Skip to content

Prep v0.12.36 - #3980

Merged
michaeljguarino merged 1 commit into
masterfrom
prep-v0.12.36
Aug 7, 2026
Merged

Prep v0.12.36#3980
michaeljguarino merged 1 commit into
masterfrom
prep-v0.12.36

Conversation

@michaeljguarino

Copy link
Copy Markdown
Member
  • bumps agent
  • ...etc

Test Plan

Test environment: https://console.your-env.onplural.sh/

Checklist

  • I have added a meaningful title and summary to convey the impact of this PR to a user.
  • If required, I have updated the Plural documentation accordingly.
  • I have added tests to cover my changes.
  • I have deployed the agent to a test environment and verified that it works as expected (required only when changing agent code).

Plural Flow: console

@michaeljguarino
michaeljguarino requested a review from a team August 7, 2026 16:23
@michaeljguarino michaeljguarino added the enhancement New feature or request label Aug 7, 2026
@soffi-ai

soffi-ai Bot commented Aug 7, 2026

Copy link
Copy Markdown

Soffi AI Summary

This is a release preparation PR (v0.12.36) that bumps the agent version and introduces output truncation and result limiting across all AI workbench tools to prevent LLM context window overflows and improve the quality of agent responses.

The core change is the introduction of a new Console.AI.Tools.Workbench.Output module that provides two primitives: truncate/1,2 (caps large string payloads with an optional hint for the agent on how to retrieve remaining data) and json/2 (encodes and truncates JSON with a hint). This module is then wired into every observability and infrastructure tool in the workbench:

  • Observability tools (Logs, Plrl.Logs, Metrics, MetricsSearch, MetricsLabelSearch, PlrlLogsLabels, PlrlLogsAggregate): Results are now passed through Output.truncate/2, and list-returning tools cap results at 500 items before encoding, preventing unbounded payloads from large log/metric datasets.
  • Infrastructure tools (KubeList, PodLogs, CloudQuery): KubeList now routes JSON output through Output.json/2 with a hint suggesting jq filtering; PodLogs truncates log text with a hint to adjust limit_bytes/since_seconds; CloudQuery is similarly updated.

The motivating concern is practical: when an AI agent queries a large Kubernetes cluster or a high-volume observability backend, the raw response can easily exceed LLM token limits or produce noise. By truncating at a well-defined boundary and embedding actionable hints in the truncation message, the agent is guided to issue more targeted follow-up queries rather than silently losing data. A unit test for the new Output module is also added.

Commits

Commit Summary
3b29281 Release prep for v0.12.36: bumps the agent chart/version and introduces output truncation + per-tool result limits across all AI workbench tools (logs, metrics, kube-list, pod-logs) to prevent LLM context overflows and guide agents toward narrower follow-up queries via embedded hints.

Deploy in Soffi


Updated: 2026-08-07 21:50 UTC

@greptile-apps

greptile-apps Bot commented Aug 7, 2026

Copy link
Copy Markdown
Contributor

Greptile Summary

Updates the deployment-operator version used by Console from v0.6.56 to v0.6.57.

  • Advances the agent version consumed by build-time chart downloads and runtime agent deployment references.

Confidence Score: 5/5

The PR appears safe to merge with no actionable issues identified.

The repository contains the corresponding deployment-operator v0.6.57 release tag, and the version-only change introduces no demonstrated build, runtime, or compatibility failure.

Important Files Changed

Filename Overview
AGENT_VERSION Bumps the deployment-operator version marker to v0.6.57; no concrete defect is established by the repository evidence.

Reviews (1): Last reviewed commit: "Prep v0.12.36" | Re-trigger Greptile

@michaeljguarino

Copy link
Copy Markdown
Member Author

plural deploy this

@plural-copilot

plural-copilot Bot commented Aug 7, 2026

Copy link
Copy Markdown
Contributor

GitOps deployment tag updated to sha-ba278d1: https://github.com/pluralsh/plrl-up-demos/pull/2561

@michaeljguarino

Copy link
Copy Markdown
Member Author

plural deploy this

@plural-copilot

plural-copilot Bot commented Aug 7, 2026

Copy link
Copy Markdown
Contributor

Deployment GitOps PR: https://github.com/pluralsh/plrl-up-demos/pull/2563

Updates the demo console image tag to sha-71ae806 and is annotated Plural Service: mgmt/apps.

@michaeljguarino

Copy link
Copy Markdown
Member Author

plural deploy this

@plural-copilot

plural-copilot Bot commented Aug 7, 2026

Copy link
Copy Markdown
Contributor

Requested GitOps deployment PR created: https://github.com/pluralsh/plrl-up-demos/pull/2564

@michaeljguarino

Copy link
Copy Markdown
Member Author

plural deploy this

@plural-copilot

plural-copilot Bot commented Aug 7, 2026

Copy link
Copy Markdown
Contributor

Deployment PR created: https://github.com/pluralsh/plrl-up-demos/pull/2567

Updates demo console to sha-f8a496d.

@michaeljguarino michaeljguarino added hotfix enhancement New feature or request and removed enhancement New feature or request labels Aug 7, 2026
@michaeljguarino

Copy link
Copy Markdown
Member Author

plural deploy this

* bumps agent
* ...etc
@plural-copilot

plural-copilot Bot commented Aug 7, 2026

Copy link
Copy Markdown
Contributor

Deployment tag sha-f8a496d is already pinned in pluralsh/plrl-up-demos via the merged GitOps PR #2567. No duplicate PR was created.

@michaeljguarino

Copy link
Copy Markdown
Member Author

plural deploy this

@plural-copilot

plural-copilot Bot commented Aug 7, 2026

Copy link
Copy Markdown
Contributor

@michaeljguarino
michaeljguarino merged commit c684b62 into master Aug 7, 2026
13 checks passed
@michaeljguarino
michaeljguarino deleted the prep-v0.12.36 branch August 7, 2026 22:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request hotfix

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant