feat(lh-115194): support Claude in the agent harness - #38
Merged
Merged
Conversation
Add first-class Claude execution with provider credential isolation, runtime-only retries, and source-aware comparison fingerprints. Strengthen deterministic command correlation, confirmation scoring, secret scanning, setup doubles, and failure diagnostics. Improve report and dashboard usability, update the skills, and bump both plugin manifests to 0.1.3.
huides00
requested review from
Scoombe,
afercal and
siddhuwarrier
as code owners
September 14, 2026 18:30
Record the Claude harness support and plugin runtime safety fixes in the Ansible release history so the 0.42.0 release rehearsal can complete.
Consistency CheckNo consistency issues found. Checker output |
afercal
approved these changes
Sep 15, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
https://cisco-sbg.atlassian.net/browse/LH-115194
Description
Agent harness runs need comparable, trustworthy results from Codex and Claude without exposing provider or customer credentials. The harness can now execute Claude sessions through the current plugin checkout, prove provider credentials are isolated before fixtures run, retry provider-only failures, and fingerprint inputs so incompatible baselines cannot be compared.
Deterministic command correlation, confirmation scoring, secret scanning, setup simulation, and failure diagnostics are strengthened to reduce false harness-invalid results and make remaining failures easier to investigate. Reports identify the agent and runtime attempts, the dashboard retains its list position while navigating cases, the skills clarify credential and mutation handling, and both plugin manifests advance to version 0.1.3.
The complete test suite and scoped pre-commit checks passed.