@cubicecho/agent-core 4.9.0 → 4.10.0

package/README.md

@@ -623,6 +623,29 @@ a `tool-call` and a `tool-result` event, told to `onToolCall` and `onToolResult`
 id is numbered by where the call lands in the transcript, so two questions do not share one. A name
 with no definition in `tools`, or outside the catalogue, is left out, and none left is no exchange.
 
+### What the servers said on the way
+
+A server can log while a call runs — a warning that the cache was stale, an error it recovered
+from — and that is often why the call went the way it did. `dispatch` is handed a third argument,
+`report`, and `report.log(entry)` tells watchers of one such message as a `server-log` event for
+the call: `id` the call's, `name` the tool, `level` the server's, and `text` the message's `data`,
+as it was where a string and as JSON otherwise, cut by `preview`. The entry is MCP's
+`notifications/message` params, `{ level, logger?, data }`, declared structurally, so
+agent-mcp-pool's `onLog` takes `report.log` as it stands:
+
+```ts
+dispatch: (call, signal, report) =>
+  pool.call(call.name, call.args, { servers, signal, onLog: report.log }),
+```
+
+None of it reaches the transcript: it is for the person watching, not the model. A call the loop
+answers itself never logs, a deduplicated repeat reports nothing of its own, and a message heard
+after the call has answered is dropped rather than landing after the result it explains.
+`runMetrics` counts `warning` as `serverWarnings` and `error` and above as `serverErrors`, so a
+summary can say the server complained without the events. A dispatcher written for
+`(call, signal)` needs no change. `report` is an object so that what a call can report — progress
+is next — grows there without `dispatch` changing again.
+
 ### What the servers say about themselves
 
 An MCP server may send `instructions` when it connects — "resolve the library id before querying

package/dist/index.d.ts

@@ -39,5 +39,5 @@ export { backoffMs, ContextOverflow, EndpointSilent, isModelLoading, isOverflow,
 export { CacheBreakReason, type Produced, type StreamTurnOptions, streamTurn, type Turn, type TurnUsage, } from './wire/stream.ts';
 export { ALL_FENCES, DEFAULT_FENCES, type Fence, FenceSplitter, type FenceSplitterOptions, SPLIT_OUTPUT, SPLIT_REASONING, type Split, stripThinking, THINK_FENCE, } from './wire/thinking.ts';
 export { type ContextBreakdown, type ContextBreakdownOptions, compact, contextChars, contextTokens, estimateTokens, messageTokens, requestChars, requestTokens, type TokenEstimateOptions, } from './wire/tokens.ts';
-export { ARGUMENTS_MALFORMED, ARGUMENTS_TRUNCATED, parseToolArguments, type ResourceLink, type RunArtifact, recoverToolCalls, type ToolAnswer, ToolArgumentsError, type ToolCall, type ToolCallOutcome, type ToolCallRequest, type ToolCallResult, } from './wire/tool-calls.ts';
+export { ARGUMENTS_MALFORMED, ARGUMENTS_TRUNCATED, parseToolArguments, type ResourceLink, type RunArtifact, recoverToolCalls, type ServerLogEntry, ServerLogLevel, type ToolAnswer, ToolArgumentsError, type ToolCall, type ToolCallOutcome, type ToolCallReport, type ToolCallRequest, type ToolCallResult, } from './wire/tool-calls.ts';
 export { FinishReason, FUNCTION_TOOL, JSON_SCHEMA_FORMAT, PartType, Role, SchemaType } from './wire/wire.ts';

package/dist/index.js

@@ -38,5 +38,5 @@ export { backoffMs, ContextOverflow, EndpointSilent, isModelLoading, isOverflow,
 export { CacheBreakReason, streamTurn, } from './wire/stream.js';
 export { ALL_FENCES, DEFAULT_FENCES, FenceSplitter, SPLIT_OUTPUT, SPLIT_REASONING, stripThinking, THINK_FENCE, } from './wire/thinking.js';
 export { compact, contextChars, contextTokens, estimateTokens, messageTokens, requestChars, requestTokens, } from './wire/tokens.js';
-export { ARGUMENTS_MALFORMED, ARGUMENTS_TRUNCATED, parseToolArguments, recoverToolCalls, ToolArgumentsError, } from './wire/tool-calls.js';
+export { ARGUMENTS_MALFORMED, ARGUMENTS_TRUNCATED, parseToolArguments, recoverToolCalls, ServerLogLevel, ToolArgumentsError, } from './wire/tool-calls.js';
 export { FinishReason, FUNCTION_TOOL, JSON_SCHEMA_FORMAT, PartType, Role, SchemaType } from './wire/wire.js';

