fix(llm_agent_builder): enforce use_emojis=false, not just true

[mateusbellozupko]

Summary

• The use_emojis agent config toggle only ever added a prompt instruction when set to true (encouraging emoji use). When false (or unset), it silently added nothing.
• This meant disabling the toggle had no actual effect on the model's behavior — emoji suppression relied entirely on the agent's own free-text instruction (if any) or the model's own default tendencies, both of which are unreliable.
• Now the false/unset path explicitly adds "Do not use any emojis in your responses, under any circumstance." to the prompt, mirroring the existing true branch's approach.

Test plan

• python3 -m py_compile on the modified file
• No existing unit tests cover this function's prompt assembly; manual review of the added instruction text

🤖 Generated with Claude Code

Summary by Sourcery

Enforce the agent emoji preference reliably when assembling LLM prompts.

Bug Fixes:

• Enforce the use_emojis setting in both directions by explicitly instructing agents to avoid emojis when the option is false or unset.

Enhancements:

• Normalize string and boolean configuration values so disabled settings are not mistakenly treated as enabled.

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

The agent builder now translates the use_emojis configuration into an explicit prompt instruction for either behavior, preventing false or unset values from silently relying on model defaults or free-text instructions.

Flow diagram for explicit emoji instruction selection

flowchart TD
    A["_create_llm_agent"] --> B["Read agent.config.use_emojis"]
    B --> C{use_emojis is true?}
    C -->|Yes| D["Append instruction to use emojis"]
    C -->|No or unset| E["Append instruction to not use emojis"]
    D --> F["Assemble agent prompt"]
    E --> F

Loading

File-Level Changes

Change	Details	Files
Make the emoji preference enforceable in both enabled and disabled states during prompt assembly.	Continue adding a positive emoji-use instruction when use_emojis is truthy. Add an explicit prohibition when use_emojis is false or unset. Clarify in comments why both branches are required.	src/services/adk/agents/llm_agent_builder.py

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've found 1 issue

Prompt for AI Agents

Please address the comments from this code review:

## Individual Comments

### Comment 1
<location path="src/services/adk/agents/llm_agent_builder.py" line_range="790" />
<code_context>
+        # instruction (or the model's default tendencies) to suppress emojis,
+        # silently failing to enforce the toggle when the operator turned it off.
         use_emojis = agent.config.get("use_emojis")
         if use_emojis:
             agent_config_sections.append(
                 "Use emojis in your responses to make communication more friendly and engaging. Incorporate appropriate emojis naturally throughout your messages."
</code_context>
<issue_to_address>
**issue (bug_risk):** A serialized configuration value such as the string `"false"` is truthy in Python, so the builder selects the emoji-enabling instruction instead of the disabling instruction. `AgentBase.config` accepts `Any` and the JSON configuration is not validated or normalized to a boolean.

**Triggers:** When an API client or persisted configuration supplies `use_emojis` as a string rather than a native JSON boolean.

**Suggested fix:** Normalize or strictly compare the value before branching, for example by accepting only `use_emojis is True` for the enabling branch and treating all other values as disabled, or by validating the config as a boolean at its boundary.

```suggestion
        if use_emojis is True:
```
</issue_to_address>

Sourcery assessment

Approval pending. 1 finding to address first.

Blocking findings: src/services/adk/agents/llm_agent_builder.py:790

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

[sourcery-ai]

Sourcery assessment

Approved.