fix(actions): rename generate_next_step to generate_next_steps for task-specific LLM support - #1603
Merged
Merged
Conversation
…sk-specific LLM support Fixes a naming mismatch bug where the action `generate_next_step` (singular) didn't match the Task enum value `generate_next_steps` (plural). This mismatch prevented task-specific LLM configuration from working correctly. When users configured a task-specific LLM with `type: generate_next_steps` in their config, the runtime would look for `generate_next_step_llm` (based on the action name) but the config registered `generate_next_steps_llm`, causing the task to fall back to the main LLM instead.
Contributor
Greptile OverviewGreptile SummaryFixed critical naming mismatch bug where the action Key Changes:
Impact:
|
| Filename | Overview |
|---|---|
| nemoguardrails/actions/llm/generation.py | Renamed action method from generate_next_step to generate_next_steps to match Task enum value |
| nemoguardrails/rails/llm/llm_flows.co | Updated Colang flow to execute generate_next_steps action instead of generate_next_step |
| tests/test_task_specific_model.py | New comprehensive test validating task-specific LLM configuration for generate_next_steps action |
Sequence Diagram
sequenceDiagram
participant User
participant Config
participant LLMRails
participant Runtime
participant Action as generate_next_steps
Note over User,Config: Before Fix (Bug)
User->>Config: Configure type: generate_next_steps
Config->>LLMRails: Register generate_next_steps_llm
LLMRails->>Runtime: Store as "generate_next_steps_llm"
Note over Runtime,Action: Action named "generate_next_step"
Runtime->>Runtime: Look for "generate_next_step_llm"
Runtime->>Action: Not found! Use main LLM instead ❌
Note over User,Config: After Fix (Working)
User->>Config: Configure type: generate_next_steps
Config->>LLMRails: Register generate_next_steps_llm
LLMRails->>Runtime: Store as "generate_next_steps_llm"
Note over Runtime,Action: Action renamed to "generate_next_steps"
Runtime->>Runtime: Look for "generate_next_steps_llm"
Runtime->>Action: Found! Use task-specific LLM ✓
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
Contributor
Additional Comments (11)
Prompt To Fix With AIThis is a comment left during a code review.
Path: tests/test_llama_guard.py
Line: 64:64
Comment:
comment still references the old action name `generate_next_step`
```suggestion
"Mock generated next step", # mock response for the generate_next_steps action
```
How can I resolve this? If you propose a fix, please make it concise.
Prompt To Fix With AIThis is a comment left during a code review.
Path: tests/test_llama_guard.py
Line: 90:90
Comment:
comment still references the old action name `generate_next_step`
```suggestion
# generate_user_intent, generate_next_steps, or generate_bot_message
```
How can I resolve this? If you propose a fix, please make it concise.
Prompt To Fix With AIThis is a comment left during a code review.
Path: tests/test_llama_guard.py
Line: 115:115
Comment:
comment still references the old action name `generate_next_step`
```suggestion
# generate_user_intent, generate_next_steps, or generate_bot_message
```
How can I resolve this? If you propose a fix, please make it concise.
Prompt To Fix With AIThis is a comment left during a code review.
Path: tests/test_llama_guard.py
Line: 140:140
Comment:
comment still references the old action name `generate_next_step`
```suggestion
"Mock generated next step", # mock response for the generate_next_steps action
```
How can I resolve this? If you propose a fix, please make it concise.
Prompt To Fix With AIThis is a comment left during a code review.
Path: tests/test_llama_guard.py
Line: 166:166
Comment:
comment still references the old action name `generate_next_step`
```suggestion
"Mock generated next step", # mock response for the generate_next_steps action
```
How can I resolve this? If you propose a fix, please make it concise.
Prompt To Fix With AIThis is a comment left during a code review.
Path: tests/test_patronus_lynx.py
Line: 94:94
Comment:
comment still references the old action name `generate_next_step`
```suggestion
"Mock generated next step", # mock response for the generate_next_steps action
```
How can I resolve this? If you propose a fix, please make it concise.
Prompt To Fix With AIThis is a comment left during a code review.
Path: tests/test_patronus_lynx.py
Line: 123:123
Comment:
comment still references the old action name `generate_next_step`
```suggestion
"Mock generated next step", # mock response for the generate_next_steps action
```
How can I resolve this? If you propose a fix, please make it concise.
Prompt To Fix With AIThis is a comment left during a code review.
Path: tests/test_patronus_lynx.py
Line: 152:152
Comment:
comment still references the old action name `generate_next_step`
```suggestion
"Mock generated next step", # mock response for the generate_next_steps action
```
How can I resolve this? If you propose a fix, please make it concise.
Prompt To Fix With AIThis is a comment left during a code review.
Path: tests/test_patronus_lynx.py
Line: 181:181
Comment:
comment still references the old action name `generate_next_step`
```suggestion
"Mock generated next step", # mock response for the generate_next_steps action
```
How can I resolve this? If you propose a fix, please make it concise.
Prompt To Fix With AIThis is a comment left during a code review.
Path: tests/test_patronus_lynx.py
Line: 208:208
Comment:
comment still references the old action name `generate_next_step`
```suggestion
"Mock generated next step", # mock response for the generate_next_steps action
```
How can I resolve this? If you propose a fix, please make it concise.
Prompt To Fix With AIThis is a comment left during a code review.
Path: tests/test_patronus_lynx.py
Line: 237:237
Comment:
comment still references the old action name `generate_next_step`
```suggestion
"Mock generated next step", # mock response for the generate_next_steps action
```
How can I resolve this? If you propose a fix, please make it concise. |
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
tgasser-nv
approved these changes
Feb 10, 2026
tgasser-nv
left a comment
tgasser-nv
left a comment
Collaborator
There was a problem hiding this comment.
Looks good! Can you run a local integration test to make sure this works with prod OpenAI and NVCF-hosted models?
| if not events: | ||
| return history | ||
|
|
||
| system_actions = [ |
Collaborator
There was a problem hiding this comment.
nit: Doesn't need to be fixed but why do we have 3 different naming conventions? There are names with spaces (call activefence api), snake case (self_check_input), and CamelCase (AddFlowsAction)
4 tasks
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
3 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.
Description
Fixes a naming mismatch bug where the action
generate_next_step(singular) didn't match the Task enum valuegenerate_next_steps(plural). This mismatch prevented task-specific LLM configuration from working correctly.When users configured a task-specific LLM with
type: generate_next_stepsin their config, the runtime would look forgenerate_next_step_llm(based on the action name) but the config registeredgenerate_next_steps_llm, causing the task to fall back to the main LLM instead.