- adminConfig.ts: drop retired V1 latestAgent*/customSettings ghost fields,
add the 8 backend fields the interface was missing
- ops alerts: register the Sla category (BreachNotification/ConsecutiveFailures/
EvaluationCompleted) + OrphanEventsCleaned so operators can route them
- analyze rules: expose app_install_duration in the builder SOURCES;
fix stale XML docs (event_data_array, count_per_group_gte/in/not_in)
- UploadIntervalSeconds: collapse 5 diverged defaults (10 vs 30) onto
Constants.DefaultUploadIntervalSeconds = 10 (the served value)
- combine-rules workflow: commit ALL three combine.js outputs and include
rules/guardrails.json in the path filters
- api.ts apps sessions builders: move trailing optional strings into an
options object (adjacent optional strings swallowed a forgotten tenantId)
- SummaryDialog: canonical phase display names ("Apps (Device)")
- mcp-server.bicep: fix pre-EU-cutover hostname in deploy docs
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
withToolTelemetry now receives the tool args and inspects the RESULT: handlers
never throw (toolError returns isError:true), so the previous isError flag was
effectively always false. Each MCP_TOOL_LOGGING line now carries soft-error
status, resultChars + overCap (vs. the anthropic/maxResultSizeChars hint),
a size-bounded args summary and the caller scope — the only telemetry that
covers backend-free tools (search_docs, validate_rule, get_resource).
New signals: search_zero_hit on the three search tools (unmet-demand signal)
and tool_call_rejected for JSON-RPC-level Zod/unknown-tool rejections, sniffed
at the /mcp route since the SDK answers those before any handler runs.
Bicep default toolLoggingEnabled=true (desired state; live flag via
az containerapp update). Docs: docs/mcp/tool-telemetry.md with KQL examples.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
True parallel operation, no forced re-consent: existing tenants keep signing
in via the legacy app (1a400946), new tenants land on the C4A8 app (886ab5e2).
Model "default legacy, funnel primary, learn in the background":
- Web: am_auth_app flag -> NEXT_PUBLIC_ENTRA_DEFAULT_APP -> primary; get-started
CTA hands over with ?authapp=primary; auth/me homedApp updates the flag so an
operator tenant flip takes effect on each user's NEXT login; AADSTS90094/65001
one-shot cross-app retry, AADSTS65004 -> failed screen with previous-app link;
am_login_attempt pins redirect returns to the app that started them.
- Backend: TenantConfiguration.HomedAppClientId (null = legacy, GA-only flip via
PUT config) + LastAuthClientId/Since observability; EntraAppRegistry resolves
the acting app per tenant (no-op until the legacy config pair is set); Graph
client-credentials, admin-consent URLs and the surfaced client id follow the
homed app (app-scoped cache keys); JwtBearer [Authorize] pipeline now shares
the middleware audience builders (was single-audience - would 401 legacy
tokens after the swap); middleware trusts EntraId:LegacyClientId implicitly.
- well-known association file now lists both app ids (publisher domain);
deploy-web passes NEXT_PUBLIC_ENTRA_LEGACY_CLIENT_ID / _DEFAULT_APP;
mcp-server.bicep default client id -> C4A8 app.
Backend xUnit 3730/3730, vitest 625/625 (13 new), tsc/ESLint clean, next build ok.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The boot marks answered the question on the first production cold start, and the
answer overturns the reasoning behind an infrastructure change made earlier today.
+244ms node started (startup + module loading)
+431ms corpora read from disk (+187ms)
+491ms index read, validated, hydrated (+60ms for 3.12 MB)
+504ms listening
+677ms query embedder warm (background)
Against a 31.5s cold start, the application accounts for half a second. The other
~98% is Container Apps activation: KEDA reacting, pod scheduling, mounting the
236 MB image, starting the container. The container also boots faster than a
development laptop (504ms vs 1273ms), so nothing here is CPU-starved.
Consequences recorded rather than quietly dropped:
- Raising the container to 0.5 vCPU was justified by the embedding model load on
the cold-start path. Prebaked, that load is 173ms and runs in the background
where only the first search could wait on it. The justification does not survive
measurement. The setting stays — it plausibly helps concurrent requests, and at
scale-to-zero the cost difference is negligible — but the Bicep comment now says
what is true instead of what was assumed, so nobody re-derives the wrong reason.
- Index size is irrelevant to startup (60ms for 3.12 MB), so the corpus can grow
freely, and the embedding rounding earns its keep on file size alone.
- The only lever that would actually remove the cold start is minReplicas: 1, at
roughly 7x the monthly free consumption grant.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The MCP server could answer telemetry questions ("why did this session fail")
but not product ones ("how do I deploy the agent", "where is my data stored").
Those answers already exist in the autopilotmonitor-docs bundle; search_docs
makes them semantically searchable.
Deliberately a separate index from search_knowledge: rules and prose answer
different questions, and sharing one topK would dilute both. Registered for
every role — published documentation carries no tenant data — and skipped
entirely when no corpus was baked in, so a doc-less build advertises no
broken tool.
Corpus handling:
- Chunked at h2/h3 and <details>/<summary>, each chunk prefixed with a
"Page > Section > Subsection" breadcrumb so a mid-page hit is self-describing.
- Newlines are normalized before any parsing. This is a correctness
precondition, not cosmetics: the bundle ships CRLF and JS `.` does not match
\r, so /^(#{2,3})\s+(.*)$/ matched zero headings — silently, degrading every
page to unlabelled paragraph splits.
- Two size exceptions: tables are never split (a split table leaves `| --- |`
rows with no header), and unbroken changelog lists split at line level (left
whole, their tails fall outside the model window and become unsearchable).
- Short sections are kept — a one-line answer is often the best hit, and the
breadcrumb supplies the context a short body lacks.
Build and delivery:
- Docs are embedded at image build time into an optional third
PrecomputedSection. Optional so a checkout without the docs repo does not
invalidate the rules and event-type vectors; the reverse (server has docs,
file does not) is staleness and is rejected.
- The deploy workflow checks the public docs repo into the build context and
passes its SHA as DOCS_COMMIT, which /health reports alongside the chunk
count — editing the docs does not update a running server, so staleness is
made checkable rather than memorable.
- Embeddings are rounded to 6 decimals on serialize: 55% smaller index (2.63
vs 5.88 MB) for a ~1e-5 norm error against a 1e-3 tolerance. indexPrecomputed
now asserts unit norm, since the hydrate path never checked it.
Infra: the Bicep template was two changes behind the live deployment (EU
cutover and ACR hardening, both applied directly in Azure). Reconciled against
the running resources — managed-identity image pull replaces the admin
credentials and the acr-password secret — and infra/ is no longer gitignored so
it stops drifting. Container raised to 0.5 vCPU / 1.0 GiB for the cold-start
query-embedder load. The template does not model the mcp.autopilotmonitor.com
custom domain, so a full deployment would remove it; the header warns about it.
Verified: 428 tests pass; 45 pages produce 324 chunks; sample queries hit the
right page top-1/2; all 8 derived URLs return 200 live; the precompute output
is accepted by the boot validator and a mutated corpus is rejected.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Track MCP tool invocations in App Insights and UserUsageLog:
- Add ClientSource + McpToolName custom dimensions to RequestTelemetry
- Propagate tool name via X-MCP-Tool-Name header from MCP server
- Wrap all 26 tool handlers with withToolTelemetry for context propagation
- Add MCP_TOOL_LOGGING env var (default false) for optional stderr logging
- Add toolLoggingEnabled param to Bicep template for persistence
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Oliver Kieselbach