs:r&&g?.action===`record`&&g.recordOutputs},run=e=>{let t=e??f;if(t===void 0)return s();let n=withErrorContent(t,_.recordOutputs),r=o.type===`tool.call`?withAgentToolContentPolicy(n,_):n;return context.with(markAgentTraceContext(withOperationConversation(r,o.scope)),s)};return o.type===`tool.call`?c.runInContext({...o,input:_.recordInputs?o.input:void 0},run,_.recordOutputs):run(void 0)}};function getExecutionContexts(e){let t=i.get(e);return t===void 0&&(t=new Map,i.set(e,t)),t}function drainOpenSpans(e){for(let t of s.get(e.scope)?.values()??[])e.type===`step.attempt.failed`&&recordAgentSpanError(t.span,e.error),t.span.end();s.delete(e.scope)}}function agentActivationLinks(e){let t=[];return e.caller?.isRemote===!0&&t.push({context:e.caller,attributes:{"eve.link.type":`agent.dispatch`}}),e.channelDelivery?.requestTraceContext!==void 0&&t.push({context:e.channelDelivery.requestTraceContext,attributes:{"eve.link.type":`channel.request`}}),t.length===0?void 0:t}function sessionIdForEvent(e){return`scope`in e?e.scope.sessionId:e.sessionId}function audienceForEvent(e,t){return`delivery`in e?normalizeChannelAudience(e.delivery.channelAudience):`scope`in e&&e.scope.channelAudience!==void 0?normalizeChannelAudience(e.scope.channelAudience):e.type===`session.started`?normalizeChannelAudience(e.channelAudience):normalizeChannelAudience(t)}function getSpanStates(e,t){let n=e.get(t);return n===void 0&&(n=new Map,e.set(t,n)),n}function takeSpanState(e,t,n){let r=e.get(t),i=r?.get(n);if(r!==void 0)return r.delete(n),r.size===0&&e.delete(t),i}function contextFromSpanContext(e){return trace.setSpan(ROOT_CONTEXT,trace.wrapSpanContext(e))}const errorText=e=>e instanceof Error?e.message:e;export{createAgentOtelInstrumentation};

package/dist/src/tracing/agent-otel-runtime-context.d.ts

@@ -1,36 +0,0 @@
-import type { AgentSessionTraceState, AgentTurnTraceState } from "#tracing/agent-trace-state.js";
-import type { InstrumentationStepAttemptStartedEvent } from "#instrumentation/lifecycle.js";
-type SpanAttributePrimitive = string | number | boolean;
-type SpanAttributeValue = SpanAttributePrimitive | SpanAttributePrimitive[];
-export declare function agentActivationAttributes(input: {
-    readonly agentName?: string;
-    readonly frameworkVersion: string;
-    readonly session?: AgentSessionTraceState;
-    readonly sessionId: string;
-    readonly turnId: string;
-    readonly turn: AgentTurnTraceState;
-}): Record<string, string | number | boolean | undefined>;
-export declare function agentChannelClassificationAttributes(session: AgentSessionTraceState | undefined, turn: AgentTurnTraceState, sessionId: string): {
-    readonly "agent.channel.kind": string | undefined;
-    readonly "agent.session.origin": string | undefined;
-};
-export declare function agentStepAttributes(input: {
-    readonly event: InstrumentationStepAttemptStartedEvent;
-    readonly frameworkVersion: string;
-    readonly session?: AgentSessionTraceState;
-    readonly turn: AgentTurnTraceState;
-}): {
-    "agent.channel.kind"?: string | undefined;
-    "agent.session.origin"?: string | undefined;
-    "agent.framework.name": string;
-    "agent.framework.version": string;
-    "agent.step.attempt": number;
-    "agent.step.index": number;
-    "agent.turn.id": string;
-    "agent.name": string | undefined;
-    "gen_ai.operation.name": string;
-};
-export declare function agentPrincipalAttributes(turn: AgentTurnTraceState): Record<string, string>;
-/** Flattens merged runtime context into AI SDK-compatible span attributes. */
-export declare function runtimeContextAttributes(runtimeContext: Readonly<Record<string, unknown>> | undefined): Record<string, SpanAttributeValue>;
-export {};

