* Add 18 more community AL/BC patterns across appsource, data-modeling, error-handling, security, style, testing, ui, upgrade, and web-services
Second contribution from CURABIS ApS, generalized from patterns observed across real AppSource/PTE development. Cross-checked against the current microsoft/knowledge corpus before opening; several originally-drafted candidates were dropped as duplicates of existing files.
* Address Jesper Schulz-Wedde's review on PR #157
- release-must-update-app-version.md: reframe around AppSource's actual
strict full-version-ordering requirement; scope branching-policy
claims as team convention, not platform rule.
- pictures-must-use-media-not-blob.md: MediaSet is a collection of
independent media objects, not automatic image variants/thumbnails.
- log-writes-must-survive-rollback.{md,good.al}: StartSession's only
data channel into the new session is its Record parameter to a
TableNo-scoped codeunit; a setter called on a local instance before
starting the session populates nothing in the new session.
- exposed-objects-must-be-in-a-permission-set.md: correct the three
exposure mechanisms (Web Services config, PageType/QueryType=API,
ServiceEnabled as a method-only attribute).
- pages-must-not-contain-business-logic.md: scope to persisted
mutations and cross-entry-point rules; presentation-only
calculations and table-owned invariants are not violations.
- given-blocks-must-cover-full-precondition-chain.good.al: replace
invented LibrarySales calls with the real API
(CreateCustomer/CreateSalesOrderForCustomerNo/PostSalesDocument).
- test-feature-scenario-tags.{md,good.al}: move [SCENARIO] inside the
test procedure body to match the current BCApps corpus; keep
[FEATURE] at codeunit level per Microsoft's own documented option.
- ui-test-codeunit-naming.md: scope the _UT suffix and adjacent-ID
pairing as an explicit team convention, not a BCApps-wide standard.
- page-design-must-match-bc-page-type-conventions.md /
table-design-must-match-bc-table-type-conventions.md: Card's
single-key primary-key claim is a contextual heuristic, not a
mandatory constraint (Ship-to Address, Customer/Vendor Bank Account
are real composite-key Card pages); a Subsidiary table with its own
identity commonly gets List+Card, not Worksheet/Tabular.
- api-page-least-privilege-write-access.{md,good.al}: only page-placed
fields are ever exposed; set InsertAllowed/DeleteAllowed=false in the
good sample so a narrow field set can't still create/delete records.
- source-organized-by-feature-not-object-type.md,
test-one-when-per-test.md: scope as team/testing-design conventions,
not Microsoft platform requirements.
- upgrade-tag-logic-must-not-nest-deeply.md: add the Microsoft Learn
citation that already backs the two-level nesting limit.
- Wire the new articles into the testing/data-modeling/error-handling/
security/ui review skills' candidate-selection signals.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* Address second round of Jesper Schulz-Wedde's review on PR #157
- log-writes-must-survive-rollback.good.al: fixed invalid trigger
OnRun(var Rec: ...) declaration; Rec is implicit when TableNo is set.
- exposed-objects-must-be-in-a-permission-set.md: distinguished the three
exposure mechanisms (page/query web service or API, codeunit published
as a web service, [ServiceEnabled] bound action on a page) and their
actual permission targets (page/query "..." = X vs codeunit "..." = X).
- code-must-not-change-workdate.md: scoped from an absolute "never" to
"not as a side effect of unrelated logic" - verified real WorkDate(x)
setter usage in BCApps demo-data generators and test codeunits.
- bcpt-scenarios-must-be-app-specific.md: SingleInstance and
StartScenario/EndScenario reframed as context-dependent patterns, not
mandatory requirements - BCPT Create Customer uses neither.
- test-feature-scenario-tags.good.al/.bad.al: replaced the invented
LibrarySales.CreateCustomerWithPrice/"Item Price Mgt." calls with a real,
verified price-list-line test using Library - Sales/Library - Inventory/
Library - Price Calculation.
- page-design-must-match-bc-page-type-conventions.md: scoped the missing
UsageCategory anti-pattern to pages intended as searchable entry points.
- defensive-vs-offensive-code-must-match-blast-radius.md/.good.al/.bad.al:
replaced the VAT registration number "low blast radius" example with a
genuinely cosmetic field (customer home page URL).
- source-organized-by-feature-not-object-type.md: anti-pattern reframed as
inconsistency with a repo's own convention, not the object-type scheme
itself.
- pictures-must-use-media-not-blob.md: removed leftover "image variants"
wording contradicting the already-corrected MediaSet description.
Proactively fixed while sweeping all fixtures for invented APIs:
- given-blocks-must-cover-full-precondition-chain.bad.al: PostSalesOrder
called with wrong arity and referenced an undeclared variable.
- ui-test-codeunit-naming.good.al/.bad.al: replaced the same fake
"Item Price Mgt."/TestPage "Item Price" with real Library - Sales calls
and the real Customer Card TestPage.
Worklist completeness: added review-skill cues for the 12 of 18 new rules
that had none (al-appsource-review.md, al-data-modeling-review.md,
al-error-handling-review.md, al-security-review.md, al-style-review.md x3,
al-testing-review.md x2, al-ui-review.md, al-upgrade-review.md,
al-web-services-review.md), and fixed test-feature-scenario-tags' cue,
which only matched the compliant (tagged) shape instead of the anti-pattern
(untagged/generic-named test).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* Fix ten focused correctness items plus sample links from Jesper's 2026-09-15 re-review
Six carried-over threads:
- api-page-least-privilege-write-access fixtures: added the mandatory
EntityName/EntitySetName properties (AL0485).
- pages-must-not-contain-business-logic fixtures: Sales Line has no
"Total Amount" field; replaced with the real "Line Amount" (field 103).
- test-feature-scenario-tags.good.al and test-one-when-per-test.good.al:
CreatePriceHeader leaves a price list in Draft status, which price
calculation ignores. Added Validate(Status, Active) + Modify before the
sales line that depends on it. Verified Status field/enum against
PriceListHeader.Table.al and PriceStatus.Enum.al in the BCApps clone.
- exposed-objects-must-be-in-a-permission-set.md: a published codeunit is
a SOAP endpoint (SOAP is deprecated), not OData - Page/Query are the
OData object types. Corrected and pointed new integrations at API
pages/queries instead.
- al-error-handling-review.md: the log-writes-must-survive-rollback cue
selected on Session.StartSession, which only appears in the compliant
fix, never in the anti-pattern - the bad fixture could never be
worklisted. Recued on the actual risk shape (log insert around a
failed TryFunction/GetLastError* path, then raise/propagate), with
StartSession as an explicit compliant discriminator instead.
