My change#210
Conversation
There was a problem hiding this comment.
Pull request overview
Adds a new weekly spotlight entry to the HRI integration team’s running progress log.
Changes:
- Inserted a new spotlight section for 2026-03-03.
- Added an updated member status table for that week.
- Documented a development update related to NLP tests and HRI extraction/confirmation behavior.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
You can also share your feedback on Copilot code review. Take the survey.
| @@ -1,5 +1,6 @@ | |||
| # Weekly Spotlights | |||
|
|
|||
|
|
|||
There was a problem hiding this comment.
There’s an extra blank line after the H1 header. Consider removing it to keep spacing consistent with the rest of the document (single blank line between header and first paragraph).
| | Oscar | | | ||
|
|
||
| - **Development** | ||
| - Made nlp tests pass by adding an LLM fallback for extract data node in HRI and a condition so that when a phrase gets classified as no or yes by a thin margin compared to I dont know it returns I dont know. |
There was a problem hiding this comment.
Typo/grammar: "I dont know" is missing an apostrophe. Please change it to "I don't know" (both occurrences in this sentence).
| - Made nlp tests pass by adding an LLM fallback for extract data node in HRI and a condition so that when a phrase gets classified as no or yes by a thin margin compared to I dont know it returns I dont know. | |
| - Made nlp tests pass by adding an LLM fallback for extract data node in HRI and a condition so that when a phrase gets classified as no or yes by a thin margin compared to I don't know it returns I don't know. |
| - Made nlp tests pass by adding an LLM fallback for extract data node in HRI and a condition so that when a phrase gets classified as no or yes by a thin margin compared to I dont know it returns I dont know. | ||
|
|
||
|
|
||
|
|
There was a problem hiding this comment.
The development bullet is a single long run-on sentence and is hard to scan in a weekly spotlight. Consider splitting it into multiple bullets or sentences, and formatting node/component names (e.g., extract data node / ask_and_confirm) as inline code for readability.
| - Made nlp tests pass by adding an LLM fallback for extract data node in HRI and a condition so that when a phrase gets classified as no or yes by a thin margin compared to I dont know it returns I dont know. | |
| - Made nlp tests pass by adding an LLM fallback for the `extract data` node in HRI. | |
| - Added a condition so that when a phrase is classified as "no" or "yes" by a thin margin compared to "I dont know", it returns "I dont know". |
|
What's up with this pr @luisrosales852 @GilMM27 ? Should it be updated & merged, or should we close it? Also @luisrosales852 use descriptive and appropriate names for both the branch, and pr title. |
No description provided.