agent-runtime: stub old tool results in history instead of carrying them forever

packages/agent-runtime/src/__tests__/run-agent-step-unfinished-tool-calls.test.ts

@@ -208,4 +208,45 @@ describe('runAgentStep - unfinished tool calls', () => {
       capturedMessages.filter((message) => message.role === 'tool'),
     ).toHaveLength(2)
   })
+
+  it('stubs stale bulky read results but keeps small and newest ones verbatim', async () => {
+    const readResult = (toolCallId: string, content: string): Message => ({
+      role: 'tool',
+      toolCallId,
+      toolName: 'read_files',
+      content: [{ type: 'json', value: [{ path: 'src/app.ts', content }] }],
+    })
+    const bigRead = (marker: string) => `${marker}\n`.repeat(1_000)
+    const agentState = await runWithHistory([
+      userMessage('do the thing'),
+      // Five bulky reads (~17k each) so past-window savings clear the
+      // pass's 20k floor; the newest-3 window is r3, r4 and the small
+      // read, which rides along despite its size floor being separate.
+      ...['first', 'second', 'third', 'fourth', 'fifth'].flatMap((name, i) => [
+        toolCallMessage(`r${i}`),
+        readResult(`r${i}`, bigRead(`const ${name} = ${i};`)),
+      ]),
+      toolCallMessage('small'),
+      readResult('small', 'export const tiny = 1'),
+      userMessage('are you there?'),
+    ])
+
+    const request = JSON.stringify(capturedMessages)
+    // The three oldest bulky reads (newest-3 window = r3, r4, small) were
+    // replaced by the omit stub already understood by getPreviouslyReadFiles
+    // and the fitToolResults re-read hints...
+    expect(request).not.toContain('const first = 0;')
+    expect(request).not.toContain('const second = 1;')
+    expect(request).not.toContain('const third = 2;')
+    expect(request).toContain('contentOmittedForLength')
+    // ...the two newest bulky reads stay verbatim...
+    expect(request.split('const fourth = 3;').length).toBeGreaterThan(10)
+    expect(request.split('const fifth = 4;').length).toBeGreaterThan(10)
+    // ...and the small read rides along inside the window.
+    expect(request).toContain('export const tiny = 1')
+    // The stored history is healed to the same state.
+    const stored = JSON.stringify(agentState.messageHistory)
+    expect(stored).not.toContain('const first = 0;')
+    expect(stored).toContain('export const tiny = 1')
+  })
 })

packages/agent-runtime/src/run-agent-step.ts

@@ -145,6 +145,7 @@ import {
   assertUserContentSize,
   UserContentTooLargeError,
 } from './util/context-size-guard'
+import { simplifyOldToolResults } from './util/simplify-tool-results'
 import {
   countTokens,
   countTokensJson,
@@ -384,9 +385,21 @@ export const runAgentStep = async (
   // and replayed, that one orphan would fail every later turn, so drop it here
   // — the single point every step's request is built — and assign the cleaned
   // history back so the checkpointed state is valid too.
-  const history = dropUnansweredToolCalls(
-    expireMessages(agentState.messageHistory, 'agentStep'),
-  )
+  // In a long session, stub tool results older than the newest few with the
+  // omit shapes fitToolResults/getPreviouslyReadFiles already understand:
+  // read_files and terminal outputs up to 100k/50k chars otherwise stay
+  // verbatim in history and are re-sent on every request until compaction.
+  // The pass waits for real past-window volume (see simplifyOldToolResults),
+  // so a history that still fits the window comfortably keeps everything;
+  // the newest results and anything this step later appends are untouched,
+  // and unreplaced messages keep reference identity for the extension check
+  // below.
+  const history = simplifyOldToolResults({
+    messages: dropUnansweredToolCalls(
+      expireMessages(agentState.messageHistory, 'agentStep'),
+    ),
+    logger,
+  })
 
   const agentMessagesUntruncated = buildArray<Message>(
     ...history,
@@ -437,8 +450,7 @@ export const runAgentStep = async (
   const systemTokens = countTokens(system)
 
   let cacheDebugCorrelation:
-    | ReturnType<typeof createCacheDebugSnapshot>
-    | undefined
+    ReturnType<typeof createCacheDebugSnapshot> | undefined
   if (CACHE_DEBUG_FULL_LOGGING) {
     try {
       cacheDebugCorrelation = createCacheDebugSnapshot({