- page-design-must-match-bc-page-type-conventions.md: the enum value is
NavigatePage, not Navigate; noted the type list is a selected subset,
not an exhaustive PageType catalogue (PromptDialog, ConfigurationDialog,
UserControlHost, XmlPort also exist, out of this article's scope).
Four new correctness gaps:
- release-must-update-app-version.md: "the version is the only identity"
was backwards - id is the app's stable identity, version identifies a
release/code-state of it.
- defensive-vs-offensive-code-must-match-blast-radius.good.al: the "low
blast radius" example had no else branch, so a failed Customer.Get()
left the field at its prior/default value instead of the explicit
chosen fallback the article claims to demonstrate. Added the else.
- bcpt-scenarios-must-be-app-specific.good.al: InitTest and both measured
StartScenario/EndScenario sections were empty/comment-only, so the
"app-specific" fixture measured no actual work. Filled in a real,
self-contained header+line creation path.
- upgrade-tag-logic-must-not-nest-deeply.good.al: the flattened version
dropped both safety conditions the bad fixture had (Discount % = 0,
nonblank posting group), silently changing behavior instead of just
removing nesting. Extracted the guarded update into a helper with both
conditions preserved as early exits.
Also converted this PR's remaining plain-backtick "See sample:" sample
references (16 articles) to the READ-convention markdown-link form,
matching the fix already made on #156/#158.
Rebased onto upstream/main (conflicts in al-ui-review.md, al-style-review.md,
al-upgrade-review.md against merged upstream PRs - all additive, both
sides' worklist cues retained).
* Fix four merge-critical issues from Jesper's 2026-09-22 review
- pages-must-not-contain-business-logic.good.al/.bad.al: the "good"
codeunit still directly assigned real Sales Line."Line Amount" and
called Modify(), bypassing the field's normal Validate cascade
(discount, VAT, related-amount maintenance) - persisting inconsistent
document lines regardless of which object the code lived in. Replaced
the real Sales Line example with a self-contained "Sample Order Line"
table and switched the codeunit to Validate()/Modify(true), so the
fixture demonstrates the page-vs-codeunit separation without teaching
unsafe direct field writes to a real BC document table.
- bcpt-scenarios-must-be-app-specific.good.al: Customer.FindFirst()
assumed a pre-existing customer (fails against an empty environment),
and a session-local NextNo counter for the header key collides across
concurrent BCPT sessions and repeated runs. Creates its own customer
when none exists, and generates keys from CreateGuid() instead of an
in-memory counter.
- upgrade-tag-logic-must-not-nest-deeply: the rule conflated two
different things - nesting one tag's existence check inside another
(the real anti-pattern Microsoft's guidance warns against) with
having business-data safety conditions inside a single tagged
migration's own loop body (which Microsoft's own worked example does,
and its own design guidance explicitly requires: "Implement extra
safety checks to avoid data corruption, even though you're using
upgrade tags"). Rewrote the Description/Best Practice/Anti Pattern to
scope the rule to actual tag nesting and migrations blended under one
tag, and rewrote both fixtures: good.al now shows two safety
conditions correctly nested inside one migration's own loop plus a
second, genuinely separate migration as its own flat tagged
procedure; bad.al now shows the real anti-pattern, one tag's check
nested inside another's guarded body.
- table-design-must-match-bc-table-type-conventions: the rule and its
worklist cue fired on any new table with a keys block, forcing
buffers, queues, logs, mapping tables, and staging tables into the
nearest-looking one of nine business-record archetypes. Added an
explicit scope note that these nine types aren't an exhaustive table
catalogue, and narrowed the al-data-modeling-review.md cue to require
positive evidence (a type-specific naming suffix, key shape, or
usage) before worklisting, instead of a bare keys/primary-key
declaration.
* Narrow upgrade-tag nesting cue to match revised article
Cue now flags only nested upgrade-tag checks or functionally unrelated
migrations under one tag, and explicitly excludes record loops and
business-data safety guards belonging to a single migration.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* Add 3 more AL/BC patterns from CURABIS Academy testing course material
Third batch from CURABIS ApS: item-ledger-entry document-no lookup after Ship-and-Invoice posting, TestPage.Visible()/.Enabled() as the mechanism for verifying field UI state, and LibraryUtility.GenerateGUID() for collision-free test fixture values.
* Address Jesper Schulz-Wedde's review on PR #158
- use-generateguid-for-unique-test-fixture-values.md: GenerateGUID()
is a Code[10] number-series value, not a real GUID; truncating it
with CopyStr for a shorter field cuts off the changing digits. Point
to GenerateRandomCode/GenerateRandomCodeWithLength/GenerateRandomXMLText
instead, which verify uniqueness against the actual table.
- Split use-testpage-visible-enabled-to-verify-field-ui-state.md: drop
its editability claim (the sample opens with OpenView() and asserts
Enabled(), which verifies enabled state, not editability — Editable()
and Enabled() are distinct TestField methods). New companion article
use-testpage-editable-to-verify-field-editability.md covers Editable()
with OpenEdit() specifically.
- Wire GenerateGUID/CopyStr and TestPage Visible/Enabled/Editable cues
into al-testing-review.md, and the Item Ledger Entry/Last Shipping No.
posting cue into al-data-modeling-review.md.
The Item Ledger Entry article itself was independently verified against
current BCApps source and needs no changes.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* Address second round of Jesper Schulz-Wedde's review on PR #158
- use-generateguid-for-unique-test-fixture-values.md/.good.al: documented
each LibraryUtility helper's actual behavior, verified against
LibraryUtility.Codeunit.al. GenerateRandomCode opens the target table as
a temporary RecordRef, so despite taking TableNo it never checks real
data. GenerateRandomXMLText performs no table lookup at all. Only
GenerateRandomCodeWithLength/GenerateRandomCode20 (capped at Code[10]/
Code[20]) genuinely verify against the real table. Fixture switched to
GenerateRandomCodeWithLength where the comment claims verified
uniqueness.
- al-testing-review.md: rewired the cue to catch the actual anti-pattern
(hardcoded literals, hand-built uniqueness, short-field GUID truncation)
instead of only matching the compliant GenerateGUID()+CopyStr shape;
broadened tokens to include TestPage, Library - Utility, and
.Visible()/.Enabled()/.Editable().
