fix: close recovery review gaps

packages/core/agent-loop/src/loop.ts

@@ -32,7 +32,7 @@ class TerminalModelRequestFailure extends Error {
     readonly requestError: RequestError,
     readonly failure: LlmFailure,
   ) {
-    super(requestError.message, { cause: requestError })
+    super(failure.message, { cause: requestError })
     this.name = 'TerminalModelRequestFailure'
   }
 }
@@ -69,6 +69,12 @@ function errorData(err: RequestError): { message: string; code?: string } {
   return { message: errorChain(err), ...typeof err.code === 'string' ? { code: err.code } : {} }
 }
 
+/** Preserve cause diagnostics, falling back to adapter-normalized prose for a hostile Error. */
+function durableFailure(err: RequestError, failure: LlmFailure): LlmFailure {
+  const message = errorChain(err)
+  return { ...failure, message: message === '<unrenderable value>' ? failure.message : message }
+}
+
 /** Map a successful max-token finish onto the turn reason; other successful finishes add nothing. */
 function stepFinishReason(finish: FinishReason): TurnEndReason | undefined {
   switch (finish.kind) {
@@ -231,7 +237,7 @@ async function runTurn(
     errorReported = true
     reason = failure === undefined
       ? { kind: 'error', step, ...errorData(err) }
-      : { kind: 'error', step, failure: { ...failure, message: errorChain(err) } }
+      : { kind: 'error', step, failure: durableFailure(err, failure) }
     try {
       events.emit('agent/error', turn, step, err)
     } catch {

packages/core/agent-loop/tests/request-recovery.spec.ts

@@ -3,6 +3,7 @@ import { Context } from 'cordis'
 import LlmService, {
   CallId,
   CONTEXT_WINDOW_EXCEEDED_CODE,
+  HarnessError,
   LlmAdapter,
   LlmError,
   ProviderRequestId,
@@ -419,6 +420,31 @@ describe('agent post-step and request-error lifecycle', () => {
     expect(seen).toBe(original)
   })
 
+  it('keeps an adapter error with a hostile message accessor on the recovery path', async () => {
+    const original = Object.defineProperty(new HarnessError('provider failed', 'SERVER'), 'message', {
+      get() { throw new Error('SDK message accessor trap') },
+    })
+    const ctx = await harness(new SynchronousDispatchFailureAdapter(original))
+    const agent = ctx.agentLoop.create(SessionId('hostile-message-recovery'), { provider: 'mock', model: 'mock' })
+    let seenError: Error | undefined
+    let seenFailure: LlmFailure | undefined
+    ctx.on('agent/request-error', async (_agent, _turn, _step, error, failure, _history, _signal, next) => {
+      seenError = error
+      seenFailure = failure
+      return next()
+    })
+
+    send(agent)
+    await waitForIdle(ctx, agent)
+
+    expect(seenError).toBe(original)
+    expect(seenFailure).toEqual({ message: 'LLM adapter failed', code: 'SERVER' })
+    expect(agent.session.events.at(-1)).toMatchObject({
+      type: 'turn/end',
+      data: { reason: { kind: 'error', failure: { message: 'LLM adapter failed', code: 'SERVER' } } },
+    })
+  })
+
   it('passes structured facts beside the original Error and records its cause chain on exhaustion', async () => {
     const original = new LlmError('provider busy', 'RATE_LIMIT', {
       cause: new Error('upstream connection reset'),

packages/core/session/README.md

@@ -60,7 +60,7 @@ Durable values need one accepted representation, not a check followed by a secon
 
 ### Session event vocabulary (`types.ts`)
 
-The append-only log's event types, enumerated member by member — payloads, surface badges, provenance — in the generated [persistence log event catalog](../../../docs/persistence-catalog.md). Token usage and provider/model/replay provenance ride on `assistant/message`; an operational error's step is on `turn/end.reason` for `kind: 'error'`, with structured provider facts for a final model-request failure.
+The append-only log's event types, enumerated member by member — payloads, surface badges, provenance — in the generated [persistence log event catalog](../../../docs/persistence-catalog.md). Token accounting reads per-step `assistant/chunk { type: 'usage' }` records and treats `assistant/message.usage` as the committed-step fallback when no usage chunk exists; failed model-request attempts have no assistant message. Provider/model/replay provenance rides on `assistant/message`; an operational error's step is on `turn/end.reason` for `kind: 'error'`, with structured provider facts for a final model-request failure.
 
 Merge-extensible via `SessionEventMap` — a plugin declaration-merges its own types (the compaction seam's `compact/*`, bounded recovery's non-surface `llm/retry`, the hook bridges' `hook/*`); merged members appear in the same catalog.