New follow-up section, distinct from the 2026-08-03 "ruled out" static
verification (Aktiv/Standard confirmed on, unchanged). This is about the
save/toggle *action* on CURABIS_DEV's MCP Server Configuration page, not
its resting state - not previously tested.
Observed 2026-08-07 (MID): Internal_CompanyNotFound recurred. VS Code
restart + retry failed (consistent with the already-falsified restart
theory). Toggling the Standard field on CURABIS_DEV and saving, then
retrying, worked immediately. MID reports having seen this same pattern -
restart-retry fails, config-touch-retry succeeds - on prior occasions.
Framed explicitly as a candidate, not a confirmed fix: n>=2 informal
observations, toggle direction untested (MID's own read is that direction
is probably irrelevant, pointing at the save/republish action busting a
server-side cache rather than at the field's value), and no baseline
established against the error's already-documented intermittency. Does
not override the Microsoft-support-escalation guidance - if anything it's
supporting evidence for that escalation, since a CURABIS-side config touch
masking a BC-side symptom points at BC's MCP session/cache layer.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
The 2026-08-03 follow-up's "restart Claude Code" step was falsified same
day by a full machine reboot that left Internal_CompanyNotFound unchanged.
Records the two theories ruled out with evidence (stale bridge process;
MCP config/company misconfiguration, both screenshot-verified) and states
plainly that this is a client-unfixable, likely BC/SaaS-side condition
requiring Microsoft support escalation.
Internal_CompanyNotFound recurred 2026-08-03 on two machines with the
company header already matching Navn correctly, ruling out the original
header-mismatch cause. Failure was intermittent and appeared to clear after
restarting Claude Code, suggesting a separate, still-unconfirmed session/
bridge staleness issue. Adds a follow-up section with next steps so future
sessions don't re-verify an already-correct header a third time.
Live incident i aften: businesscentral MCP fejlede med et generisk
30-sekunders "connection timed out", ingen brugbar fejl. To reelle, adskilte
fejl fundet ved at teste direkte mod BC's endpoint:
1. ~/.bc-mcp.config.json havde "company": "CURABIS ApS" (Vist navn), men BC's
faktiske Navn-felt er "Curabis ApS". BC svarede korrekt og hurtigt (400,
under 200ms) - problemet var aldrig BC.
2. bc-mcp-bridge.js svaelgede det svar stille: en fejl-krop formateret som
almindelig JSON, men markeret content-type text/event-stream, blev sendt
til parseSSE() som kun leder efter "data:"-linjer - fandt ingen, returnerede
en tom liste. Broen skrev derfor INGENTING, hverken stdout eller stderr, og
Claude Code ventede blot sin egen 30-sekunders timeout ud.
Rettet:
- forward() tjekker nu !r.ok FOER content-type-forgrening, ubetinget - en
fejlrespons naar aldrig parseSSE, uanset hvad serveren paastaar om sin
egen content-type. Testet direkte mod det reproducerede scenarie: fejlen
vises nu med det samme (5s test-vindue, ikke 30s timeout), med det fulde
BC-fejlsvar synligt i baade stdout (JSON-RPC error) og stderr.
- bc-mcp.config.template.json matchede slet ikke broens faktiske felter
(tenantId/baseUrl vs. broens tenant/company/configurationName) - enhver ny
udvikler der udfyldte skabelonen efter dens egne feltnavne ville faa en
config der intet virkede med. Rettet til de rigtige feltnavne, plus en
eksplicit advarsel om Navn vs. Vist navn i company-feltet.
- Mode A's opsaetningsbesked (Step 3b) opdateret til at naevne alle
placeholder-felter, ikke kun secret'en.
- To nye BCQuality-videnfiler dokumenterer begge fejl til fremtidig
fejlsoegning.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- bc-mcp.agent.md-templaten fik en manglende "preload de tre bc_actions_*
værktøjer via ToolSearch select:"-sektion, som ellers kun levede i
bc-mcp-tools-must-be-preloaded.md og derfor aldrig blev håndhævet.
- Rettet forkert antaget navnemønster (ListUpdate<entity>_PAG<id> ->
Modify_<Entity>_PAG<id>, bekræftet empirisk via bc_actions_search).