package/dist/src/tracing/agent-otel-runtime-context.js

@@ -1 +0,0 @@
-import{normalizeInstrumentationChannelKind}from"#internal/instrumentation.js";import{agentInvocationSpanName}from"#tracing/agent-span-contract.js";import{agentSpanNamingAttributes}from"#tracing/agent-span-naming.js";import{agentTraceIdentityAttributes,traceSessionIdOf}from"#tracing/agent-otel-attributes.js";function agentActivationAttributes(e){let t=e.session?.decision?.action===`record`,n=t&&e.session?.decision?.recordInputs===!0,r=t&&e.session?.decision?.recordOutputs===!0,i=e.turn.parentLineage??e.session?.parentLineage,a=i!==void 0,o=!a||e.turn.traceSessionId===e.sessionId,s=agentChannelClassificationAttributes(e.session,e.turn,e.sessionId),c=a?void 0:e.session?.scheduleId;return{"agent.framework.name":`eve`,"agent.framework.version":e.frameworkVersion,"agent.name":e.agentName,"agent.channel.audience":e.session?.channelAudience,...agentPrincipalAttributes(e.turn),"agent.channel.delivery.id":e.turn.channelDelivery?.deliveryId,"agent.channel.delivery.input":e.turn.channelDelivery?.inputAttribute,...s,"agent.channel.name":e.turn.channelDelivery?.channelName,"agent.channel.request.id":e.turn.channelDelivery?.requestId,"agent.parent_call.id":i?.callId,"agent.parent_run.id":i?.sessionId,"agent.run.type":a?`subagent`:`session`,"agent.schedule.id":c,"agent.session.title":o&&n?e.session?.title:void 0,"agent.subagent.name":e.turn.subagentName,"agent.trace.content.input":n,"agent.trace.content.output":r,"agent.turn.id":e.turnId,"agent.turn.sequence":e.turn.sequence,"gen_ai.agent.name":e.agentName,"gen_ai.input.messages":e.turn.inputMessagesAttribute,"gen_ai.operation.name":`invoke_agent`,"gen_ai.output.messages":e.turn.outputMessagesAttribute,...agentSpanNamingAttributes(agentInvocationSpanName(e.agentName),`invoke_agent`),...agentTraceIdentityAttributes({rootSessionId:e.turn.rootSessionId,traceSessionId:e.turn.traceSessionId,sessionId:e.sessionId})}}function agentChannelClassificationAttributes(e,t,n){let r=(t.parentLineage??e?.parentLineage)===void 0||t.traceSessionId===n,i=t.channelDelivery?.channelKind??(r?e?.channelKind??(e?.channelType===void 0?void 0:normalizeInstrumentationChannelKind(e.channelType)):void 0);return{"agent.channel.kind":i,"agent.session.origin":!r||i===void 0?void 0:e?.scheduleId===void 0?`channel`:`schedule`}}function agentStepAttributes(e){let{event:t,session:n,turn:r}=e,i=agentChannelClassificationAttributes(n,r,t.scope.sessionId);return{"agent.framework.name":`eve`,"agent.framework.version":e.frameworkVersion,"agent.step.attempt":t.scope.attemptIndex,"agent.step.index":t.scope.stepIndex,"agent.turn.id":t.scope.turnId,"agent.name":t.scope.functionId,...i[`agent.channel.kind`]===`unknown`?void 0:i,"gen_ai.operation.name":`workflow`,...agentSpanNamingAttributes(`agent.step`,`workflow`),...agentTraceIdentityAttributes({rootSessionId:t.scope.rootSessionId??t.scope.sessionId,traceSessionId:traceSessionIdOf(t.scope),sessionId:t.scope.sessionId}),...runtimeContextAttributes(t.runtimeContext)}}function agentPrincipalAttributes(e){let t={};return setOptionalAttribute(t,`agent.principal.current.id`,e.currentPrincipal?.id),setOptionalAttribute(t,`agent.principal.current.type`,e.currentPrincipal?.type),setOptionalAttribute(t,`agent.principal.initiator.id`,e.initiatorPrincipal?.id),setOptionalAttribute(t,`agent.principal.initiator.type`,e.initiatorPrincipal?.type),t}function runtimeContextAttributes(e){let t={};if(e===void 0)return t;for(let[n,r]of Object.entries(e))flattenContextAttribute(t,`ai.settings.context.${n}`,r);return t}function flattenContextAttribute(e,t,n){if(n!=null){if(typeof n==`string`||typeof n==`number`||typeof n==`boolean`){e[t]=n;return}if(Array.isArray(n)){let r=n.filter(e=>typeof e==`string`||typeof e==`number`||typeof e==`boolean`);if(r.length!==n.length||new Set(r.map(e=>typeof e)).size!==1)return;e[t]=r;return}if(typeof n==`object`)for(let[r,i]of Object.entries(n))flattenContextAttribute(e,`${t}.${r}`,i)}}function setOptionalAttribute(e,t,n){n!==void 0&&(e[t]=n)}export{agentActivationAttributes,agentChannelClassificationAttributes,agentPrincipalAttributes,agentStepAttributes,runtimeContextAttributes};