package/dist/run/events.d.ts

@@ -1,7 +1,7 @@
 import type { TokenLedger } from '../context/ledger.ts';
 import type { TurnUsage } from '../wire/stream.ts';
 import { CacheBreakReason } from '../wire/stream.ts';
-import type { ResourceLink } from '../wire/tool-calls.ts';
+import { type ResourceLink } from '../wire/tool-calls.ts';
 /**
  * What a run is doing, while it is doing it.
  *
@@ -96,6 +96,13 @@ export declare const RunEventKind: {
      * per uri per run: a later call that links the same uri again only adds to its count.
      */
     readonly Artifact: 'artifact';
+    /**
+     * A tool's server logged something while a call was running, which the dispatcher passed on
+     * through `report.log`. `id` is the call's, `name` the tool, `level` the server's, and `text`
+     * the message's data — as it was where a string, as JSON otherwise — cut by `preview`. Never in
+     * the transcript, and never from a call the loop answers itself.
+     */
+    readonly ServerLog: 'server-log';
     /**
      * What the run has cost so far, at the end of every turn, and what that one turn did. Sent
      * whether or not the endpoint reported tokens, since the timings and the cache comparison are
@@ -187,6 +194,11 @@ export interface RunEvent {
      * an event built before it existed still compiles.
      */
     link?: ResourceLink;
+    /**
+     * The level the server logged at, on `server-log` and on no other kind. Optional for the reason
+     * `id` is.
+     */
+    level?: string;
 }
 /**
  * What `emit` is given: the run and the sequence are the bus's to assign.
@@ -314,6 +326,10 @@ export interface RunMetrics {
     loadCalls: number;
     /** `artifact` events: the distinct things the run's tool calls linked to. */
     artifacts: number;
+    /** `server-log` events at `warning`. */
+    serverWarnings: number;
+    /** `server-log` events at `error` or above: `critical`, `alert` and `emergency` with it. */
+    serverErrors: number;
     /**
      * Tools `load_tools` loaded that were not loaded already. Filled by `runAgentLoop`, which sees
      * the resolution; the events carry only its text.

package/dist/run/events.js

@@ -3,6 +3,7 @@ import { ABORT_EVENT, MS_PER_MINUTE } from '../core/platform.js';
 import { assignSettings, scoped } from '../core/scope.js';
 import { LOAD_TOOLS } from '../tools/tool-loading.js';
 import { CacheBreakReason } from '../wire/stream.js';
+import { ServerLogLevel } from '../wire/tool-calls.js';
 import { FinishReason } from '../wire/wire.js';
 /** How many minutes an unended run's events are kept, absent a `retainUnendedMs`. */
 const RETAIN_UNENDED_MINUTES = 30;
@@ -62,6 +63,13 @@ export const RunEventKind = {
      * per uri per run: a later call that links the same uri again only adds to its count.
      */
     Artifact: 'artifact',
+    /**
+     * A tool's server logged something while a call was running, which the dispatcher passed on
+     * through `report.log`. `id` is the call's, `name` the tool, `level` the server's, and `text`
+     * the message's data — as it was where a string, as JSON otherwise — cut by `preview`. Never in
+     * the transcript, and never from a call the loop answers itself.
+     */
+    ServerLog: 'server-log',
     /**
      * What the run has cost so far, at the end of every turn, and what that one turn did. Sent
      * whether or not the endpoint reported tokens, since the timings and the cache comparison are
@@ -453,6 +461,10 @@ export function fold(events) {
     close();
     return blocks;
 }
+/** The log levels quietest first, which is what makes "warning and above" a comparison. */
+const SEVERITY = Object.values(ServerLogLevel);
+/** Where `warning` sits in `SEVERITY`: a level past it is an error. */
+const WARNING = SEVERITY.indexOf(ServerLogLevel.Warning);
 /** How a run ended, as `runMetrics` reads it. */
 export const RunOutcome = {
     /** The run did not fail, and its last turn was not cut off. */
@@ -507,6 +519,8 @@ export function runMetrics(events, { contextLength } = {}) {
         toolErrors: {},
         loadCalls: 0,
         artifacts: 0,
+        serverWarnings: 0,
+        serverErrors: 0,
         promptTokens: 0,
         completionTokens: 0,
         cachedTokens: 0,
@@ -550,6 +564,15 @@ export function runMetrics(events, { contextLength } = {}) {
         else if (event.kind === RunEventKind.Artifact) {
             metrics.artifacts++;
         }
+        else if (event.kind === RunEventKind.ServerLog) {
+            const severity = SEVERITY.indexOf(event.level ?? '');
+            if (severity === WARNING) {
+                metrics.serverWarnings++;
+            }
+            else if (severity > WARNING) {
+                metrics.serverErrors++;
+            }
+        }
         else if (event.kind === RunEventKind.Usage && event.usage?.turn) {
             const turn = event.usage.turn;
             last = turn;