Ny regel bc-mcp-naming-convention-must-be-reverified.md kræver at
navnekonventioner altid markeres som "forvent, reverificér" fremover.
- francis.agent.md + immanuel.agent.md: hand-off fra Francis til Immanuel
er nu eksplicit automatisk. Michael er ikke et mellemstop i pipelinen -
han involveres først når PR'en er klar til merge.
Observeret 2026-07-04: en session brugte ToolSearch med keyword-søgning
i stedet for select: (fandt irrelevante værktøjer), ledte derefter efter
et ListUpdate-værktøj der ikke findes, og spurgte om lov til at fortsætte
til Immanuel midt i pipelinen.
Normalisering af alle 39 custom knowledge-filer til READ-kontraktens
skema (validate_frontmatter.py + Test-KnowledgeIndex.ps1 begge groenne):
- R01/R02: 28 filer manglede frontmatter eller brugte aeldre skemaer
(title/category/severity/rule-id m.fl.) - alle har nu praecis de 6
kraevede noegler; keywords haandskrevet pr. fil da de driver
worklist-selektionen i INDEX/knowledge-index
- R09: manglende Description-sektion - regel-agtige foersteoverskrifter
(Core Rule/Rule/Regel/Core Principle) omdoebt, eller sektion indsat
efter titlen hvor intro-tekst fandtes
- R10: fenced code blocks konverteret til 4-space indrykkede blokke
i alle filer (indhold uaendret)
- R11: 4 filer over 100 linjer fortaettet redaktionelt uden semantisk
tab (ai-eval-scores 143->100, git-lifecycle 121->97,
permission-sets 113->99, test-feature-scenario-tags 105->91)
- R05: AL0197->al0197, add_repo->add-repo; keyword-lister trimmet
til maks 10
Ingen regler er fjernet eller aendret i betydning - kun form.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- custom/agents/smiley.agent.md: ny altid-aktiv session watchdog (George Smiley).
Observerer hele sessionen, aktiverer Columbo/al-triage/Francis/bc-mcp/weber
diskret uden at annoncere sig selv. Stop-gate forhindrer kode uden afklaret krav.
- custom/knowledge/mcp/bc-mcp-tools-must-be-preloaded.md: ny MCP-regel godkendt
af Immanuel (alle 4 Categorical Imperative tests bestået). BC MCP tool-schemas
skal pre-loades via ToolSearch ved agent-invokering for at undgå mid-task latency.
- custom/setup/curabis-standard.agent.md: Smiley tilføjet til artifacts-liste,
Smiley-sektion tilføjet til CLAUDE.md-template, Mode B visibility-check opdateret
med Smiley special-case (always-active, ikke on-demand).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- All 7 existing Tier 1/2 knowledge files now include a BCApps Reference
section with concrete source links and observed patterns
- New: bcpt-scenarios-must-be-app-specific — PerformanceTest apps must
include app-domain BCPT scenarios, not only Microsoft generic samples
- New: permission-sets-must-follow-least-privilege — View/Edit/Admin
hierarchy with IncludedPermissionSets, mirroring BCApps BusFound pattern
- api-page-key-fields-must-be-editable-on-insert clarified: SystemId as
ODataKeyField + Editable=false is valid (auto-generated); rule applies
to consumer-provided key fields only
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
When a developer asks for open tasks, only return tasks from the project(s)
linked to the current git repository. Flag it if no project is linked.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Rules derived from BC MCP API page development experience:
- api-page-flowfields-must-be-calcfields: FlowFields return empty on API
pages unless explicitly CalcFields'd in OnAfterGetRecord
- stored-derived-fields-must-not-be-exposed-directly: Stored fields updated
only via OnValidate triggers can be stale; recalculate live in OnAfterGetRecord
- api-page-key-fields-must-be-editable-on-insert: ODataKeyFields with
Editable=false are rejected as unknown properties on POST
- api-page-least-privilege-write-access: Create dedicated minimal pages per
write concern rather than widening general-purpose pages
- agent-must-not-write-business-process-status: Agents must only write
developer-tracking fields; business status fields affect invoicing/time registration
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