package/dist/src/tracing/agent-otel-session-context.d.ts

@@ -1,22 +0,0 @@
-import { type InstrumentationSessionStartedEvent, type InstrumentationTraceSeed, type InstrumentationTurnStartedEvent } from "#instrumentation/lifecycle.js";
-import type { AgentSpanIdGenerator } from "#tracing/agent-span-id-generator.js";
-import type { TraceCapturePolicy } from "#tracing/otel-declaration.js";
-import type { AgentSessionTraceState, AgentTraceStateStore } from "#tracing/agent-trace-state.js";
-import { type AgentSamplingOperation } from "#tracing/agent-span-contract.js";
-import type { ConversationEnvironment } from "#shared/conversation-context.js";
-interface AgentOtelSessionContextInput {
-    readonly environment: ConversationEnvironment;
-    readonly frameworkVersion: string;
-    readonly idGenerator: AgentSpanIdGenerator;
-    readonly samplesTrace?: (traceId: string, operation?: AgentSamplingOperation) => boolean;
-    readonly stateStore: AgentTraceStateStore;
-    readonly tracePolicy?: TraceCapturePolicy;
-}
-type SessionMetadata = Omit<InstrumentationSessionStartedEvent, "idempotencyKey" | "type">;
-interface AgentOtelSessionContext {
-    readonly ensureSessionContext: (event: SessionMetadata) => Promise<AgentSessionTraceState>;
-    readonly prepareSessionTrace: (event: InstrumentationSessionStartedEvent) => Promise<InstrumentationTraceSeed>;
-    readonly prepareTurnTrace: (event: InstrumentationTurnStartedEvent) => Promise<InstrumentationTraceSeed>;
-}
-export declare function createAgentOtelSessionContext(input: AgentOtelSessionContextInput): AgentOtelSessionContext;
-export {};

