Addresses ADO bug 651092. Upgrade and feature data update code must run in the
context of the company being upgraded; ChangeCompany leaves triggers, events and
upgrade tags in the calling company and races the target company's own upgrade.
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
* 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 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
* 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>
* 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>
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>
* 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>
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>
The knowledge corpus now covers performance, security, privacy, upgrade,
style, and UI. Previously only two leaf reviewer skills existed
(al-performance-review, al-security-review), so four of the six domains
had knowledge with no skill sourcing from them. A community reader
landing in privacy/, upgrade/, style/, or ui/ would see articles with
no apparent consumer.
Three changes:
1. Move existing review skills into `microsoft/skills/review/`. The
`review/` subfolder groups all review-kind skills together and leaves
room for future non-review action skills at the `microsoft/skills/`
level. Updates references in README.md, agent-consumption.md, and
skills/entry.md to the new paths.
2. Add four new leaf reviewer skills — al-privacy-review,
al-upgrade-review, al-style-review, al-ui-review — each following
the same DO template as al-performance-review/al-security-review but
sourcing from the corresponding knowledge domain. al-upgrade-review
and al-ui-review return `not-applicable` when the diff contains no
upgrade surface or no page files, respectively.
3. Update al-code-review to compose all six leaf skills and retarget
the dangling references in every populated JSON example
(`use-setloadfields.md`, `no-plaintext-secrets-in-telemetry.md`,
`avoid-implicit-commit.md` — none of which exist in the corpus) to
real knowledge files: `call-setloadfields-before-filters.md`,
`use-secrettext-for-credentials.md`, `never-hardcode-secrets-in-al.md`.
Validator passes with 0 errors / 0 warnings.
