Copilot round 11. Two of the three are the enum-strip logic this PR added
misbehaving on degenerate input; the third is one more keyword for the
fail-closed rule.
1. An empty `enum` permits nothing at all, but the strip reported "unchanged"
(nothing was removed) and the collapse built a Select with no options — a
required field then had no interaction able to supply a value. It now
reaches the same conclusion as `[null]`: no selectable member, so decline.
The outcome is renamed `unselectable`, since "only-null" no longer describes
both routes to it.
2. Filtering `null` out of `enum` shortens it, which could make an ALREADY
mismatched `enumNames` come out the same length — so `enum: [null, "b"]`
with `enumNames: ["None"]` started labelling `b` as "None", turning labels
both renderers had correctly ignored into a confident mislabel. A list that
was not parallel before filtering is now dropped rather than kept.
3. `$ref` joins the opaque set. It is never resolved here and applies alongside
its siblings, so `{ type: "string", $ref: "#/$defs/intOnly" }` can be
unsatisfiable. The wrapper path already declined on it by virtue of the
annotation allowlist; this extends the same rule to branches, the
`type: [T, "null"]` path, and `admitsNull`.
No round 12 was requested: the review loop was stopped at the user's direction.
Signed-off-by: cliffhall <cliff@futurescale.com>
Copilot round 10: one finding, the last position of the rule the previous two
rounds established. A *non-null* branch can carry its own `anyOf`, and the
hoist drops it — the branch's `anyOf` overwrites the wrapper's in the spread
and is then cleared, so `{ anyOf: [{ type: "string", anyOf: [{ const: "a" }] },
{ type: "null" }] }` widened into an unconstrained nullable string.
Rather than add a fourth inline condition, the four sites that ask "does this
schema compose something I cannot evaluate?" now share one predicate,
`hasUnevaluatedComposition` (an opaque applicator, or a nested `anyOf`):
- the surviving branch in the `anyOf` collapse (this round's finding),
- the null branch in `admitsNull`,
- the `type: [T, "null"]` collapse path,
- and, via `hasOpaqueApplicator`, the top of `admitsNull`.
Each of those was missed independently across rounds 8-10 for the same reason:
the guard existed but was spelled out inline at each site and drifted. Sharing
the predicate is the part that stops a fifth site from repeating it.
Signed-off-by: cliffhall <cliff@futurescale.com>
Copilot round 9: four findings, all of them places where round 8's fail-closed
inversion was the right idea applied incompletely. The rule was only enforced
at the positions I happened to be editing; it now holds everywhere a schema is
inspected.
1. `admitsNull` returned early on an explicit `type`, ignoring a sibling
`anyOf` — but the two are conjunctive, so `{ type: ["string", "null"],
anyOf: [{ type: "string" }] }` admits no null at all. A sibling union now
withholds the claim.
2. A null-typed branch could be unsatisfiable via its own nested `anyOf`
(`{ type: "null", anyOf: [{ type: "string" }] }`). The branch check tested
`not`/`allOf`/`oneOf` but not `anyOf`; it now treats a nested union as
equally opaque.
3. The `type: [T, "null"]` collapse path had no applicator guard at all —
`collapsed` clears `anyOf` unconditionally and the renderers ignore the
rest, so `{ type: ["string", "null"], anyOf: [{ const: "a" }] }` was widened
into an unconstrained string field. That path now declines the same way the
`anyOf` path does.
4. The `admitsNull` docstring still advertised `oneOf` support that round 8
deliberately removed. Rewritten to state what is recognized, what is
declined and why, and the asymmetry that settles the direction.
The three code fixes share one helper (`hasOpaqueApplicator`) rather than
repeating the condition, so the next position that needs it cannot drift.
Signed-off-by: cliffhall <cliff@futurescale.com>
Copilot round 8 opened the same conjunctive-semantics seam a third time, so
this stops patching cases and inverts the defaults instead. Both guards now
fail CLOSED: anything this module cannot evaluate sends the field to the JSON
editor rather than to a widget built from a partial reading.
1. The wrapper-conflict check enumerated the *validation* keywords and declined
when two of them disagreed — which meant any keyword nobody listed
(`oneOf`, `allOf`, `not`, `$ref`, a future vocabulary) was silently treated
as safe to drop. That whitelist fails open, and open means rendering a
widget for a constraint that is not the schema's. It is replaced by an
allowlist of *annotation* keywords: the collapse declines whenever the
wrapper carries anything beyond annotations and the union itself. Stricter
than the old equality test — a wrapper restating its branch's `type` now
declines too — which costs a dropdown on a rare redundant shape and buys a
rule with no gap in it.
2. `admitsNull` returned true for shapes it had not actually evaluated:
`not: { type: "null" }` rules null out, `allOf` can add a member that does,
`oneOf` requires *exactly one* branch to match (so a null branch does not
by itself mean null validates), and a branch like `{ type: "null",
const: "x" }` is unsatisfiable. All now answer false. Under-claiming
nullability costs a clear button; over-claiming lets the form emit a value
the schema rejects, so the asymmetry decides it.
Note the third finding — draft validity never reaching the submit controls —
is NOT fixed here, and it is worse than I described last round: `ToolDetailPanel`
gates Execute on `isExecuting` alone and never calls `hasMissingRequiredFields`,
so my earlier claim that required fields were already covered was wrong for the
Tools tab. Corrected on #2020, which is where the fix belongs.
Signed-off-by: cliffhall <cliff@futurescale.com>
Copilot round 7: both findings are the same principle applied one level
further — JSON Schema siblings are conjunctive, and this code was treating
them as alternatives.
1. The hoist is a spread, so a branch keyword *replaced* the wrapper's. That
is not a conjunction: a wrapper `enum: ["a"]` around a branch
`enum: ["a", "b"]` means `"a"`, but the spread produced `["a", "b"]` and
the dropdown would have offered — and submitted — a `"b"` the schema
rejects. `type`, bounds, and the object keywords fail the same way.
The collapse now declines when wrapper and branch carry different values
for the same validation keyword, and the field renders through the JSON
editor with its schema intact. Intersecting them properly is a much larger
surface, and a subtly wrong intersection would be worse than none.
Identical values are not a conflict, so the ordinary redundant-`type`
shape still collapses; metadata (`title`, `description`, `default`,
`enumNames`) never conflicts, since nothing validates against it.
2. `admitsNull` let a `{ type: "null" }` branch outvote an explicit
non-null top-level `type`. `{ type: "string", anyOf: [..., { type:
"null" }] }` rejects null — the value must satisfy the type *and* the
union — so an explicit `type` now decides instead of falling through to
the branch scan.
Signed-off-by: cliffhall <cliff@futurescale.com>
Copilot round 6: no visible comments, three suppressed. All valid.
1. JSON Schema keywords at one level are conjunctive, so a syntactic null does
not by itself mean the schema accepts null. `{ type: ["string", "null"],
enum: ["envio"] }` names "null" and still rejects it — yet the collapse
marked it `nullable: true`, giving the field a clear button that emits a
value the schema forbids, and `admitsNull` let required-field gating accept
it. Both now consult `nullExcludedBySiblings`.
The distinction that makes this safe: a *branch's* `enum` is not a sibling.
In `anyOf: [{ type: "string", enum: [...] }, { type: "null" }]` — the #1928
shape — the enum constrains that branch alone and the union still permits
null, so `nullable` is read off the ORIGINAL schema rather than the hoisted
merge. Reading the merge would have called the headline case non-nullable.
Flattening is unaffected either way; only the nullability claim is withheld.
2. The collapse newly routed a nullable array of numeric item enums into the
string-only `MultiSelect` path, which would submit `["1"]` for `[1]`. Gated
on `isStringEnum`, matching `toConstOptions`; `isStringEnum` is now a type
predicate so the narrowing is real rather than asserted.
3. Invalid JSON and an empty field both report `undefined`, so an optional
complex argument could be dropped from the submission while invalid text sat
visible in the box. The field now says so via `error`. Note a *required*
field was already gated — its value is `undefined`, which
`hasMissingRequiredFields` treats as missing — so this is specifically the
optional case. Disabling Execute/Open/Submit on an invalid optional draft
needs a validity channel out of `SchemaForm` into all four call sites, which
is wider than this fix; filed separately.
Signed-off-by: cliffhall <cliff@futurescale.com>
Copilot round 5: one inline comment, two suppressed. All three valid, and two
were defects from round 4's own fix.
1. Stripping the `null` sentinel from an `enum` left the parallel `enumNames`
untouched. Both renderers discard labels outright when the two lengths
disagree, so `{ enum: ["a", null], enumNames: ["Alpha", "None"] }` lost the
`Alpha` label entirely — a worse outcome than the sentinel it was fixing.
`enumNames` is now filtered by the same indices, and only when it was
positionally parallel to begin with (a mismatched list is already ignored
by both renderers, so re-indexing it would invent an alignment the server
never declared).
2. `enum: [null]` became `enum: undefined`, which widened a schema permitting
*only* `null` into a plain string field accepting arbitrary text — the form
would then invite values the schema forbids. Trading a cosmetic problem for
a correctness one, which was the wrong call. The collapse now declines
entirely for that case and the field renders through the JSON editor.
3. That JSON editor was still carrying #1928's original mechanism: it stored
unparseable text back as the *value*, which the next render
re-`JSON.stringify`d, so typing `[` gave `"["` then `"\"[\""`. Routing
nullable fields to real widgets removed the common way of landing there but
never fixed the editor — and #2007's fix deliberately sends object unions to
it, so a fallback nobody can type into is not a fallback. `SchemaJsonField`
now holds the draft text locally (the split `SchemaNumberInput` already
uses) and reports parsed JSON, or `undefined` while the text is mid-edit —
an inspector must not report a value it cannot send. Keyed by `resetKey`
like the number field, since it now holds state.
Also replaces an `as unknown as string[]` in the round-4 test, which violated
the repo's TypeScript rules and papered over `InspectorFormSchema.enum` being
unable to model a valid `["a", null]`. The fixture is wire data, so it now goes
through `toFormSchema` — the same wire→form narrowing boundary every production
call site uses.
Signed-off-by: cliffhall <cliff@futurescale.com>
Copilot round 4: no new visible comments, two in the suppressed block. Both
valid.
1. The `type: [T, "null"]` encoding keeps its keywords at the top level, so a
nullable enum written that way carries the null *inside* the list:
`{ type: ["string", "null"], enum: ["envio", "recebimento", null] }`. The
collapse left it there, which broke both renderers in different ways — the
web dispatcher handed `null` to Mantine as option data, and the TUI's
all-strings check rejected the whole enum and fell back to a plain text
field. Neither is the dropdown the schema asks for.
The collapse now strips a `null` member whenever it flattens, since that
fact has already moved onto `nullable`. An enum of nothing but `null`
drops out entirely: it offers no value a dropdown could show, so the plain
widget serves the field better than an empty select. Covered in core and
end-to-end in both dispatchers.
2. The new integration test claimed in its own header to pin the registry and
config wiring, then called `createNullableFieldsTool()` directly — so a
misspelt preset case or a config naming a dead preset would have left it
green. A fair "this does not test what it says" catch. It now resolves the
checked-in `nullable-fields-http.json` through `loadConfig` →
`resolveConfig`, matching `duplicate-tool-names.test.ts`, and asserts the
resolved tool names before booting the server.
Signed-off-by: cliffhall <cliff@futurescale.com>
Three findings (one inline, two in the suppressed block), all valid.
1. `toConstOptions` still stringified every non-null `const`, so
`items: { anyOf: [{ const: 1 }, { const: 2 }] }` submitted `["1"]` where
the schema says `[1]`. Same wrong-type-on-the-wire problem that keeps a
numeric `enum` off the select path, so it gets the same answer: only a
string `const` is selectable, anything else falls to the JSON editor
where the value keeps its type.
2. `hasMissingRequiredFields` derived null admission from the *renderer's*
collapse, which is narrower on purpose — it only flattens a two-member
union. So `anyOf: [string, number, null]` renders through the JSON
fallback (where `null` is typeable) yet was still marked missing,
disabling submit on a value the schema accepts. Null admission is a
validity question, not a rendering one, so it is now its own predicate:
`admitsNull` in core, recognizing `nullable`, `type: "null"`,
`type: [..., "null"]`, and a null branch anywhere in an `anyOf`/`oneOf`
of any size.
3. Nothing exercised the `record_shipment` preset — the web and TUI tests
build the `anyOf` shape by hand, which verifies the renderers but
*assumes* the premise the whole fix rests on: that Zod's `.nullish()`
emits `anyOf: [<branch>, { type: "null" }]` with the enum on the branch.
A Zod output change or a registry typo would leave every unit test green
while the documented reproduction server quietly stopped reproducing.
Added an integration test that boots the preset over HTTP, asserts the
wire shape, and runs it back through the collapse — following the
`duplicate-tool-names.test.ts` precedent, which exists for the same
reason (#1957).
Signed-off-by: cliffhall <cliff@futurescale.com>
Closes#2007.
Two things, both surfaced while answering "does #1928's PR also fix #2007?".
**#2007, and why it belongs in this PR.** `z.array(z.union([z.object(…),
z.object(…)]))` gives an `items.anyOf` whose branches carry no top-level
`const`, so every MultiSelect option was `String(item.const ?? "")` — the
empty string, twice. Mantine *throws* on duplicate option values, greying
out the whole tool panel.
That is a pre-existing bug, but this branch makes it reachable from a new
direction: a *nullable* array of object unions previously had no top-level
`type` and fell to the JSON fallback, and now collapses to `type: "array"`
with `items.anyOf` — straight into the crash. Shipping the collapse without
this fix would widen an existing crash, so the two go together. Both shapes
are covered by tests.
`toConstOptions` now returns `null` unless every branch yields a distinct,
non-empty value, and the field falls through to the JSON editor — which is
the honest widget for a union of object shapes anyway. Applied to the
`string`/`oneOf` path as well, which had the identical `?? ""` and the same
duplicate-throw waiting on it.
**Copilot round 2.** Round 1's fix kept "an explicit `type` is
authoritative", so `{ type: "number", enum: [1, 2] }` still collapses with
its enum hoisted. The TUI's dispatcher tests `property.enum` *before* the
type switch, and `toSelectOptions` stringifies, so that reached a select
that submits `"1"` for `1`. The select path is now gated on `isStringEnum`
(exported from core for this), and a typed non-string enum falls through to
its typed field: the enum constraint is lost, the value's type is not,
which is the safer of the two losses. Pre-existing for a plain numeric
enum; the collapse just made the nullable form reachable too.
Signed-off-by: cliffhall <cliff@futurescale.com>
Four findings, all valid:
1. Returning `T` was unsound. The collapse genuinely changes two fields —
`type` stops being an array, `anyOf` becomes `undefined` — so a caller
whose `T` typed either that way could keep treating it so afterwards.
The result is now `T | NormalizedNullableUnion<T>`, which states exactly
that: `Omit<T, "type" | "anyOf">` plus a `RenderableType` `type`, a
cleared `anyOf`, and `nullable`. The one assertion left is isolated in a
`collapsed()` helper, needed only because `Omit` stays deferred while `T`
is open.
2. A typeless `enum` does not imply strings. JSON Schema allows
`enum: [1, 2]`, and inferring `"string"` for it would hand numbers to a
`Select` declared `string[]`, and make the TUI submit `"1"` for `1`. Now
only an all-string enum earns the inference; anything else stays on the
JSON fallback. An explicit `type` is still authoritative.
3. `hasMissingRequiredFields` counted every null as missing, so clearing a
*required* nullable enum — newly possible via the clear button — would
disable submit on a value the schema permits. `required` constrains
presence, not content, so null now counts as present exactly when the
field's schema admits it.
4. `collectSchemaDefaults` read the raw union, so a default nested inside a
nullable object's branch was displayed by the form but never seeded into
the submitted values. It normalizes each property first, like the
renderer does.
Signed-off-by: cliffhall <cliff@futurescale.com>
Closes#2015, folded into #1928 rather than left as a follow-up.
The TUI's `schemaToForm` has the same defect the web `SchemaForm` had: its
local `JsonSchemaProperty` declares only `type?: string` — no `anyOf`, no
array-valued `type` — so a `.nullish()` argument has no top-level `type` or
`enum` for the dispatcher to read and falls to the `switch` default, losing
its select. Milder than the web bug (a plain text field, not a corrupting
JSON textarea), but the same class.
Fixing it in a second place is the argument for not having the logic in a
first place. So the collapse moves to `core/json/nullableUnion.ts` as
`normalizeNullableUnion`, generic over a minimal `NullableUnionSchema`
shape — the least a caller must expose to be *recognized* as a nullable
union — so neither client has to adopt the other's schema type. Both form
builders now share one copy and cannot drift on which schemas they render.
- `core/json/nullableUnion.ts` — the shared collapse, plus tests at
`clients/web/src/test/core/nullableUnion.test.ts` (the web suite is what
gates `core/`).
- `clients/web`: `schemaUtils.normalizeUnionType` is gone; `SchemaForm` and
`resolveRefsInMessage` call the core function directly.
