feat(coding-agent): disable thinking block rendering

[cheetahbyte]

Summary

Adds a new disableThinkingBlock setting that completely prevents thinking blocks from being rendered in assistant output, rather than just replacing them with a short label like the existing hideThinkingBlock option.

Changes

• New setting disableThinkingBlock (default: true) — when enabled, thinking blocks are omitted entirely from the UI, with no placeholder label shown. This means thinking content is hidden by default unless a user explicitly disables this setting.
• Updated hideThinkingBlock semantics — the existing option now only controls whether a short "Thinking..." label is shown in place of thinking blocks. It has no effect when disableThinkingBlock is enabled.
• Interactive settings UI — adds a new "Disable thinking blocks" toggle alongside the existing "Hide thinking" option.
• Real-time application — the setting is applied when starting the interactive mode, when reloading a session, and when changed from the settings selector. Chat views are rebuilt on toggle so the display updates immediately, including any in-progress streaming responses.
• Documentation — the settings reference now documents both options and their default values.
• Tests — added coverage verifying thinking blocks are completely omitted when disabled, and that the setting defaults to enabled while preserving the existing hide setting.

[kody-ai]

Code Review Completed! 🔥

The code review was successfully completed based on your current configurations.

Kody Guide: Usage and Configuration

Interacting with Kody

• Request a Review: Ask Kody to review your PR manually by adding a comment with the @kody start-review command at the root of your PR.

• Validate Business Logic: Ask Kody to validate your code against business rules by adding a comment with the @kody -v business-logic command.

• Provide Feedback: Help Kody learn and improve by reacting to its comments with a 👍 for helpful suggestions or a 👎 if improvements are needed.

Current Kody Configuration

Review Options

The following review options are enabled or disabled:

Options	Enabled
Bug	✅
Performance	✅
Security	✅
Business Logic	✅

Access your configuration settings here.

​

[kody-ai]

The switch to build:offline lets stale model data pass CI indefinitely: validateGeneratedModelData (packages/ai/scripts/model-data.ts:209-210) checks generatedAt for parseability only, never age or upstream. Add a freshness guard to check-model-data or a scheduled workflow that runs npm run hydrate:model-data and opens a PR when the baseline is outdated.

- name: Build offline
  run: npm run build:offline

- name: Verify model data freshness
  run: node packages/ai/scripts/check-model-data.ts --require-fresh

Prompt for LLM

File .github/workflows/ci.yml:

Line 35 to 36:

The switch to build:offline lets stale model data pass CI indefinitely: validateGeneratedModelData (packages/ai/scripts/model-data.ts:209-210) checks generatedAt for parseability only, never age or upstream. Add a freshness guard to check-model-data or a scheduled workflow that runs npm run hydrate:model-data and opens a PR when the baseline is outdated.

Suggested Code:

      - name: Build offline
        run: npm run build:offline

      - name: Verify model data freshness
        run: node packages/ai/scripts/check-model-data.ts --require-fresh

_{Talk to Kody by mentioning @kody}

_{Was this suggestion helpful? React with 👍 or 👎 to help Kody learn from this interaction.}

​

​