- al-data-modeling-review.md: restricted the Item Ledger Entry
Last-Shipping-No. cue to sales combined posting; purchase combined
posting is Receive+Invoice and uses different fields entirely.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* Fix remaining correctness issues from Jesper's 2026-09-15 re-review
- use-generateguid-for-unique-test-fixture-values.md: narrowed the
collision rule to primary-key/unique-lookup fields - an ordinary
descriptive field carries no uniqueness constraint, so a hardcoded
or deterministic value there isn't the anti-pattern (the article and
its al-testing-review.md worklist cue both said "primary-key or
descriptive field"). Also corrected GenerateRandomCode: it opens its
target table as a temporary RecordRef that starts and stays empty,
so its repeat/until loop always exits after one iteration and never
retries even within a single test run - the "non-colliding within a
test run" claim was false. It's the rightmost N characters of
GenerateGUID()'s sequential series, so a short field's value cycles
(Code[1] repeats every 10 calls, Code[2] every 100). Verified against
LibraryUtility.Codeunit.al in the BCApps reference clone.
- item-ledger-entry-document-no-follows-last-shipping-no: both
fixtures called FindSet() without consuming its optional Boolean,
which raises a runtime error on an empty result set - the opposite
of the article's own claimed "silently matches zero rows, no error"
behavior. Wrapped in `if ... then;` per the existing
guard-database-reads.good.al idiom.
- al-data-modeling-review.md: widened both not-applicable scope
clauses (intro and outcome) to include dimension wiring, posting-
routine structure, and Item Ledger Entry document-number lookups -
the leaf declared itself not-applicable outside setup/master/key/
numbering/block/audit surfaces despite having a targeted cue for
this PR's own new article.
- Converted this PR's 8 plain-backtick "See sample: `x.good.al`."
references (across all 4 new articles) to the READ-convention
markdown-link form required by Knowledge-Retrieval.ps1.
Rebased onto upstream/main (one conflict in al-data-modeling-review.md
intro wording, merged).
* Stop routing GenerateRandomCode20 as compliant for shorter fields
al-testing-review.md's cue presented GenerateRandomCodeWithLength and
GenerateRandomCode20 as interchangeable options for "a shorter field
needing real verified uniqueness." They aren't: verified against
LibraryUtility.Codeunit.al, GenerateRandomCode20 truncates
GenerateGUID()'s sequential value down to the target field's length by
keeping the leftmost (slowest-changing) characters via PadStr, so its
retry loop against a field shorter than 20 can churn through the same
truncated prefix for a long time. GenerateRandomCodeWithLength has no
such problem (it generates exactly the requested length of random
text). The knowledge article itself already scoped GenerateRandomCode20
to Code[20] correctly - only the skill cue needed narrowing to match.
---------
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
* Add 18 community AL/BC patterns across style, data-modeling, web-services, appsource, breaking-changes, performance, and testing
Contributed by CURABIS ApS, generalized from patterns observed across real AppSource/PTE development. Each article follows the knowledge file format (frontmatter, Description/Best Practice/Anti Pattern, sibling .good.al/.bad.al samples).
* Address Jesper Schulz-Wedde's review on PR #156
- Rename 3 articles so their .good.al/.bad.al companion stems match
(do-not-change-primary-key, testfield-required-setup-field,
al-identifiers-english), fixing the R14 orphan-sample errors.
- do-not-change-primary-key.good.al: include Flow in the new table's
own primary key so it actually models the discriminating dimension.
- al-build-output-must-not-pollute-project-root.md: drop the
unsubstantiated AL0197 causal claim and the non-existent
al.outputPath setting; reframe as build-artifact hygiene sourced
from ALTool --outfolder / al_build outputPath.
- prefer-email-module.md: Email Message is Codeunit 8904, not a table;
distinguish it from the underlying Sent/Outbox/Draft storage.
- file-datatype-saas.md: File.Open/Create/Read/Write fails to compile
against a Cloud-scoped project, it does not compile and silently
fail at runtime.
- namespace-must-be-verified-from-source.md: narrow to "resolve from
the referenced object's source or symbols," since source-file line
one is not the only authoritative source (symbol packages, comments
before the namespace line).
- test-data-must-be-random-and-complete.md: drop "assume an empty
database" and "collision-free" absolutes; reframe around
independence from unrelated business records and reserving explicit
values for scenario-defining inputs.
- binary-choice-must-be-boolean.md: scope to genuine true/false
semantics, not mechanical two-member-enum-to-boolean conversion.
- document-report-word-layout.md: scope down to a sourced Microsoft
Learn recommendation instead of an unconditional performance
guarantee; cite the three Learn pages.
- Wire the new articles into their review skills' candidate-selection
signals (file-datatype-saas, prefer-email-module,
namespace-must-be-verified-from-source, var-parameters-require-an-
addressable-variable) so they can actually enter a worklist.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* Fix dimension-management-wiring.md: ValidateShortcutDimCode and CreateDim
do not exist on the current DimensionManagement codeunit
Verified against microsoft/BCApps: the real master-table validation
procedure is ValidateDimValueCode (or ValidateShortcutDimValues when a
DimSetID is also needed), and the real document-side inheritance
procedure is GetDefaultDimID, not CreateDim. Caught from Jesper
Schulz-Wedde's review thread, which had been partially hidden by
GitHub's comment folding.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* Address second round of Jesper Schulz-Wedde's review on PR #156
- dimension-management-wiring.md/.good.al: split into the two distinct
models the article was conflating - master data (Default Dimension
records via ValidateDimValueCode/SaveDefaultDim) vs. transactional/
document data (a single Dimension Set ID assembled via AddDimSource +
GetDefaultDimID, verified against BCApps' ExchRateAdjmtProcess.Codeunit.al).
Added a compiling document-table example alongside the existing master
table one.
- Deleted api-page-flowfields-must-be-calcfields (.md/.good.al/.bad.al):
Microsoft's own FlowFields documentation states a FlowField used as a
control's direct source expression is automatically calculated on any
page - no API-page exception is documented, and none could be
reproduced.
- prefer-email-module.bad.al/.md: Codeunit Mail has no Send/GetErrorDesc
members; fixed to the real current 7-argument CreateMessage signature,
and corrected the claim that the legacy path "still runs" - its base
implementation no longer sends anything, only raises integration events.
- check-post-line-batch-pattern.md/.good.al: reframed from a universal
invariant to the standard shape, naming the real Gen./Item/CA/Res./Job/
Insurance/Mfg. Item/FA Jnl.-Check Line/-Post Line/-Post Batch codeunits
it's based on. Added the missing Check Line companion codeunit so the
good fixture is internally complete.
- test-data-must-be-random-and-complete.good.al: removed leftover
"collision-free" wording contradicting the already-corrected article text.
- fixed-choice-set-must-use-enum-not-integer.md: removed the reintroduced
state-count heuristic ("the line is the state count"), aligned with
binary-choice-must-be-boolean.md's semantics-based distinction.
- namespace-must-be-verified-from-source.md: removed the false claim that
the compiler and AL Language Server use different namespace-resolution
rules.