- `clients/tui`: `schemaToForm` normalizes each property before dispatch,
and `JsonSchemaProperty` grows the `anyOf` / array-`type` fields the
encoding uses.
Verified by driving the built TUI under a pty against the
`nullable-fields-http.json` showcase server. Before, every argument of
`record_shipment` rendered as a plain text field; after, `direction` is a
select ("No value"), `quantity` an integer, `express` a boolean
("[Not set]").
Signed-off-by: cliffhall <cliff@futurescale.com>
* fix(core): mirror SEP-2243 x-mcp-header args to Mcp-Param-* on tools/call (#1846)
A strict modern (2026-07-28) HTTP server (e.g. the GitHub MCP Server)
rejects a tools/call whose argument carries an `x-mcp-header` annotation
when the matching `Mcp-Param-*` request header is missing (-32020
"header mismatch"). The Inspector never sent that header.
The SDK only mirrors inside `client.callTool()` (and skips it entirely in
a browser environment), but the Inspector routes tools/call through
`client.request()` for manual MRTR driving (#1704), so the SDK never
mirrors for us — on any transport. On top of that, the remote (web)
transport dropped per-request headers before they reached the backend's
upstream fetch.
- core/json/xMcpHeader.ts: port the SDK's non-public `buildMcpParamHeaders`
+ value encoding (Base64 sentinel for non-ASCII/whitespace/empty values)
and add `mcpParamHeadersForTool`.
- InspectorClient.attemptToolCall: on a modern connection, build the
headers from the tool's declarations + call arguments and attach them to
the tools/call request options. `Protocol.request` forwards `headers`
to the transport and preserves them across MRTR retry legs, so the
direct StreamableHTTP transport applies them. Fixes CLI/TUI.
- RemoteClientTransport.requestSend + /api/mcp/send + RemoteSendRequest:
forward per-send headers and apply them to the backend's upstream
transport.send. The browser can't set cross-origin headers, but the
Node backend can — where the Inspector's real request is issued. Fixes web.
Verified end-to-end against the live GitHub MCP Server (modern HTTP).
Closes#1846
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 36dbeb09-12b0-4c19-af36-2573772a7dbd
* review: harden backend header allowlist, fix breadcrumbs, trim comments
Address Copilot review on #1847:
- server.ts: restrict client-supplied per-send headers to the `Mcp-Param-`
prefix (string values only) via `mcpParamHeadersOnly` before applying them
upstream, so the per-send channel can't inject arbitrary headers (e.g.
Authorization). `settings.headers` remains the channel for configured
upstream headers. Covered by new unit tests.
- Fix stale `#1810` breadcrumbs → `#1846` in the two new tests.
- Trim the verbose mirroring comments in inspectorClient/types/remote transport.
- Drop the redundant base64-on-the-wire integration test (encoding is unit-
tested; wire delivery is proven by the verbatim test), remove two unneeded
test casts, and cover the boolean `true` branch.
Not changed (declined with reason on the PR): buildMcpParamHeaders remains a
faithful port of the SDK's helper and does not re-validate values against the
declared JSON Schema type — arg types are enforced by schema validation on
both sides, and matching the SDK's conforming wire output is the module's goal.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 36dbeb09-12b0-4c19-af36-2573772a7dbd
* review: mirror Mcp-Param-* on the task-augmented tools/call too
Address the maintainer review on #1847:
- `callToolStream` (the "Run as task" path) built its own request options and
never mirrored, so a task-augmented `tools/call` on an annotated tool was
still rejected by a strict modern server with -32020. It now mirrors like the
plain path.
- Extract the two blocks both `tools/call` entry points had duplicated —
`convertStringToolArgs` (the string-arg coercion) and
`applyMirroredParamHeaders` (the SEP-2243 mirroring) — so the paths can't
drift again. That duplication is why the task path was missed.
- Regression test: `callToolStream` against the modern `get_weather` server
asserts the POST carries `Mcp-Param-City` (verified failing without the fix).
- README: the modern-network showcase claimed mirroring is skipped in the
browser so the web client gets -32020, and that CLI/TUI mirror. Both are now
wrong — the Inspector mirrors itself, on every client. AGENTS: note that
xMcpHeader.ts now also builds the wire headers.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UkhhCHryVp5H3dqEnhwZ7t
* docs: correct the stale "browser omits Mcp-Param-*" copy
Both statements predate this PR and are now the opposite of true, per the
wire capture on #1847 (proxy-observed upstream headers, web leg included).
- ToolDetailPanel: the mirrored-headers note claimed the browser omits
`Mcp-Param-*`. It now says the web client's headers are applied by the Node
backend that issues the upstream request.
- createRemoteFetch: the header comment claimed an `x-mcp-header`-annotated
tool is "uncallable from the web client against a strict modern server" —
the exact wrong conclusion to reach while debugging a -32020. It now records
that the Inspector builds the headers itself, and that they do NOT travel
this `/api/fetch` proxy path: they ride the transport's per-send `headers`
through `/api/mcp/send`.
Copy only — no test asserted the old note text (ToolDetailPanel.test.tsx
matches the section title only).
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UkhhCHryVp5H3dqEnhwZ7t
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: cliffhall <cliff@futurescale.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Copilot-Session: 36dbeb09-12b0-4c19-af36-2573772a7dbd
* core: refactor serverList.ts object↔Record casts into typed helper (#1690)
Remove the four pre-existing `as unknown as Record<string, unknown>` /
`as unknown as MCPServerConfig` casts in core/mcp/serverList.ts:
- stripInspectorFields: rewrite as clone + `delete` over INSPECTOR_FIELD_KEYS.
Every Inspector-extension key is optional on StoredMCPServer, so the result
is still (a subtype of) MCPServerConfig with no cast.
- oauth-strip in extractSecretsFromStored: `oauth` is optional, so a plain
`delete stripped.oauth` is legal — drop the cast.
- mcpConfigToServerEntries: route the one genuinely-needed widening through a
single documented `toRecord(value: object)` helper. Taking `object` makes the
single `as Record<string, unknown>` legal (no TS2352), so the double cast
disappears from the call site.
Net: zero `as unknown as` in serverList.ts; the one remaining structural cast
lives inside the audited toRecord helper. Behavior-neutral — existing coverage
(79 serverList tests) unchanged; full `npm run ci` passes.
Closes#1690
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5
* core+web+test-servers: eliminate/justify remaining `as unknown as` casts (#1690)
Codebase-wide follow-on to the serverList refactor: audit every `as unknown
as` double cast outside tests and either remove it or ensure it carries a
justifying comment (the review bar is "no *unjustified* double cast").
Removed (widened via a shared helper or narrowed to a single cast):
- Promote the serverList `toRecord(value: object)` widening helper to
core/json/jsonUtils.ts and reuse it at core/mcp/node/config.ts (normalize
loop), core/mcp/remote/node/server.ts (pino level dispatch), and
clients/web/src/App.tsx (window global lookup).
- inspectorClient.rawWireRequest: type the frame as `JSONRPCRequest` and
narrow only `params` with a single structural cast (the SDK's `_meta`-typed
params is what blocked direct assignment).
- toolOutputValidation: SDK `outputSchema` → `JsonSchemaType` is a single cast.
- test-server-fixtures: the optional `task` handle is reachable with a single
cast (target field is optional).
Justified in place (genuinely unavoidable — private SDK internals, partial
interface stubs, third-party/nominal bridges): the inspectorClient private-map
accesses, resourceContext + tokenAuthProvider partial `OAuthClientProvider`
stubs, the ext-apps peer bridge, modern/legacy `_requestHandlers` bypasses,
and the happy-dom `matchMedia` test mock.
Behavior-neutral. Full `npm run ci` passes (validate, ≥90 coverage gate,
smoke, Storybook).
Refs #1690
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5
* address @claude review nits: consistent cast justifications + drop reflow noise (#1690)
- test-servers/src/modern-tasks.ts: add an inline justification above the
`_requestHandlers` double cast, mirroring the sibling in
composable-test-server.ts (was leaning on the function JSDoc only).
- Annotate the partial-`AppBridge` mock double casts in the story fixtures
(AppsScreen ×2, AppRenderer, InspectorView) so no non-test-file double cast
is unjustified.
- inspectorClient.ts: revert unrelated Prettier reflow hunks (protocolVersion,
task-content array, timeout-reject wrap, reconnect guard) so the diff is the
single rawWireRequest cast change only.
Behavior-neutral (comment/format-only). `npm run ci` green apart from a known
flaky redaction test whose assertion collided with a random request id.
Refs #1690
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5
* actually revert the reflow noise this time (#1690)
The reflow reverts in cc187ea were silently undone by a `prettier --write` I
ran on the same file right after, so the four Prettier-only hunks from 6a3afa4a
were still in the diff (caught in re-review). Revert them for real now — and
without re-running Prettier on the file:
- core/mcp/inspectorClient.ts: restore the protocolVersion line, task-content
array, timeout-reject call, and reconnect guard to their origin/v2/main form,
so the file's diff is only the single rawWireRequest cast change.
- test-servers/src/modern-tasks.ts: restore the ModernTaskStatus union to its
one-line form (the leading-`|` reflow was also Prettier churn), leaving only
the new `_requestHandlers` justification comment.
Formatting-only; `npm run validate` green.
Refs #1690
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Tools: x-mcp-header annotation tooling + -32602 unknown-tool rendering (#1632)
Card 9/10 of the SDK-v2 + New Spec stack. Adds SEP-2243 `x-mcp-header`
tooling to the Tools tab and adjusts result rendering for SDK v2's
unknown-tool behavior, and bumps the SDK to 2.0.0-beta.5.
- **`core/json/xMcpHeader.ts`**: a faithful port of the SDK's (non-public)
`scanXMcpHeaderDeclarations` — validates every SEP-2243 constraint
(primitive types incl. `number`, RFC 9110 token, case-insensitive
uniqueness, statically-reachable `properties`-only chain) and derives the
mirrored `Mcp-Param-{Name}` params for a kept tool.
- **Excluded tools**: the SDK silently drops tools with invalid annotations
from `tools/list`. InspectorClient now re-lists the RAW (unfiltered) list
and scans it to recompute the excluded set with reasons — gated to the
modern non-stdio era (matching the SDK's gate), recomputed on every
aggregate refresh, surfaced via a new `excludedToolsChange` event +
`getExcludedTools()` and `useInspectorClient().excludedTools`. The Tools
sidebar lists them struck-through under an "Excluded (SEP-2243)" divider
with the reason on hover.
- **Mirrored args**: ToolDetailPanel shows a "Mirrored request headers"
section listing each arg → `Mcp-Param-{Name}` (with the browser-omits note).
- **-32602 rendering**: SDK v2 rejects an unknown-tool call with `-32602`
instead of an `isError` result, which previously rendered nothing. New
ToolCallErrorPanel renders a thrown tool-call error, with a targeted
"Unknown Tool" hint for `-32602`.
Adds unit + Storybook + integration coverage (a real modern server with an
invalid-header tool fixture) for every path. `npm run ci`-equivalent checks
green.
Closes#1632
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5
* test-servers: x-mcp-header modern showcase config + preset (#1632)
Register the `invalid_header_tool` fixture as a preset and add
`xmcpheader-modern-http.json` — a modern HTTP showcase serving echo, a
valid-header `get_weather`, and the invalid-header tool — so the Tools-tab
x-mcp-header tooling (mirrored headers, excluded-tools surface, -32602
rendering) can be exercised manually. Documented in the README alongside the
other per-SEP showcase configs. Smoke-tested end to end in the web client.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5
* docs: add #1632 proof screenshots to pr-screenshots
End-to-end web-client verification of the x-mcp-header Tools tooling against
the modern showcase server: excluded-tools surface + reason, mirrored-headers
section, and the -32602 unknown-tool error panel.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5
* Respond to review: disambiguate -32602, doc/search nits (#1632)
Addresses the review on PR #1735:
1. -32602 "Unknown Tool" mislabel: `-32602` is generic Invalid params, so a
known tool called with bad arguments hit the same code and rendered under
the definitive "Unknown Tool" heading. Replace `isUnknownToolError` with
`classifyToolCallError(code, message)` → "unknown-tool" only when the
message names it (not found / unknown tool / …), else "invalid-params"
(new "Invalid Parameters" heading + schema hint), else "generic".
2. Double pagination walk: expand the `listAllTools` comment to document that
the excluded-tools recompute is a deliberately un-cached second raw walk
(doubles list round-trips on modern non-stdio, runs even on a cache-served
aggregate) — accepted for a debugging tool, no-op on legacy/stdio.
3. Doc nit: `scanXMcpHeaderDeclarations` no longer claims to visit "$ref
targets" — reworded to note `$ref` is never followed (refs resolve into the
unreachable `$defs` body).
4. Search nit: the excluded-list filter now matches name AND title, matching
the main tools filter.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5
* Tighten unknown-tool matcher to be tool-scoped (#1632 re-review nit)
The re-review noted the -32602 disambiguation was symmetric: broad markers
("does not exist", "unrecognized") could inversely mislabel a genuine
invalid-params message (e.g. "property 'region' does not exist") as "Unknown
Tool". Scope the not-found/does-not-exist family to require the word "tool" in
the same clause (matching the SDK's "Tool <name> not found"); keep "unknown
tool" / "no such tool" as standalone unambiguous markers. Adds a
tool-less-"does not exist" test asserting it classifies as invalid-params.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5
* Add trigger_invalid_params showcase tool + Invalid Parameters screenshot (#1632)
Adds a `trigger_invalid_params` spec-error trigger to the modern showcase
server: the injector answers its `tools/call` with a real `-32602 Invalid
params` JSON-RPC error whose message does NOT name an unknown tool. This lets
the "Invalid Parameters" branch of the tool-call error panel (added in the
review response) be exercised live, distinct from the unknown-tool `-32602`.
- `SPEC_ERROR_TRIGGERS` gains the `trigger_invalid_params` entry (HTTP 200,
in-band -32602) + preset registration.
- Enable `injectSpecErrors` on `xmcpheader-modern-http.json` and add the tool.
- README + pr-screenshots README document it; adds the live "Invalid
Parameters" proof screenshot.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XNdjEPKLG637X8YmhDiEk5
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Migrate all three clients + core + test-servers from
@modelcontextprotocol/sdk@1.29 to SDK v2 (2.0.0-beta.4), keeping behavior
identical against legacy (2025-11-25) servers. Foundation for the SDK V2 +
New Spec stack.
Packages
- Split @modelcontextprotocol/sdk -> @modelcontextprotocol/client (Client,
transports, OAuth, error taxonomy, protocol types) + core (Zod schemas);
stdio -> client/stdio, Ajv -> client/validators/ajv. Test-servers ->
@modelcontextprotocol/server (+ server-legacy/sse). Deterministic import
rewrite (schemas -> core, everything else -> client); the codemod misroutes
client code to /server so it was not used for path routing.
- new Client(..., { versionNegotiation: { mode: 'legacy' } }) — nothing
2026-era goes on the wire.
Runtime (core/mcp/inspectorClient.ts)
- Error taxonomy: McpError -> ProtocolError, ErrorCode -> ProtocolErrorCode;
RequestTimeout -> SdkError/SdkErrorCode.
- Handlers take method strings; task methods (tasks/*, notifications/tasks/*)
use the 3-arg custom form (excluded from v2's spec-method set).
- Legacy tasks kept working (per project requirement): requestor tasks re-
implemented over raw client.request + explicit deprecated schemas;
experimental.tasks.callToolStream replaced by a local pollTaskToolCall
async generator (with _progressHandlers revival so task-execution progress
still reaches the caller). Receiver (server-initiated) tasks: the v2 Client
validates a sampling/elicit handler result and rejects the legacy { task }
response with -32602 — installReceiverTaskResponseBypass swaps the wrapped
entry in the private _requestHandlers map for the task-augmented branch so
{ task } reaches the wire (fixes server-initiated sampling-via-task).
- Pagination: list verbs use raw client.request({method}, List*ResultSchema)
for single-page behavior (v2's client.listX() auto-aggregate all pages).
Web / auth / apps
- Rename local JsonSchemaType -> InspectorFormSchema + add toFormSchema()
structural narrowing at the SDK-schema -> form boundary.
- ext-apps still peers on SDK v1: one compat boundary with documented casts
(remove when ext-apps#702 lands a v2 peer).
- OAuth provider saveClientInformation reconciled with v2's
OAuthClientInformationContext; InvalidClientMetadataError re-homed as a
local class (server-legacy/auth is not browser-safe).
- vitest.shared.mts dedupes @modelcontextprotocol/client+core to one copy so
vi.mock intercepts the SUT's import.
Accepted v2 behavior changes (per #1624 / spec §9.2): unknown-tool call
rejects with -32602; cancellation is stream-abort (no guaranteed
notifications/cancelled frame); output-schema strictness restored via the
Inspector's own Ajv check on the default path.
npm run ci green: validate (web 3087 / cli 212 / tui 274 / launcher 5),
coverage (>=90 per-file, all clients), smoke (launcher/cli/web), storybook
(410).