package/dist/src/tracing/agent-otel-session-context.js

@@ -1 +0,0 @@
-import{normalizeChannelAudience}from"#shared/channel-audience.js";import{normalizeInstrumentationChannelKind}from"#internal/instrumentation.js";import{agentInvocationSpanName}from"#tracing/agent-span-contract.js";import{isSampledTrace,resolveTracePolicy,resolveTracePolicyDecision}from"#tracing/sampled-trace.js";import"#instrumentation/lifecycle.js";import{readInstrumentationDecision}from"#shared/instrumentation-decision.js";import{applyPrincipalTraceDecision}from"#instrumentation/principal-summary.js";import{traceSessionIdOf}from"#tracing/agent-otel-attributes.js";import{agentActivationAttributes}from"#tracing/agent-otel-runtime-context.js";function createAgentOtelSessionContext(e){let ensureSessionContext=async t=>{let n=await e.stateStore.getSession(t.sessionId);if(n===void 0){let r=normalizeChannelAudience(t.channelAudience),i=resolveSessionTraceDecision(t,r,e.environment,e.tracePolicy);n={agentName:t.agentName,channelAudience:r,channelKind:t.channelKind,channelType:t.channelType,decision:i,context:initialSessionContext(e,t,i),parentLineage:t.parentLineage,rootSessionId:t.rootSessionId,traceSessionId:traceSessionIdOf(t),scheduleId:t.scheduleId,title:t.title},await e.stateStore.setSession(t.sessionId,n)}return n};return{ensureSessionContext,prepareSessionTrace:async e=>{let t=await ensureSessionContext(e);return portableSpanContext(t.context,t.decision)},prepareTurnTrace:async t=>{let n=await e.stateStore.getTurn(t.sessionId,t.turnId);if(n!==void 0){let r=await e.stateStore.getSession(t.sessionId);return portableSpanContext(n.context,r?.decision)}let r=await ensureSessionContext(t),i=t.sequence===0,a=i?t.parentTraceContext:void 0,o=i?{...r.context,isRemote:!1}:freshTurnContext(e,t.idempotencyKey,r.decision);a!==void 0&&!(`isRemote`in a&&a.isRemote===!0)&&(o={...o,traceId:a.traceId});let s={caller:a===void 0?void 0:adoptedSpanContext(a),context:o,currentPrincipal:applyPrincipalTraceDecision(t.currentPrincipal,r.decision),initiatorPrincipal:applyPrincipalTraceDecision(t.initiatorPrincipal,r.decision),parentLineage:t.parentLineage??r.parentLineage,rootSessionId:t.rootSessionId,traceSessionId:traceSessionIdOf(t),sequence:t.sequence,startTimeMs:Date.now(),subagentName:(t.parentLineage??r.parentLineage)?.subagentName};if(isSampledTrace(s.context)&&(a===void 0||`isRemote`in a&&a.isRemote===!0)){let n=r.agentName??s.subagentName,i=e.samplesTrace?.(s.context.traceId,{name:agentInvocationSpanName(n),attributes:agentActivationAttributes({agentName:n,frameworkVersion:e.frameworkVersion,session:r,sessionId:t.sessionId,turnId:t.turnId,turn:s})})??!0;o={...o,traceFlags:+!!i}}return await e.stateStore.setTurn(t.sessionId,t.turnId,{...s,context:o}),portableSpanContext(o,r.decision)}}}function portableSpanContext(e,t){return{decision:t,spanId:e.spanId,traceFlags:e.traceFlags,traceId:e.traceId}}function adoptedSpanContext(e){return{isRemote:`isRemote`in e&&e.isRemote===!0,spanId:e.spanId,traceFlags:e.traceFlags,traceId:e.traceId}}function initialSessionContext(e,t,n){let r=t.traceSeed;if(r!==void 0)return{...adoptedSpanContext(r),traceFlags:n.action===`drop`?0:r.traceFlags};let i=(t.parentTraceContext!==void 0&&`isRemote`in t.parentTraceContext&&t.parentTraceContext.isRemote===!0?void 0:t.parentTraceContext?.traceId)??e.idGenerator.deriveTraceId(`session:${t.sessionId}`),a=n.action===`record`;return{isRemote:!1,spanId:e.idGenerator.deriveSpanId(`session:${t.sessionId}`),traceFlags:+!!a,traceId:i}}function freshTurnContext(e,t,n){let r=e.idGenerator.deriveTraceId(`turn:${t}`),i=n?.action===`record`;return{isRemote:!1,spanId:e.idGenerator.deriveSpanId(`turn:${t}`),traceFlags:+!!i,traceId:r}}function resolveSessionTraceDecision(e,t,n,r){let i={audience:t,environment:n};return e.parentTraceContext!==void 0&&!isSampledTrace(e.parentTraceContext)?{action:`drop`}:e.traceSeed?.decision===void 0?e.traceSeed===void 0?e.parentTraceContext===void 0?e.agentName===void 0?r===void 0?resolveTracePolicyDecision(!0,i):{action:`drop`}:resolveTracePolicy(r,{agentName:e.agentName,audience:t,channel:{kind:normalizeInstrumentationChannelKind(e.channelKind??e.channelType)},environment:n,principalType:`unknown`}):resolveTracePolicyDecision(isSampledTrace(e.parentTraceContext),i):resolveTracePolicyDecision(isSampledTrace(e.traceSeed),i):readInstrumentationDecision(e.traceSeed.decision)??{action:`drop`}}export{createAgentOtelSessionContext};

package/dist/src/tracing/agent-otel-turn-state.d.ts

@@ -1,6 +0,0 @@
-import type { InstrumentationAttemptScope } from "#instrumentation/lifecycle.js";
-import type { AgentTraceStateStore } from "#tracing/agent-trace-state.js";
-/** Keeps the first model input so the turn-level invoke_agent span represents its task. */
-export declare function rememberTurnInputMessages(store: AgentTraceStateStore, scope: InstrumentationAttemptScope, inputMessagesAttribute: string | undefined): void | PromiseLike<void>;
-/** Keeps the latest model output so the completed invoke_agent span represents its result. */
-export declare function rememberTurnOutputMessages(store: AgentTraceStateStore, scope: InstrumentationAttemptScope, outputMessagesAttribute: string | undefined): void | PromiseLike<void>;

package/dist/src/tracing/agent-otel-turn-state.js

@@ -1 +0,0 @@
-function rememberTurnInputMessages(e,t,n){if(n!==void 0)return e.updateTurn(t.sessionId,t.turnId,e=>({...e,inputMessagesAttribute:e.inputMessagesAttribute??n}))}function rememberTurnOutputMessages(e,t,n){if(n!==void 0)return e.updateTurn(t.sessionId,t.turnId,e=>({...e,outputMessagesAttribute:n}))}export{rememberTurnInputMessages,rememberTurnOutputMessages};

package/dist/src/tracing/agent-otel-usage.d.ts

@@ -1,10 +0,0 @@
-import type { Span } from "#compiled/@opentelemetry/api/index.js";
-import type { InstrumentationUsage } from "#instrumentation/lifecycle.js";
-import type { AgentTurnTraceState } from "#tracing/agent-trace-state.js";
-/** Applies eve's structural token usage attributes to an agent span. */
-export declare function setAgentUsage(span: Span, usage: InstrumentationUsage): void;
-/** Applies standard GenAI token usage and retains eve's cost attribute. */
-export declare function setGenAiUsage(span: Span, usage: InstrumentationUsage): void;
-export declare function setAgentInvocationUsage(span: Span, modelUsage: AgentTurnTraceState["modelUsage"]): void;
-/** Projects Vercel AI Gateway cost metadata onto GenAI span attributes. */
-export declare function readGatewayCost(providerMetadata: Readonly<Record<string, unknown>>): Record<string, string | number> | undefined;

package/dist/src/tracing/agent-otel-usage.js

@@ -1 +0,0 @@
-import{AGENT_USAGE_ATTRIBUTES}from"#tracing/agent-span-contract.js";function setAgentUsage(e,t){t.costUsd!==void 0&&e.setAttribute(AGENT_USAGE_ATTRIBUTES.costUsd,t.costUsd),t.inputTokens!==void 0&&e.setAttribute(AGENT_USAGE_ATTRIBUTES.inputTokens,t.inputTokens),t.outputTokens!==void 0&&e.setAttribute(AGENT_USAGE_ATTRIBUTES.outputTokens,t.outputTokens);let n=t.inputTokenDetails;n?.cacheReadTokens!==void 0&&e.setAttribute(AGENT_USAGE_ATTRIBUTES.cacheReadTokens,n.cacheReadTokens),n?.cacheWriteTokens!==void 0&&e.setAttribute(AGENT_USAGE_ATTRIBUTES.cacheWriteTokens,n.cacheWriteTokens)}function setGenAiUsage(e,t){t.costUsd!==void 0&&e.setAttribute(AGENT_USAGE_ATTRIBUTES.costUsd,t.costUsd),t.inputTokens!==void 0&&e.setAttribute(`gen_ai.usage.input_tokens`,t.inputTokens),t.outputTokens!==void 0&&e.setAttribute(`gen_ai.usage.output_tokens`,t.outputTokens);let n=t.inputTokenDetails;n?.cacheReadTokens!==void 0&&e.setAttribute(`gen_ai.usage.cache_read.input_tokens`,n.cacheReadTokens),n?.cacheWriteTokens!==void 0&&e.setAttribute(`gen_ai.usage.cache_write.input_tokens`,n.cacheWriteTokens)}function setAgentInvocationUsage(e,t){t!==void 0&&setGenAiUsage(e,t)}function readGatewayCost(e){let t=e.gateway;if(!isRecord(t))return;let n={},r=readUsd(t.cost);r!==void 0&&(n[`gen_ai.usage.cost`]=r);let i=readUsd(t.gatewayCost);i!==void 0&&(n[`gen_ai.usage.gateway_cost`]=i);let a=readUsd(t.inputInferenceCost);a!==void 0&&(n[`gen_ai.usage.input_cost`]=a);let o=readUsd(t.outputInferenceCost);return o!==void 0&&(n[`gen_ai.usage.output_cost`]=o),typeof t.generationId==`string`&&t.generationId.length>0&&(n[`gen_ai.generation.id`]=t.generationId),Object.keys(n).length===0?void 0:n}function readUsd(e){if(typeof e!=`string`)return;let t=Number(e);return Number.isFinite(t)?t:void 0}function isRecord(e){return typeof e==`object`&&!!e&&!Array.isArray(e)}export{readGatewayCost,setAgentInvocationUsage,setAgentUsage,setGenAiUsage};