package/dist/run/run-calls.d.ts

@@ -1,7 +1,7 @@
 import type OpenAI from 'openai';
 import type { CatalogServer } from '../tools/catalog.ts';
 import type { Turn } from '../wire/stream.ts';
-import { type RunArtifact, type ToolAnswer, type ToolCall, type ToolCallOutcome, type ToolCallRequest, type ToolCallResult } from '../wire/tool-calls.ts';
+import { type RunArtifact, type ToolAnswer, type ToolCall, type ToolCallOutcome, type ToolCallReport, type ToolCallRequest, type ToolCallResult } from '../wire/tool-calls.ts';
 import type { RunEventInput } from './events.ts';
 /**
  * The tools between two turns: a step's calls read, run and written into the transcript.
@@ -66,8 +66,13 @@ export declare const definedAs: (definitions: ReadonlyMap<string, OpenAI.ChatCom
 /**
  * Runs one tool call and resolves to what the model reads, alone or with what the call produced;
  * what it throws, the model reads too.
+ *
+ * @remarks
+ * `report` is how the call tells watchers what its server said on the way, and a dispatcher with
+ * nothing to report leaves it off: one written for `(call, signal)` is a `ToolDispatch` still.
+ * `signal` is `undefined` rather than optional so that `report` can follow it.
  */
-export type ToolDispatch = (call: ToolCallRequest, signal?: AbortSignal) => Promise<string | ToolAnswer>;
+export type ToolDispatch = (call: ToolCallRequest, signal: AbortSignal | undefined, report: ToolCallReport) => Promise<string | ToolAnswer>;
 /**
  * What running a step's calls reads of the run and writes back into it. One per run, shared by
  * every step: the sets and counts here are the run's own, not copies.

package/dist/run/run-calls.js

@@ -84,6 +84,46 @@ export const assistantMessage = (content, parsed) => ({
  * @returns A new array of the definitions themselves, not copies.
  */
 export const definedAs = (definitions, names) => [...names].flatMap((name) => definitions.get(name) ?? []);
+/**
+ * A server's log message as the text of its event.
+ *
+ * @param data - What the server sent: a string, or any JSON value.
+ * @returns A string as it was, anything else as JSON, cut by `preview`. What JSON cannot spell is
+ * shown as `String` shows it.
+ */
+function logText(data) {
+    if (typeof data === 'string') {
+        return preview(data);
+    }
+    try {
+        return preview(JSON.stringify(data) ?? String(data));
+    }
+    catch {
+        return preview(String(data));
+    }
+}
+/**
+ * What one call's dispatcher may report through, and the switch that closes it once it has answered.
+ *
+ * @param run - The run, whose watchers hear what is reported.
+ * @param id - The call's id, which every event it reports carries.
+ * @param name - The tool the call is shown as.
+ * @returns The report to hand `dispatch`, and `close`, after which it reports nothing.
+ */
+function reportFor(run, id, name) {
+    let isOpen = true;
+    const log = ({ level, data }) => {
+        if (isOpen) {
+            run.onEvent({ kind: RunEventKind.ServerLog, id, name, level, text: logText(data) });
+        }
+    };
+    return {
+        report: { log },
+        close: () => {
+            isOpen = false;
+        },
+    };
+}
 /**
  * A dispatcher's answer in the one shape, whichever it gave.
  *
@@ -293,6 +333,7 @@ async function runCall(run, prepared, answered, step) {
     const { name, raw } = request;
     run.onEvent({ kind: RunEventKind.ToolCall, id: call.id, name, text: preview(raw) });
     run.onToolCall?.(request);
+    const { report, close } = reportFor(run, call.id, name);
     let content;
     let links = [];
     let ok = true;
@@ -318,9 +359,11 @@ async function runCall(run, prepared, answered, step) {
             run.used.add(name);
             // Read before `once` looks, which it does before it awaits anything.
             shared = dedupable && answered.has(key);
+            // A repeat answered from the first call reports nothing of its own: the first call's
+            // report is the one its dispatcher holds.
             const answer = dedupable
-                ? await once(answered, key, () => run.dispatch(request, signal))
-                : await run.dispatch(request, signal);
+                ? await once(answered, key, () => run.dispatch(request, signal, report))
+                : await run.dispatch(request, signal, report);
             ({ text: content, links } = answerOf(answer));
         }
     }
@@ -331,6 +374,9 @@ async function runCall(run, prepared, answered, step) {
         content = errorMessage(error);
         ok = false;
     }
+    finally {
+        close();
+    }
     run.onEvent({ kind: RunEventKind.ToolResult, id: call.id, name, ok, text: preview(content) });
     const isFirstAnswer = shared === false;
     if (isFirstAnswer) {

