Skip to main content

Release 0.4.10 — Overthink Boilerplate Template Variable

Released: 2026-05-08 Chart: oci://ghcr.io/cnoe-io/charts/ai-platform-engineering:0.4.10 Previous release: 0.4.9

Highlights

0.4.10 reworks how "overthink" gating instructions reach agent prompts. Instead of a per-config custom_prompt string, the platform now injects a built-in OVERTHINK_BOILERPLATE template variable server-side, so agent prompts can opt into standard [DEFER]/[LOW_CONFIDENCE] gating with a single {{ client_context.overthink_boilerplate }} reference. A follow-up fix relocates that logic from the agent runtime to the slack-bot, where it belongs. This is a drop-in Helm upgrade — no values.yaml edits are required.

What's New

Overthink

  • OVERTHINK_BOILERPLATE template variable — replaces the removed custom_prompt field on OverthinkConfig with a built-in boilerplate injected into every system-prompt render context. Agent prompts using overthink: enabled: true can include {{ client_context.overthink_boilerplate }} to get standard [DEFER]/[LOW_CONFIDENCE] gating instructions without coupling the prompt to platform marker conventions; the variable is always available and silently ignored when not referenced (#1364)

Bug Fixes

  • overthink: move the OVERTHINK_BOILERPLATE constant out of agent_runtime.py and into the slack-bot, injecting overthink_boilerplate into client_context only when overthink.enabled is true — the runtime treats client_context as an opaque dict and should not own this logic, so the slack-bot can now evolve independently of the runtime (#1369)

Breaking Changes

Removed: overthink.custom_prompt (slack-bot config). The custom_prompt field was removed from OverthinkConfig. This only affects deployments that explicitly set it in their slack-bot configuration.

Before (0.4.9):

overthink:
enabled: true
custom_prompt: "Defer to a human when uncertain..."

After (0.4.10):

overthink:
enabled: true
# custom_prompt removed — reference the built-in boilerplate in your agent's
# system prompt instead:
# {{ client_context.overthink_boilerplate }}

Consequence: If you leave custom_prompt in place, it is no longer applied, and your previous gating instructions will not reach the prompt. Add {{ client_context.overthink_boilerplate }} to the agent's system prompt to restore standard [DEFER]/[LOW_CONFIDENCE] gating. No Helm chart values are affected.

Known Issues

None known at this time.

Upgrade

helm upgrade ai-platform-engineering \
oci://ghcr.io/cnoe-io/charts/ai-platform-engineering \
--version 0.4.10 \
-f your-values.yaml

Upgrade Guide: 0.4.9 → 0.4.10

Overview

0.4.10 is a drop-in Helm upgrade. The only operator-visible change is the removal of the slack-bot overthink.custom_prompt field, replaced by the server-injected {{ client_context.overthink_boilerplate }} template variable. No chart values.yaml edits are required.

Helm Values Changes

No Helm values changes between 0.4.9 and 0.4.10. Drop-in upgrade — no values.yaml edits required.

Data Migrations

No MongoDB schema or data migrations required.

Upgrade Runbook

1. Update chart version

helm upgrade ai-platform-engineering \
oci://ghcr.io/cnoe-io/charts/ai-platform-engineering \
--version 0.4.10 \
-f your-values.yaml

2. (If you used overthink.custom_prompt) Update your agent prompt

Remove custom_prompt from your slack-bot overthink config and add the boilerplate reference to the agent's system prompt:

{{ client_context.overthink_boilerplate }}

3. Verify

kubectl get pods -n <namespace>