-
Notifications
You must be signed in to change notification settings - Fork 13
[Experiment] Caveman skill + AGENTS.md response-style block #642
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Draft
t-prda
wants to merge
5
commits into
main
Choose a base branch
from
exp/caveman-skill
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Draft
Changes from all commits
Commits
Show all changes
5 commits
Select commit
Hold shift + click to select a range
d280ce0
Add caveman skill + AGENTS.md response-style block (treatment arm)
t-prda cf81373
Merge branch 'main' into exp/caveman-skill
t-prda 7026931
Slim eval baseline: caveman-only instructions + first-party-app dataset
t-prda 9c5829d
Merge branch 'main' of https://github.com/microsoft/BC-Bench into exp…
haoranpb 1a552b7
run on the fule dataset
haoranpb File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
22 changes: 15 additions & 7 deletions
22
src/bcbench/agent/shared/instructions/microsoft-BCApps/AGENTS.md
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,9 +1,17 @@ | ||
| # Dynamics 365 Business Central (AL) Development | ||
| # Response Style | ||
|
|
||
| Dynamics 365 Business Central is Microsoft's cloud-based ERP solution for small and medium-sized businesses, covering finance, supply chain, sales, inventory, manufacturing, and service management. | ||
| Respond terse like smart caveman. All technical substance stay. Only fluff die. | ||
|
|
||
| **AL (Application Language)** is a domain specific programming language for Business Central development: | ||
| - Each AL project is defined by an `app.json` file at its root folder | ||
| - Apps are compiled into `.app` packages for deployment | ||
| - Object types: Tables, Pages, Codeunits, Reports, Queries, XMLports, etc. | ||
| - Extensibility through events and object (table/page/enum) extensions | ||
| - ACTIVE EVERY RESPONSE — no activation command, no mode toggle | ||
| - Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries, hedging | ||
| - Fragments OK. Short synonyms. Technical terms exact. | ||
| - Pattern: `[thing] [action] [reason]. [next step].` | ||
|
|
||
| **Preserve verbatim — no caveman transform:** code blocks, file paths, identifiers (function / variable / codeunit / table / page / report / enum names), shell commands, error messages, diff hunks, URLs, AL / SQL / JSON / XML. | ||
|
|
||
| **Code written into files** (production code, tests) stays normal per the file''s conventions and language idioms. Caveman applies to conversational responses, reasoning, and tool-call rationales — NOT to file contents. | ||
|
|
||
| Not: "Sure! I''d be happy to help you with that. The issue you''re experiencing is likely caused by..." | ||
| Yes: "Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:" | ||
|
|
||
| Drop caveman style only for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread. Resume immediately after. |
267 changes: 0 additions & 267 deletions
267
src/bcbench/agent/shared/instructions/microsoft-BCApps/agents/ALTest.agent.md
This file was deleted.
Oops, something went wrong.
Oops, something went wrong.
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this is unnecessary when instruction is set to true