Local results, with their limits.

MacBook checks recorded on 16 November 2026. Published as documentary evidence, not a corporate-pilot acceptance.

Environment and source

RC8 source 6abc06f, Docker Desktop, Apple Silicon running Linux amd64 images under emulation. The cabinet used an owner token. Real model calls used an external OpenAI API through PR-Agent. Qwen was not tested.

The owner supplied a normalized report on 17 November. This publication checks and summarizes that record; it does not rerun the tests. The original private report and company source are not public downloads.

A real run. Educational code.

Recorded on a MacBook, 16 November 2026. A local GitLab and an external OpenAI model.

The recorded outcome

SHA
8a87c4f9
Run
9f90f98e
State
draft_ready
Findings
3

The answer reached a saved draft

A real model reviewed a synthetic SQL-injection change. After a local credential-fingerprint patch, the run completed with three findings. The patch addressed a workflow conflict, not the SQL code.

This public record is a summary of the saved acceptance report. It does not contain the original MR, full finding text or cabinet footage. It is not a live demo or an independent rerun.

The patches are not an accepted release. Publication, fix, new-SHA review, CI and the team decision still need a complete acceptance run.

Read the local results and limitsPublic record · JSON

Results are separate experiments

CheckRecorded resultLimit
Reviewer assignmentCoordinator polling started reviews; recorded on 6 MRsLocal GitLab; automatic publication disabled
Bot mentionOne MR triggered by a mentionA small trigger check, not a reliability measurement
CI triggerPipeline assigned the bot; coordinator run reached draft_ready with 4 findingsA separate synthetic run; not the 3-finding case or an accepted blocking CI gate
Four historical MRsSmall changes reached draft_ready with no findings, one model call eachUnlabelled sample: process evidence, not proof of correctness or quality
Restart persistenceSaved run/draft records and Worker attempts matched; no repeated model callsNot backup/restore, failure during a write or five concurrent reviews
Retrieval in shadowA separate fixture prepared 5 support fragments, 6005 bytes; model received only the 474-byte diffRetrieved fragments were not sent to the model; no proven review-quality benefit
Findings on real codeWorker returned two model findings; Control then failed with conflictDefects not independently confirmed; no successful full rerun of the same MR after the patch

Local patches are not the release

A credential fingerprint based on file device/inode metadata produced an observed conflict after a model response on Docker Desktop. A local patch removed those two fields. It needs regression coverage for replacement and revocation, inclusion in a fixed build and full package acceptance. The separate quota-message fix and installer/indexer workarounds are not presumed merged.

Installation required local network and filesystem workarounds, more Worker memory and a trusted local GitLab CA. The embedding timeout was changed locally under emulation. These observations are not copy-and-run production settings.

Before a corporate pilot

  • Merge the reviewed patches into a fixed build and run credential replacement/revocation regression checks.
  • Accept one complete MR, controlled publication, fix, new SHA, re-review, CI and human-decision path.
  • Read a new useful model result through ContextForge, including access denial and revocation.
  • Measure five overlapping real reviews, queueing, p95, limits, failures and full cost.
  • Accept cabinet SSO, company and retrieval isolation, backup/restore and clean target Linux installation.
  • Validate enforced retrieval on representative code and compatibility/quality of the proposed corporate Qwen route.

A finding, zero findings, a CI trigger, approval and merge are different outcomes. Quality, savings and full cost have not been measured.

A measurable evaluation

Start with one repository and a technical owner. Accept a fixed build, compare the same historical MRs with the current process, then agree a small live flow. Set success thresholds before starting. Track confirmed defects, false findings, misses, human handling time, waiting, all calls and retries, and operations. Expand to one more team only after accepted results and measured benefit.

Deployment acceptance and measurement plan · Release status