Closes#1624
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* wip(core): bulk-copy v1.5 InspectorClient runtime files (#1302)
Verbatim ports from origin/v1.5/main into v2/main core/:
- logging/ (2 files)
- storage/ + storage/adapters/ (4 files)
- auth/ + auth/browser/ + auth/node/ + auth/remote/ (16 files)
- mcp/config.ts + mcp/node/ (4 files, stdio transport)
- mcp/remote/ + mcp/remote/node/ (12 files, HTTP/SSE transport)
- mcp/inspectorClient.ts (~2169 LOC), messageTrackingTransport,
fetchTracking, oauthManager, index, state/index
Total: ~7,800 LOC of source files, copied unmodified via
`git show origin/v1.5/main:<path> > <dest>`.
Also:
- Add deps: pino, hono, @hono/node-server, atomically, zustand, @types/node
- tsconfig.app.json: extend paths to resolve new node-only deps from
core/, add "node" to types, disable erasableSyntaxOnly (v1.5 code
uses parameter properties — TODO to re-enable in follow-up)
Compiles down to 47 type errors, all in three categories:
- 24 TS2305: v2 dropped v1.5 type exports (InspectorClientOptions,
CreateTransport, InspectorClientEnvironment, AppRendererClient,
SamplingCreateMessage class, ElicitationCreateMessage class,
jsonUtils helpers, OAuth events). Per user direction, will re-add
these to v2's diverged files (types.ts, samplingCreateMessage.ts,
etc.) so the ported code stays verbatim.
- 15 TS7006: implicit-any params in v1.5 code (v1.5 tsconfig was
looser than v2's noImplicitAny). Need explicit annotations.
- 8 other TS errors: ../package.json import, Transport|null narrowing,
hono Context generic mismatch, one unused parameter.
Tests not yet ported (19 files, ~11,170 LOC).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* wip(core): integrate ported v1.5 InspectorClient + port tests (#1302)
Source integration (typecheck + build now pass):
- Re-add v1.5 types/classes dropped during v2 evolution:
- types.ts: CreateTransport*, AppRendererClient, InspectorClient{Environment,Options}
- samplingCreateMessage.ts / elicitationCreateMessage.ts: classes + keep v2's
InspectorPending{Sampling,Elicitation} interface
- inspectorClientEventTarget.ts: oauth* event keys
- json/jsonUtils.ts: convertParameterValue / convertToolParameters /
convertPromptArguments + ParameterSchema
- inspectorClient.ts: replace `../package.json` import (v2 has no
core/package.json) with a hardcoded identity constant
- remote/node/server.ts: cast hono Context for streamSSE (hono's
generic typing tightened since v1.5)
- oauth-callback-server.ts: drop unused hostname field
- tsconfig: enable @types/node, add paths for new bare-module deps
(pino, zustand, hono, atomically) in app + test configs
- vite.config.ts: mirror those module aliases for the unit project
(which runs from repoRoot)
Tests ported (19 files, ~11K LOC) under clients/web/src/test/core/:
- All core/__tests__/auth/* (7 files)
- inspectorClient.test.ts + 4 OAuth variants
- mcp/oauthManager.test.ts, jsonUtils.test.ts
- transport, remote-transport, remote-server-config, storage-adapters
- helpers/oauth-client-fixtures.ts
Bulk-rewrote `from "../mcp/…"` → `from "@inspector/core/mcp/…"` etc.
Current state:
- typecheck: 0 errors
- build: passes (vite v8, 788 modules)
- unit tests: 1014 / 1034 pass (937 pre-existing + 77 new core tests)
- 20 failures in 13 files; failure modes:
- 13 file-load failures needing the v1.5 `test-servers/` package
(@modelcontextprotocol/inspector-test-server) which isn't in v2 yet
or real fs/network not available in happy-dom
- 7 assertion failures in discovery.test.ts + state-machine.test.ts
(SDK 1.29 vs 1.25 API drift — mocks don't match new shape)
Coverage gate not yet checked against new files.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* wip(core): port test-servers, more types, partial test integration (#1302)
- Port v1.5 test-servers/ package (12 files, ~5K LOC) under
repo-root/test-servers/, wire @modelcontextprotocol/inspector-test-server
alias in both vite.config.ts (regex form) and tsconfig.test.json.
- Add deps: express ^5, yaml ^2, @types/express ^5.
- Re-export InspectorClientOptions/Environment/Transport* from inspectorClient.ts
so v1.5 tests that import them from that module path keep resolving.
- Switch InspectorClientEventMap to use SamplingCreateMessage /
ElicitationCreateMessage classes (matches v1.5 event payload contracts)
while keeping the InspectorPending{Sampling,Elicitation} interfaces in
the *.ts modules for v2 consumers that still use them.
- Fix verbatim-module-syntax issue in test-servers and drop unused stdio
config field.
- Adjust inspectorClient.test.ts task types to TaskWithOptionalCreatedAt
(SDK 1.29 tightened Task shape vs v1.5's 1.25).
- Drop spurious maxMessages/maxFetchRequests/maxStderrLogEvents from
remote-transport.test.ts (never on InspectorClientOptions).
State:
- typecheck: 0 errors
- build: passes
- unit tests: 1099 / 1270 pass
- 171 failures in 10 test files, almost all integration tests that need
real HTTP/fs/network (happy-dom can't host them). Next: add a node-env
vitest project to run these properly.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(core): port v1.5 InspectorClient + transports + auth subsystem (#1302)
Bulk-port of the v1.5 core runtime (~7,800 LOC source + ~16K LOC tests +
~5K LOC test-servers/) into v2. Files copied verbatim from origin/v1.5/main
via `git show >`; only minimal adapters added on the v2 side.