- intrinsic-al-functions-must-use-modern-casing.md: removed the unverified
claim that PascalCase is the VS Code formatter's default output.
Worklist completeness: added cues for the 8 rules in data-modeling,
testing, performance, and web-services that had none (Jesper's explicit
ask), plus the same gap in all 7 style rules from this PR (not explicitly
named this round, but the identical systemic issue) - 15 cues total across
al-data-modeling-review.md, al-testing-review.md, al-performance-review.md,
al-web-services-review.md, and al-style-review.md.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* Fix remaining correctness issues from Jesper's 2026-09-15 re-review
- dimension-management-wiring: SaveDefaultDim's third argument is the
shortcut dimension number (1-8), not the field's AL field ID; the
fixture passed FieldNo(...) = 10. GetDefaultDimID's InheritFromDimSetID
must be 0 when recomputing after the linking record changes, not the
document's existing Dimension Set ID (which would retain the previous
customer's leftover dimensions). Verified against
DimensionManagement.Codeunit.al and BankDepositHeader.Table.al in the
BCApps reference clone.
- check-post-line-batch-pattern: "Post Line writes exactly one line to
the ledger" overclaimed - Gen. Jnl.-Post Line alone calls InsertGLEntry
from a dozen call sites (balancing entry, VAT, currency rounding,
deferrals) and can write several G/L Entries per journal line.
Reworded to "posts exactly one journal line" and softened the
"distinct, non-overlapping responsibilities" absolute.
- namespace-must-be-verified-from-source.bad.al: dropped the "resolves
in a local build, fails in VS Code" comment (taught an inherent
compiler/language-server disagreement that isn't real); reframed as
stale/cached symbols, matching the prose fix already made.
- file-datatype-saas.good.al: replaced the deprecated 5-argument
UploadIntoStream overload with the current 2-argument one, and
actually staged through TempBlob as the article's own Best Practice
instructs (the declared TempBlob variable was previously unused).
- test-data-must-be-random-and-complete: no longer treats a
short-but-valid value as defective merely for being "underfilled" -
AL field lengths are maxima, not minimums. Scoped to missing values
or a scenario with an explicit length/format requirement (e.g. a
truncation test). Updated the al-testing-review.md routing cue to
match.
- stored-derived-fields-must-not-be-exposed-directly: stopped mandating
source-field exposure as part of the core pattern: the good fixture
exposed only one of the derived value's two inputs (Hours Used, not
Budgeted Hours), making the claimed "so the consumer can verify it"
impossible. Reframed as an optional, all-or-nothing addition and
fixed the fixture to expose both inputs.
Rebased onto upstream/main to resolve conflicts in
al-breaking-changes-review.md, al-data-modeling-review.md,
al-performance-review.md, and al-style-review.md against merged PRs
#148 and #153; all sides' worklist tokens/cues retained.
* Fix remaining READ-convention sample links across this PR's 18 articles
The same plain-backtick "See sample: \`x.good.al\`." form fixed on
al-methods-limited-during-write-transactions (PR #161) turned up
repo-wide on 15 more of this PR's articles - Knowledge-Retrieval.ps1
requires the markdown-link form to associate a sample with its
article. All 16 fixed; the four local validators (frontmatter,
knowledge-index, knowledge-retrieval, review-fixtures, skill-index)
pass.
* Fix two merge-critical correctness issues from Jesper's 2026-09-22 review
- api-page-key-fields-must-be-editable-on-insert.good.al and
stored-derived-fields-must-not-be-exposed-directly.good.al: both were
writable API pages missing DelayedInsert = true, contradicting this
repo's own api-page-delayedinsert-true rule - the canonical "good"
samples were teaching code BCQuality itself flags.
- dimension-management-wiring.good.al: UpdateDimensionSetID exited
early when Customer.Get failed, leaving the previous customer's
shortcut dimension and Dimension Set ID in place - the same staleness
bug the InheritFromDimSetID = 0 fix (from the prior review round) was
meant to prevent, just triggered by a failed lookup instead of a
successful one. Now clears the shortcut field and recomputes with an
empty source list on a failed lookup too, so GetDefaultDimID
correctly returns an empty Dimension Set ID instead of never running.
---------
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
* Add Finance posting domain-knowledge pilot
Adds three atomic domain-rule knowledge files under community/knowledge/finance/ as a pilot for Type-A (normative) Business Central domain knowledge: post through the posting engine, treat posted ledger entries as immutable, and treat the Dimension Set ID as the source of truth for dimensions. Includes a good/bad AL sample pair for the posting rule.
These encode BC-specific invariants that LLMs reliably get wrong, fitting the existing remedial/atomic knowledge grain with no schema or contract changes. Passes the repo frontmatter validator and is discovered by the knowledge index.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Clarify editable operational fields on posted ledger entries
Addresses review feedback from @JeremyVyska on PR #57: the immutability rule applies to financial content, not the whole entry. Reframes the Description around financial content and gives the operational-field exception (payment/application data, on-hold, applies-to, communication fields edited via CustEntry-Edit/VendEntry-Edit and the ledger entry pages) its own paragraph in Best Practice instead of understating it as a narrow set.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Expand Finance pilot into a source-verified review domain
Move Finance knowledge to the Microsoft-owned layer, add nine scoped rules with eighteen AL samples, and register bounded Finance review with complete paired evaluation coverage.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* Fix Finance review applicability and ownership boundaries
Remove application-area gating and later VAT-field dependencies, align dynamic shared conventions, separate SCM ownership, and keep journal examples focused on the intended invariant.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* Remove logo branding (#194)
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* Add title and description to README
* Add foundational AL developer knowledge (#195)
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* Clarify locale-safe DateFormula Evaluate inputs (#193)
* Clarify locale-safe DateFormula Evaluate inputs
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* Normalize DateFormula article sections
Keep the analyzer-gap explanation in Description and its scoped probe evidence in References, without a novel Validation section. Normative guidance and fixtures are unchanged.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* Add SCM functional knowledge domain (#192)
* Add SCM functional knowledge domain
Introduce nine source-backed rules with original AL sample pairs, bounded SCM review routing, and complete positive/clean evaluation coverage.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* Normalize SCM knowledge and review ownership
Align article and AL sample conventions, keep BC facts separate from review mechanics, and clarify reciprocal Finance ownership without bespoke shared test assertions.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* knowledge(events): ChangeCompany leaves triggers and trigger-event subscribers running in the calling company
ChangeCompany redirects only the data access of a record variable; Learn states that triggers still run in the current company. The database trigger events are raised on every database operation and only pass RunTrigger to the subscriber, so Insert(false) after ChangeCompany still runs every subscriber in the calling company. Generated code either assumes the record 'becomes' a target-company record, or switches RunTrigger off and hand-copies the trigger logic, leaving the subscribers writing to the wrong company; none of the tested runs reached StartSession with the company parameter.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* knowledge(events): qualify StartSession async semantics and fix concurrency-unsafe sample key
Addresses PR #152 review: StartSession is a fire-and-forget background
session (Ok reports only whether it started, not whether the codeunit
succeeded, and errors inside it do not propagate), so the Best Practice
now scopes the recommendation and calls out the durable status/error
channel a synchronous-success write needs. The good sample's
FindLast()+1 entry-number pattern raced under concurrent background
sessions; switched to AutoIncrement, which the platform guarantees is
unique across concurrent transactions.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* knowledge(events): serialize the setup-counter increment; promote article and wire the review skill
PR #152 round 3 (JesperSchulz):
- The good sample's OnAfterInsertEvent subscriber still raced on the
shared "Transfer Setup Good" singleton (Get/increment/Modify);
AutoIncrement only protected the request key. Added
TransferSetup.LockTable() before Get() to serialize concurrent
background sessions.
