# fix\(server\): agents can continue the same reviewer conversation · PR \#23253 · pingdotgg/t3code

[View on GitCafe](https://git.cafe/pingdotgg/t3code/pull/23253)

Repository: [pingdotgg/t3code](https://git.cafe/pingdotgg/t3code)

Visibility: public

State: open

Source repository: pingdotgg/t3code

Source branch: fix/issue-19821

Target branch: main

Head commit: 54651ff9489f583ea17993e20b43f13b4bf83e5e

[Discussion and reviews](https://git.cafe/pingdotgg/t3code/pull/23253)

[Commits](https://git.cafe/pingdotgg/t3code/pull/23253/commits?format=markdown)

[Files changed](https://git.cafe/pingdotgg/t3code/pull/23253/diffs?format=markdown)

## Description

---

## Problem

When asked to continue a three-round review in the same child's conversation, agents started a fresh child for every round and lost the reviewer's memory. The injected instructions and `delegate_task` description required fresh delegation even though `t3_thread_send` already supports same-child follow-ups.

## Change

Limit the fresh-child rule to independent review rounds and explicitly direct conversation follow-ups to `t3_thread_send` with the existing `childThreadId`. Update the existing orchestration guidance and add a regression test covering the injected instructions and both tool descriptions.

## Scope and approval

Fixes #19821
GitCafe: https://git.cafe/pingdotgg/t3code/issues/19821
Triaged bug via the automated issue flow. Scope is agent-facing guidance for existing delegation behavior.

## Verification

- The regression test fails against main's original guidance with four assertions and passes after the fix. [Red log](https://gh-file-drop-api-prod-mi5fy3sowv63ufte.pinglabs.workers.dev/f/ceaf0ca117354e85/red-test.log), [green log](https://gh-file-drop-api-prod-mi5fy3sowv63ufte.pinglabs.workers.dev/f/5f64bc5da67f2dd0/green-test.log).
- `vp test run apps/server/src/mcp/toolkits/orchestrator/tools.test.ts apps/server/src/provider/CodexDeveloperInstructions.test.ts`: 18 passed, including Codex's instruction byte caps; repeated successfully after merging mirrored main and clarifying the docs. [Final test log](https://gh-file-drop-api-prod-mi5fy3sowv63ufte.pinglabs.workers.dev/f/26c18f8a47f1d82d/19821-final-tests.log).
- Targeted lint and formatting checks passed. Two independent reviewers returned MERGE in both full review rounds. The final round verified the four-file diff against mirrored main.
- Real isolated web dev server: Codex GPT-6.1-Sol and Claude Opus 5.5 each used one child for three rounds, recalled a marker omitted from the round-2 prompt, and completed three distinct tasks. [Codex transcript](https://gh-file-drop-api-prod-mi5fy3sowv63ufte.pinglabs.workers.dev/f/7a2d25b7de4eb00f/19821-runtime-after.md), [Claude transcript](https://gh-file-drop-api-prod-mi5fy3sowv63ufte.pinglabs.workers.dev/f/049d941e688045fd/19821-runtime-claude-after.md).

| Evidence | Before | After |
| --- | --- | --- |
| Runtime guidance and recall | [Both parents created fresh children](https://gh-file-drop-api-prod-mi5fy3sowv63ufte.pinglabs.workers.dev/f/b532b8d0f3933a0a/19821-runtime-before.md) | [Codex same-child recall](https://gh-file-drop-api-prod-mi5fy3sowv63ufte.pinglabs.workers.dev/f/7a2d25b7de4eb00f/19821-runtime-after.md); [Claude same-child recall](https://gh-file-drop-api-prod-mi5fy3sowv63ufte.pinglabs.workers.dev/f/049d941e688045fd/19821-runtime-claude-after.md) |

No render paths changed; the [audited visual fixture matrix is empty](https://gh-file-drop-api-prod-mi5fy3sowv63ufte.pinglabs.workers.dev/f/6de44814cc81e116/issue-19821-proof-audit-pass1.md). The before live service build was not mapped to a source commit; the failing regression pins the original guidance to main. The fixed runtime probes ran at [e7417481e5](https://git.cafe/pingdotgg/t3code/commit/e7417481e5a2a2f130551092f05e1aced2072b08); the final head preserves the same agent-facing guidance and clarifies active versus completed child behavior in the docs. The Codex probe recovered from a development watcher restart. Desktop, mobile, and other providers were not run separately.

[Complete evidence index](https://gh-file-drop-api-prod-mi5fy3sowv63ufte.pinglabs.workers.dev/f/cdc61ddc1f0d780c/issue-19821-evidence-index.md).

Models: GPT-6.1-Sol through the Codex harness; Claude Opus 5.5 through the Claude harness in T3 Code.