feat(coding-agent): delivered job and LSP notifications via aside channel

- Routed background-job completions and late LSP diagnostics through the new non-interrupting aside channel so the model sees them mid-run between requests.
- Removed inline custom rendering from the LSP tool now that diagnostics surface through the shared transcript renderer.

packages/agent/CHANGELOG.md

@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Added
+
+- Added a non-interrupting "aside" message channel to the agent loop (`AgentLoopConfig.getAsideMessages` / `Agent.setAsideMessageProvider`). Asides are drained at each step boundary (after a tool batch, before the next model call) and at the yield check, so passive notifications (e.g. background-job completions, late LSP diagnostics) reach the model *between requests* without waiting for the agent to stop and without aborting in-flight tools the way steering does.
+
 ### Changed
 
 - Changed core custom and hook messages to convert to `developer` messages for provider context.

packages/coding-agent/CHANGELOG.md

@@ -8,6 +8,7 @@
 
 ### Changed
 
+- Changed background-job completion and late LSP diagnostic delivery to inject at the next agent step boundary (mid-run), via the new non-interrupting "aside" channel, instead of only when the agent reaches a yield/follow-up point. The model now sees these notifications between its own requests without the turn having to end first, and in-flight tools are never interrupted; `job`-poll acknowledgement still suppresses results the agent already saw.
 - Changed late LSP diagnostics after edit or write to surface in the chat transcript as `Late diagnostics` entries rendered through the same grouped tree renderer the `edit`/`write` tools use (per-file nodes, severity icons, `:line:col` locations), and to honor the global tool-output expand toggle (collapsed entries cap at 5 diagnostics with a `… N more` hint)
 - Changed delayed diagnostics delivery to batch late results in one message per flush instead of a raw hidden custom payload
 - Changed hidden custom messages and file-mention context to reach providers as `developer` messages instead of user-authored turns, so system reminders no longer pollute compacted user history.

packages/coding-agent/src/cli/gallery-fixtures/codeintel.ts

@@ -4,7 +4,6 @@ import type { GalleryFixture } from "./types";
 export const codeintelFixtures: Record<string, GalleryFixture> = {
 	lsp: {
 		label: "LSP",
-		customRendered: true,
 		streamingArgs: {
 			action: "references",
 			file: "src/server/auth.ts",

packages/coding-agent/src/cli/gallery-fixtures/types.ts

@@ -25,7 +25,7 @@ export interface GalleryFixture {
 	renderState?: (state: GalleryFixtureState, width: number, expanded: boolean) => string[] | Promise<string[]>;
 	/**
 	 * Set for tools whose real `AgentTool` attaches `renderCall`/`renderResult`
-	 * directly on the instance (e.g. `lsp`, `task`). The harness then attaches
+	 * directly on the instance (e.g. `task`). The harness then attaches
 	 * the registry renderer onto the fake tool so the component routes through
 	 * the custom-tool branch — the same path production takes — instead of the
 	 * built-in registry branch. The two branches can diverge, so exercising the

packages/coding-agent/src/lsp/index.ts

@@ -40,7 +40,6 @@ import {
 	rangesOverlap,
 } from "./edits";
 import { detectLspmux } from "./lspmux";
-import { renderCall, renderResult } from "./render";
 import {
 	type CodeAction,
 	type CodeActionContext,
@@ -1310,10 +1309,6 @@ export class LspTool implements AgentTool<typeof lspSchema, LspToolDetails, Them
 	readonly summary = "Query LSP (language server) for diagnostics, hover info, and references";
 	readonly description: string;
 	readonly parameters = lspSchema;
-	readonly renderCall = renderCall;
-	readonly renderResult = renderResult;
-	readonly mergeCallAndResult = true;
-	readonly inline = true;
 	readonly strict = true;
 
 	constructor(private readonly session: ToolSession) {