- Promoted changecompany-runs-triggers-in-the-calling-company from
community/knowledge/events/ to microsoft/knowledge/events/, and wired
ChangeCompany/StartSession/RunTrigger tokens plus a targeted
detection cue into microsoft/skills/review/al-events-review.md so a
diff containing the anti-pattern reliably worklists this article,
preserving the documented RunTrigger=false hand-off exception.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
---------
Co-authored-by: waldo1001 <12088142+waldo1001@users.noreply.github.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Generate a deterministic action-skill index from frontmatter, publish structural schemas for orchestration and findings, and validate flat review composition in CI.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: dayland <dayland@microsoft.com>
Copilot-Session: 76eb42c4-2acd-4f9c-a898-f4a44f9d46f7
* Add bounded knowledge retrieval
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 0d8b7764-f15a-49ea-8d50-d9147334f8af
* Fix bc-version overflow and pathless-row identity in bounded retrieval
Catalog matching compared an Int32 -BCVersion against a bigint range bound.
PowerShell coerces the right operand to the left operand's type, so a bound
wider than Int32 threw a conversion error and failed the whole domain catalog
rather than the single row. Metadata validation already accepts such bounds,
so compare as bigint on both sides.
The shared pager built its oversized-row message with $row.path, which
throws under Set-StrictMode -Version Latest when a row carries no path,
replacing the explicit bound failure with a property-lookup error. Resolve the
path defensively for dictionary and object rows so the offset-based fallback
is reachable.
Both paths gain regression coverage that fails without these fixes.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 0d8b7764-f15a-49ea-8d50-d9147334f8af
Retire deterministic compiler and analyzer duplicates, remove their review routing, and clarify the admission test for contextual analyzer knowledge.
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* Document standalone review runner contract
Keep model selection and scheduling outside BCQuality while allowing orchestrators to run isolated review leaves concurrently with deterministic rollup semantics.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* Support complete app folder reviews
Define folder-path as a current-state review scope and accept it across the standalone adapter, broad coordinator, and every AL review leaf.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* Add walk-up app review quick start
Put the complete app-folder installation and prompt flow directly in the README so partners can discover the standalone experience without reading integration details first.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* Organize conceptual guides under docs
Move architecture and standalone runner documentation out of the repository root, add a documentation index, and update all inbound links.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
The narrowed UI-handler guidance still stated the execution rule without the
qualifier the linked Microsoft reference uses. The article said every listed
handler must execute at least once, and the testing leaf skill asked for
`[HandlerFunctions(...)]` to match the invoked handlers exactly. The reference
says every *nonoptional* listed handler must execute, and that send-notification
and recall-notification handlers can be optional. As written, an agent could
flag a deliberately unused optional notification handler.
The discriminator is narrower than the handler type. Both
`[SendNotificationHandler([HandlerIsOptional: Boolean])]` and
`[RecallNotificationHandler([HandlerIsOptional: Boolean])]` take an explicit
optionality argument, so `[SendNotificationHandler(true)]` is exempt while the
same attribute written without the argument stays nonoptional like every other
handler type. Keying the exemption on the argument rather than the type keeps it
checkable from the diff and avoids the opposite false positive, where an agent
stops flagging genuinely nonoptional notification handlers.
Changes:
- The article now states the nonoptional qualifier, explains that optionality is
declared rather than inferred, and adds an explicit do-not-flag clause. That
clause also forbids proposing removal, because the listed entry is what keeps
the test passing on the runs where the notification does fire.
- The testing leaf skill carries the same boundary in its `ui-handlers-in-tests`
cue, and its mechanical-fix list no longer allows removing a listed optional
notification handler as a one-click suggestion.
- `SendNotificationHandler` and `RecallNotificationHandler` were missing from the
skill's testing token list, so notification handlers were not reliably
surfaced to the relevance step at all. Both are now listed.
- The good sample gains a test that lists an unreached
`[SendNotificationHandler(true)]`; the bad sample gains the mirror image, an
unreached `[SendNotificationHandler]` with no optionality argument. The pair
differs only by that argument, which is the point.
- `evaluation/review-fixtures.json` pins the testing domain to
`ui-handlers-in-tests` so the boundary is exercised: the good sample is the
clean control at `minimumCleanRate` 1.0 and the bad sample is the expected
finding. Keywords were retagged with `notification` and `optional-handler`.
validate_frontmatter.py reports 0 errors; Test-ReviewFixtures.ps1 passes with
32 cases across 16 leaf domains and resolves the testing fixture to this article.
The article was rewritten to say a reset is required only when the value can
carry over, and its H1 was updated to match, but three artefacts still carried
the old "always initialize to false" premise:
- The slug still read `initialize-ishandled-to-false-before-publishing`, which
contradicts the body. The slug is not cosmetic: Build-KnowledgeIndex.ps1
ranks candidates on keywords, frontmatter dimensions, domain, path and title,
so a stale path pushes selection back toward the behaviour this change
narrows. Renamed to `reset-ishandled-only-when-the-value-can-carry-over`,
following the existing precedent for conditional slugs such as
`unreleased-symbol-change-is-not-a-breaking-change`.
- Keywords still listed `initialization` and `deterministic` and omitted
`false-positive`, the tag this repository uses for suppression articles.
Replaced with `carry-over` and `loop-iteration` and added `false-positive`.
- The good sample demonstrated only the "prefer separate fresh locals" clause
and contained no reset at all, so the article's headline case had no positive
example. It was also asymmetric with the bad sample, which gained a loop
procedure showing a local that carries `true` into the next iteration.