package/dist/wire/tool-calls.d.ts

@@ -189,6 +189,59 @@ export interface ToolAnswer {
     /** What the call produced, in the order the tool gave them. Never sent to the model. */
     links?: ResourceLink[];
 }
+/**
+ * The levels a server's log message is sent at, quietest first: MCP's, which are syslog's.
+ *
+ * @remarks
+ * `runMetrics` reads `warning` and the four above it as a server complaining. A level outside
+ * this list is still shown, and is counted as neither.
+ */
+export declare const ServerLogLevel: {
+    readonly Debug: 'debug';
+    readonly Info: 'info';
+    readonly Notice: 'notice';
+    readonly Warning: 'warning';
+    readonly Error: 'error';
+    readonly Critical: 'critical';
+    readonly Alert: 'alert';
+    readonly Emergency: 'emergency';
+};
+/** Any one of the levels in `ServerLogLevel`. */
+export type ServerLogLevel = (typeof ServerLogLevel)[keyof typeof ServerLogLevel];
+/**
+ * One log message a tool's server sent while the call was running, as `ToolCallReport.log` is
+ * handed it.
+ *
+ * @remarks
+ * The params of MCP's `notifications/message`, declared structurally rather than imported, as
+ * `ResourceLink` is: agent-mcp-pool's `ServerLogEntry` has these field names, so its `onLog`
+ * takes `report.log` as it stands. `level` is a plain string so a server's own word is shown
+ * rather than refused.
+ */
+export interface ServerLogEntry {
+    /** How serious the server says it is: one of `ServerLogLevel`, by the spec. */
+    level: string;
+    /** The server's name for the part of itself that logged, where it gave one. */
+    logger?: string;
+    /** Whatever the server sent: a string usually, any JSON value by the spec. */
+    data: unknown;
+}
+/**
+ * What a dispatcher may tell the run about the call it is making, besides its answer.
+ *
+ * @remarks
+ * An object rather than a fourth and fifth argument, so what a call can report grows here —
+ * progress is the next one — without `dispatch` changing again. Every member is a bound function,
+ * so it can be handed on alone: `onLog: report.log`. What is reported reaches the run's events
+ * and never the transcript: it is for the person watching, not the model.
+ */
+export interface ToolCallReport {
+    /**
+     * Tells watchers of a server's log message, as a `server-log` event for this call. Heard after
+     * the call has answered, it is dropped: the event would land after the result it explains.
+     */
+    log: (entry: ServerLogEntry) => void;
+}
 /**
  * One thing a run's tool calls produced: the first link to a uri, and where it came from.
  *

package/dist/wire/tool-calls.js

@@ -472,3 +472,20 @@ export function recoverToolCalls(content, { names = [] } = {}) {
     rest += tail.slice(cursor);
     return { content: `${content.slice(0, from)}${rest}`.trim(), toolCalls };
 }
+/**
+ * The levels a server's log message is sent at, quietest first: MCP's, which are syslog's.
+ *
+ * @remarks
+ * `runMetrics` reads `warning` and the four above it as a server complaining. A level outside
+ * this list is still shown, and is counted as neither.
+ */
+export const ServerLogLevel = {
+    Debug: 'debug',
+    Info: 'info',
+    Notice: 'notice',
+    Warning: 'warning',
+    Error: 'error',
+    Critical: 'critical',
+    Alert: 'alert',
+    Emergency: 'emergency',
+};

package/llms.txt

@@ -406,10 +406,13 @@ Reading what a model meant by a tool call when it did not write one cleanly.
 - `ResourceLink` (type) — A handle to something a tool call made or found — a document it wrote, a file it saved.
 - `RunArtifact` (type) — One thing a run's tool calls produced: the first link to a uri, and where it came from.
 - `recoverToolCalls` — Tool calls a model wrote into its reply as text, taken out of it and made into calls.
+- `ServerLogEntry` (type) — One log message a tool's server sent while the call was running, as `ToolCallReport.log` is handed it.
+- `ServerLogLevel` — Any one of the levels in `ServerLogLevel`.
 - `ToolAnswer` (type) — A dispatcher's answer when it has more to say than the text: what the model reads, and what the call produced for the host.
 - `ToolArgumentsError` — Tool arguments that could not be read as an object, with why.
 - `ToolCall` (type) — A tool call as the loop handles it, recovered or streamed.
 - `ToolCallOutcome` (type) — What one tool call did, in the order the model asked.
+- `ToolCallReport` (type) — What a dispatcher may tell the run about the call it is making, besides its answer.
 - `ToolCallRequest` (type) — One call the model made, as `dispatch` and `onToolCall` are handed it.
 - `ToolCallResult` (type) — One call's whole answer, as `onToolResult` is handed it.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@cubicecho/agent-core",
-  "version": "4.9.0",
+  "version": "4.10.0",
   "description": "The endpoint-agnostic half of an OpenAI-compatible agent loop: tool-schema compatibility, on-demand tool loading, one-shot side tasks, run events, and a pooled client.",
   "keywords": [
     "openai",