Added the matching loop procedure to the good sample: a local declared outside
the loop is reset at the top of each iteration. That case cannot be solved by
introducing another local, because AL has no block scope, so it is the only
shape that demonstrates the reset the article still requires. It also gives the
engine the correct `suggested-code` shape for the loop finding; without it the
one-click fix adapted from the good sample would propose splitting the variable
rather than adding one line.
Also renamed the sample codeunits from "IsHandled Init ..." to
"IsHandled Carry Over ...", and updated the two references to the old slug:
the events leaf skill cue and the events pin in evaluation/review-fixtures.json.
validate_frontmatter.py reports 0 errors; Test-ReviewFixtures.ps1 passes with
32 cases across 16 leaf domains and resolves the events fixture to the renamed
article.
Online eval shows style/variable-declaration-order-by-type firing as false positives (tp/fp 2/1) at minor. The article title itself is 'Order variable declarations by type (CodeCop AA0021)', so it is analyzer-redundant exactly like the this-keyword AA0248, label-suffix AA0074, and ToolTip rules already calibrated to info. Add AA0021 to the analyzer-redundant list so it emits at info and stops competing with substantive style review.
Co-authored-by: wenjiefan <wenjiefan@microsoft.com>
Online eval (182 PRs) shows the reference-less agent-finding channel is where 86% of false positives come from, and it is net-negative in the lowest-yield domains: privacy agent findings score 0 TP / 8 FP and UI/accessibility 1 TP / 11 FP. Restrict these two leaves to knowledge-backed findings only; an uncovered concern is omitted (and, if material and recurring, fixed durably by adding a BCQuality article per the self-improvement loop) instead of emitted with references: [].
* Complete AL review knowledge readiness
Fill telemetry and Query coverage, strengthen thin review domains, correct audited content defects, and add deterministic cheap-model evaluation and reference-integrity safeguards.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 9825b012-e653-496a-9310-c1f4b6f8ac27
* Generalize review fixture discovery
Derive smoke cases from the leaf, domain, and paired-sample conventions so new leaves require no scoring-contract changes. Keep only exceptional selection/context overrides and fail when retrieval metadata cannot rank the selected article.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 9825b012-e653-496a-9310-c1f4b6f8ac27
* Preserve published field IDs in sample
Keep the existing Email and Contact Email field IDs unchanged, clarify that the sample represents an independent baseline, and use a local breaking-change rule for the generic smoke evaluation.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 9825b012-e653-496a-9310-c1f4b6f8ac27
* Clarify published field identity rules
State explicitly that a published field keeps its ID, name, and type while a replacement is added as a separate field under an unused ID.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 9825b012-e653-496a-9310-c1f4b6f8ac27
* Align field obsoletion sample baselines
Use Email field ID 3 as the shared baseline so the bad example demonstrates a same-ID rename while the good example retains the original field and adds a separate replacement.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 9825b012-e653-496a-9310-c1f4b6f8ac27
---------
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
* Emit human-readable domain label on review findings
Add an optional findings[].domain field to the DO review output contract so
each finding carries its own human-readable review-domain display label. Leaf
review skills set it on every finding they emit; the al-code-review super-skill
copies it verbatim during rollup and sets it to "Agent" for its own
cross-cutting agent findings. This decouples consumers from BCQuality's domain
taxonomy: they render finding.domain verbatim instead of maintaining a
sub-skill-id -> label map.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Define domain display-label constraints
Clarify that review domains may contain internal whitespace, punctuation, case-sensitive text, and non-ASCII characters. Require consumers to preserve and safely encode the complete label instead of relying on lossy slugs, matching the replacement BC-ALAgents consumer.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 77d0a40e-8bf5-40ac-a450-40eb0255db03
---------
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Move eight net-new rules into the Microsoft layer, remove six overlapping articles, and update review skill discovery and references.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 0b130227-d418-4bc0-9e7d-ec6a37adf039
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
The al-style-review worked example set findings[0].id to a non-existent
knowledge file (apply-approved-label-suffixes.md) while references[0].path
points to the real file (label-suffix-approved-list.md). The DO output
contract requires id to equal references[0].path for citation-based
findings. Align id to the existing file.
Co-authored-by: wenjiefan <wenjiefan@microsoft.com>
Online-eval data shows the style leaf is the largest source of dismissed
findings. Two causes:
- Mechanical, analyzer-enforced conventions (this-keyword AA0248, label
suffixes AA0074, missing ToolTip, label scope) fire at gating severity
and duplicate what CodeCop/AppSourceCop already report. Calibrate them
to info so a severity-gating consumer drops the redundant noise.
- Correctness/logic/data-integrity defects get reframed as style
conventions and emitted here. Sharpen the scope boundary: such defects
belong to the relevant domain leaf, or to al-code-review's cross-cutting
agent channel when no knowledge file covers them, never to this leaf.
Co-authored-by: wenjiefan <wenjiefan@microsoft.com>
Repair broken knowledge references and align review examples with canonical articles. Correct explicit version gates, restore a missing title, and recognize the plugin directory in the root guard.
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
De-enumerate the AL review leaf list so it lives in exactly one place:
the al-code-review super-skill's frontmatter sub-skills list.
- al-code-review.md: drop the enumerated parenthetical from description
and remove the redundant bullet re-list in the Source section.
- README.md: remove the hardcoded count word and the enumerated domain
list from the leaf-skill sentence.
- validate_frontmatter.py: add cross-file rule R26 asserting a
super-skill's declared sub-skills exactly match the sibling
al-*-review.md leaf files on disk (missing, stale, and unregistered
leaves all fail CI).
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Seed web-services (API v2) knowledge domain
Add eight web-services API page knowledge articles (each with .good.al/.bad.al samples), a new al-web-services-review leaf skill, and wire it into al-code-review and the README.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Trim web-services domain to 6 non-duplicative articles
Drop API entity-naming/camelCase and DelayedInsert articles (owned by the style domain). Reframe the committed-data and API-versioning articles to stay strictly within the endpoint design/behavior lane, and update the leaf skill's worklist tokens and Output example accordingly.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Seed a new breaking-changes (AL API stability) knowledge domain with six
articles plus good/bad AL samples, a new al-breaking-changes-review leaf
skill, and minimal wiring into al-code-review and the README.
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add events knowledge domain and review leaf skill
Add a new `events` knowledge domain covering AL events & subscribers,
wired into the AL review pipeline.
- 3 atomic articles (+ .good.al/.bad.al samples) under
microsoft/knowledge/events/: the IsHandled override pattern, thin
OnBefore/OnAfter integration-event publishers, and static vs manual
subscribers.
- New leaf skill microsoft/skills/review/al-events-review.md sourcing the
events domain.
- Wired into microsoft/skills/review/al-code-review.md (sub-skills + Source
+ description) and README.md (leaf-skill count + domain list).
AL event syntax verified against Microsoft Learn. Samples are
demonstration-only (not compiled by CI). Additive change; no contract change.
Part of #34.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add 12 general AL event-design articles to events domain
Add 12 atomic knowledge articles under microsoft/knowledge/events covering
general AL event-design best practices: IsHandled initialization and OnAfter
preservation, appending new event parameters, position-based event naming,
reusing/extending events, avoiding per-iteration publishing, Temp-prefixing
temporary record parameters, unabbreviated parameter names, preferring the
this keyword over IncludeSender, avoiding loosely typed parameters, not
mutating existing event contracts, and not bypassing critical operations
with IsHandled. Each article ships a .good.al and .bad.al demonstration
sample (object IDs 50240-50296; not compiled by CI). Extend the
al-events-review leaf Worklist with one targeted check per new rule.
Additive only; no contract or wiring change (events leaf already wired).
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Refine events articles after review feedback
Correct wording in five events articles to reflect that AL event
subscribers bind by parameter name, not position:
- add-new-event-parameters-at-the-end: drop the inaccurate claim that
appending a parameter forces subscribers to be updated or causes wrong
values; keep the append-at-end best practice.
- do-not-add-ishandled-to-an-existing-event: reframe from "breaking
change" to the semantic/purpose shift that leaves existing subscribers
pointless; rename the breaking-change keyword to semantic-change.
- name-events-by-publisher-position: extend the good sample with
position-named publishers raised from table and report trigger
contexts.
- initialize-ishandled-to-false-before-publishing: scope the detection
and best practice to events that actually carry a var IsHandled, so an
OnBefore with no IsHandled is not flagged.
- do-not-bypass-critical-operations-with-ishandled: add a litmus-test
definition of a critical operation (code that cannot stand as an
independent, self-contained unit).
Knowledge-only; no contract or wiring change.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Soften Anti Pattern wording in add-new-event-parameters article
Remove the last name-vs-position misconception from the Anti Pattern so it
is consistent with the corrected Description: mid-list insertion is framed
as noisy and harder to review rather than as forcing subscriber re-mapping.
Detection sentence unchanged.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add events domain reviewers to CODEOWNERS
Add @AleksandricMarko and @pchriste-microsoft-com as required reviewers
for the events knowledge domain, matching the existing per-domain expert
ownership convention. Inserted in alphabetical order ahead of the
performance line.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Adds the interfaces knowledge domain covering AL interfaces and enum-with-implementation: three atomic articles with good/bad AL samples, a new al-interfaces-review leaf skill, and additive wiring into al-code-review and the README. Purely additive; no contract change.
Part of #34.
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Make domain-skill knowledge discovery index-aware
The 6 AL domain review skills and read.md now enumerate candidate articles
from the BCQuality knowledge index (knowledge-index.json) instead of opening
every file under the domain folder to read its frontmatter. The worklist
selection predicate is unchanged (keywords intersect diff tokens, or topic
matches a changed object type) - only the discovery source changes, so the
same articles are selected. Full article bodies are read only for worklisted
entries.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Reconcile §Source wording with the lean knowledge index
The BCQuality filter now emits a lean index whose per-article description is a
one-line hint rather than the full verbatim Description. Update the six domain
skills' §Source to say the index carries a one-line description hint (keywords,
title, and a one-line description) instead of the full description. The
worklist selection predicate is unchanged: keywords drive selection and the
agent opens worklisted articles in full for their rule bodies.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Own the knowledge-index generator in BCQuality
The knowledge index is an acceleration of the skills' Source step, and its
schema is part of that contract — so BCQuality should own the generator rather
than each consumer re-implementing it. Add tools/Build-KnowledgeIndex.ps1 (the
parser + lean-description shaping + emit, lifted verbatim from the
BCAppsBCQuality filter prototype) and document the index in agent-consumption.md.
Consumers prune their clone to policy, then call this script; the index stays
in lockstep with the Source contract and every orchestrator gets the same
faithful index for free. The worklist selection predicate is unchanged.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Own knowledge-index generation in BCQuality (runtime + CI), not the consumer
The index is now produced by BCQuality itself: Entry's preparation step
rebuilds knowledge-index.json over the live, already-pruned clone at the start
of every run, and a new CI workflow validates the generator's health
(determinism, full coverage, selection-input integrity). Consumers no longer
invoke or know about the index.
Rebuilding over the pruned clone (vs shipping a committed full-corpus index)
keeps the index exact for any consumer policy: it can never list a denied
article, so policy-excluded rules cannot leak into discovery. READ now states
the index is discovery-only -- a finding must cite an article opened in full,
and rows whose file is absent are discarded before ranking.
- skills/entry.md: new 'Preparation -- knowledge index' precondition
- skills/read.md: index ownership + discovery-only invariant
- microsoft/skills/review/*.md (6): 'BCQuality builds' (not 'the filter emits')
- agent-consumption.md 5a: runtime+CI ownership rationale
- .github/workflows/knowledge-index.yml + scripts/Test-KnowledgeIndex.ps1: generator guard
- .gitignore: never commit the runtime index
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Make runtime index build non-interactive and self-contained
entry.md now gives the exact build command (pwsh ./tools/Build-KnowledgeIndex.ps1)
so the agent's preparation step is unambiguous, and the generator's -BCQualityRoot
parameter is optional (defaults to the clone root) so it runs in non-interactive
-p mode without prompting.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Resolve knowledge-index root to absolute path (cross-platform fix)
Get-ChildItem.FullName is always absolute, so deriving the relative article
path via Substring(\.Length) requires an absolute root. A relative root
such as '.' (used by the CI guard's 'Test-KnowledgeIndex.ps1 -Root .') left the
full path almost intact on Linux, producing bogus 'home/runner/.../knowledge'
paths and failing the coverage check. Normalise both the generator's
-BCQualityRoot and the test's -Root with Resolve-Path before use.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Agent findings (model-judgment findings not backed by a curated knowledge
file) were producing too many false positives. Raise their emission bar and
make them advisory:
- skills/do.md: add a canonical 'Precision bar' for agent findings (emit only
concrete, material defects an expert would agree on; steelman first; an
explicit never-emit list; 'when in doubt, omit') and cap agent-finding
severity at minor (advisory, non-gating), with a promotion note for
severe-but-uncovered concerns.
- al-code-review.md: decouple the mandatory self-review reasoning from output
so emitting zero agent findings is a valid outcome; add the severity cap.
- Six leaf review skills: add the per-domain precision bar and severity cap
(style leaf gets domain-appropriate wording).
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
BCQ now wins on coverage in the synthetic complex benchmark, but only
2 of 25 rendered comments carried GitHub suggestion blocks while the
AIRHack reviewer emitted suggestions for every finding. Tighten the
DO contract and leaf-skill instructions so suggested-code is no longer
a soft affordance for mechanical fixes.
Changes:
- Add optional findings[].suggested-code-omission-reason to the DO
schema.
- Document suggested-code as expected for small, local, mechanical
findings, with examples (delete unreachable code, Count() > 0 ->
not IsEmpty(), move local Label, add missing ToolTip/OptionCaption,
replace string-concatenated Error, change permission token, add an
obvious else/guard branch).
- Require omission reasons when a mechanical-looking finding omits
suggested-code.
- Update all AL leaf skills and al-code-review guidance with the same
stronger contract.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The original DO contract pinned all agent reasoning to the super-skill:
'Agent findings are emitted only by super-skills... Leaf sub-skills MUST
NOT emit agent findings'. This funnels all agent reasoning across all 6
domains through a single super-skill pass, which is the root structural
cause of the attention dilution we have been chasing in BCAppsBCQuality
PRs #28 and #30:
- T1 standalone run showed al-security-review finds rimd-on-read-only
cleanly when run alone, but emits zero agent findings because the
contract forbids it. So obvious things like case-without-else (no
matching KB article yet) get dropped on the floor.
- The al-code-review self-review pass keeps producing 0-1 agent findings
per PR because it is asked to reason across 6 domains in one pass.
The fix is to move agent reasoning into the leaves, bounded by each
leaf's domain. Each leaf now has both knowledge-backed and agent-finding
permissions within its own scope; the super-skill self-review pass
becomes a smaller, cross-cutting role.
skills/do.md
- Replace the 'only by super-skills' / 'MUST NOT' clause with a
two-tier model: leaf sub-skills MAY emit agent findings strictly
within their declared domain; super-skills MAY emit agent findings
for cross-cutting concerns that span domains.
- Update the encoding rules: leaf agent findings have references:[]
and an agent:-prefixed id, no from-sub-skill (the leaf's own report
carries the finding under its own skill.id). Super-skills set
from-sub-skill='agent' for their own self-review findings; when
rolling up leaf agent findings, they set from-sub-skill=<leaf-id>.
- Clarify that 'MUST validate against knowledge' applies to super-
skill self-review candidates only - leaves already validated within
their domain when they decided to emit.
microsoft/skills/review/al-{security,performance,privacy,style,upgrade,
ui}-review.md
- New paragraph after the confidence rules instructing each leaf to
surface domain-specific agent findings when no knowledge file
covers a defect the agent recognises from general AL knowledge.
- Bound the scope: 'The scope is strictly <domain>; defects outside
this domain belong to other leaves and MUST NOT be emitted here.'
- Same validation requirement: check the worklist for a matching
knowledge file first; if one exists, upgrade to a knowledge-backed
finding instead.
microsoft/skills/review/al-code-review.md
- Rewrite the 'Agent self-review pass' subsection. The pass is now
explicitly for cross-cutting concerns that no single leaf could
have surfaced because they span multiple domains. Domain-specific
reasoning belongs in the leaves, not duplicated here.
- Update the rollup behavior to acknowledge leaf-emitted agent
findings: they are rolled up like any other sub-skill finding, with
from-sub-skill set to the leaf id, and are not re-validated by the
super-skill (the leaf already validated within its own domain).
- Drop the 'Leaf sub-skills MUST NOT emit agent findings' line.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Drop the specific pattern checklist (architecture-level smells, error-
handling gaps, magic constants, privacy/telemetry surface, resource
lifecycle - with concrete code patterns under each). It baked case-
study findings into the skill contract and aged badly. Replace with a
domain-level framing: walk by the domains the sub-skills already cover
(performance, security, privacy, style, upgrade, UI) plus the cross-
cutting concerns (architecture, error handling, resource lifecycle).
The domains are anchors for completeness, not a script.
The structural rule - do an explicit self-review pass after the leaves
- is what carries the value. The content of the pass belongs in the
agent's general AL judgement and in the knowledge layer.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Driven by a parity comparison between BCAppsBCQuality PR #27 and
BCAppsCampAIRHack PR #162 on byte-identical content:
| | BCQuality | AIRHack |
|--|--|--|
| Total findings | 6 | 10 |
| Performance | 0 | 4 |
| Security | 0 | 5 |
Standalone runs of al-security-review and al-performance-review against
the SAME diff produced the expected matches (rimd-on-read-only via
inherent-permissions-minimal-grant; redundant-Get via
avoid-redundant-get-when-record-already-loaded). The miss in the live
run is therefore not a knowledge-coverage gap and not a worklist
filtering issue. It is attention dilution inside the al-code-review
super-skill, which the model collapses into one rolled-up generation
pass on real-size PRs.
Changes:
microsoft/skills/review/al-code-review.md
- New 'Execution discipline (mandatory)' subsection in the Action step
that explicitly forbids collapsing leaves into one shared reasoning
pass and requires each sub-skill to walk its Source -> Relevance ->
Worklist -> Action steps as its own iteration before the next leaf
starts.
- Self-review pass is now described as the final, mandatory iteration
with a concrete candidate-category checklist (architecture-level
smells, error-handling gaps, magic constants, privacy/telemetry,
resource lifecycle). Returning zero agent findings on a real-size
diff is explicitly defined as a defect.
microsoft/skills/review/al-{security,performance,privacy,style,
upgrade,ui}-review.md
- Each leaf skill now states that when an unambiguous .good.al
companion exists, findings[].suggested-code should carry the
literal replacement for the source lines. Closes the
one-click-suggestion gap created when BCQ#19 only updated
al-code-review.
microsoft/knowledge/security/case-must-handle-unknown-enum-values.{md,
bad.al,
good.al}
- New article: case over a security-sensitive enum (Authentication
Type, Authorization Mode, Identity Provider, Permission Scope,
Encryption Algorithm) MUST have an else arm. Without it, an unknown
enum value silently falls through and the security context never
initialises. The bad sample is lifted from the SharePoint Graph
helper that triggered the parity finding.
microsoft/knowledge/performance/instream-length-unreliable-for-bc-
streams.{md,bad,good}
- New article: InStream.Length returns 0 / partial for HTTP-response
streams and some file-API streams, breaking size-threshold branching
in upload code. Bad sample is the simple-vs-chunked Graph upload
pattern; good sample materialises into a Temp Blob first.
Companion change: microsoft/BCAppsBCQuality#28 extends the
orchestrator's bootstrap prompt with the same per-iteration execution
discipline and adds a CI warning when a >5-file PR returns zero agent
findings (regression signal).
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