Subsystems landed
-----------------
- core/logging/, core/storage/, core/auth/ (browser + node + remote)
- core/mcp/ runtime: inspectorClient.ts (2169 LOC), oauthManager,
messageTrackingTransport, fetchTracking, config, index
- core/mcp/node/ (stdio transport)
- core/mcp/remote/ + remote/node/ (HTTP/SSE transport + Hono server)
- test-servers/ package (composable MCP test servers, fixtures, harness)
v2 adapter layer
----------------
- types.ts: append CreateTransport*, AppRendererClient,
InspectorClient{Environment,Options} (v2 had pruned these — v1.5 needs them)
- samplingCreateMessage / elicitationCreateMessage: keep v1.5 classes AND
v2's Inspector Pending* interfaces in the same files
- inspectorClientEventTarget: add oauth* event keys; switch pending
sampling/elicitation payloads to the classes (matches v1.5 contracts)
- json/jsonUtils: append convertParameterValue/convertToolParameters/
convertPromptArguments + ParameterSchema
- inspectorClient.ts: re-export Options/Environment/Transport* so tests
that import these from `inspectorClient.js` keep resolving; replace
`../package.json` import with a hardcoded identity (v2 has no core/package.json)
- remote/node/server.ts: cast hono Context for streamSSE (hono generic
tightened since v1.5)
- oauth-callback-server: drop unused hostname field
- tsconfig.app.json / tsconfig.test.json: add @types/node + paths for
pino/zustand/hono/@hono/node-server/atomically/express/yaml, disable
erasableSyntaxOnly (parameter-property syntax from v1.5)
- vite.config.ts: regex-form module aliases (so the package's exports
field handles subpaths like `hono/streaming`, `zustand/middleware`),
alias for @modelcontextprotocol/inspector-test-server → test-servers/src
Tests
-----
- 19 v1.5 test files copied under clients/web/src/test/core/,
imports rewired to @inspector/core/* and @modelcontextprotocol/inspector-test-server
- 1004 unit tests pass; 298 storybook tests pass; coverage gate passes
Known follow-ups (out-of-scope here, tracked in TODOs)
------------------------------------------------------
- 13 integration test files are excluded from the unit project (spawn real
HTTP/stdio servers; run real OAuth flows; mock SDK auth → happy-dom CORS).
Needs a node-env vitest project. Files listed under `test.projects[0].test.exclude`.
- Source files exercised only by those integration tests are excluded from
the coverage gate pending the node-env project. Listed under
`test.coverage.exclude` with comment.
- Manual smoke tests against real stdio / HTTP / OAuth server per the AC
on #1302 still need verification locally.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs/fix: address #1306 review (AGENTS tree, #1307 links, @types/node, .substr)
- AGENTS.md: expand the project-structure tree to include all v1.5-ported
subsystems (core/auth/{browser,node,remote}, core/storage, core/logging,
core/mcp/{node,remote/{,node}}, core/mcp/state) plus the new top-level
test-servers/ directory (with a note about its @modelcontextprotocol/
inspector-test-server alias).
- vite.config.ts: reference #1307 from both the test exclude block and the
coverage exclude block so the next person editing either sees the
marching order for shrinking the lists.
- package.json: restore @types/node to ^24 (an earlier `npm install
--save-dev @types/node@^22` accidentally pinned it lower than the repo
was using; nothing here required ^22).
- core/mcp/fetchTracking.ts: replace deprecated .substr(2, 9) with
.slice(2, 11) to match the convention in core/mcp/inspectorClient.ts.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Stands up the type-only prerequisites for the v2 UX component
interfaces refactor per specification/v2_ux_interfaces_plan.md.
Phase 0.1 — MCP SDK dependency:
- Add @modelcontextprotocol/sdk ^1.29.0 and zod ^4.3.6 to both the
root package.json and clients/web/package.json so component files
can import Tool / Prompt / Resource / Task / LoggingLevel / etc.
directly from the SDK.
Phase 0.2 — Inspector wrapper-types module:
- Create core/mcp/types.ts mirroring the type-only subset of v1.5's
core/mcp/types.ts: MCPServerConfig (discriminated union), ServerType,
MCPConfig, ConnectionStatus, StderrLogEntry, MessageEntry (Date
timestamps, not ISO strings), FetchRequestEntry(+Base), ServerState,
and the *Invocation types. Adds v2-only wrappers
InspectorResourceSubscription and InspectorServerJsonDraft.
- Add core/mcp/taskNotificationSchemas.ts for the Inspector-owned
notifications/tasks/list_changed signal (not in the SDK).
- Add core/mcp/elicitationCreateMessage.ts re-exporting ElicitRequest
and ElicitResult plus an InspectorPendingElicitation interface for
typing the pending-queue.
- Add core/json/jsonUtils.ts for the shared JsonValue / JsonObject
types used inside core/mcp/types.ts.
- Copy v1.5's clients/web/src/utils/jsonUtils.ts (JsonSchemaType) and
schemaUtils.ts (AJV-backed validators) verbatim so SchemaForm can
switch off its local JsonSchema type.
- Copy v1.5's clients/web/src/lib/types/customHeaders.ts verbatim for
ServerSettingsForm and the experimental panel.
- Add clients/web/src/types/navigation.ts with InspectorTab (UI-routing
concept, lives with the web client rather than in core/).
- Wire tsconfig.app.json + vite.config.ts with the @inspector/core/*
path alias so component files can import from core/ without
relative-path hell.
Phase 0.3 — Vet (likely) hedges in v2_ux_interfaces.md:
- Follow-up sweep on commit 2ef257da. Replaces the remaining
useMcpClient references with useInspectorClient, ties pending
elicitation / sampling callbacks to the in-InspectorClient queue
rather than a non-existent useElicitation / useSampling hook,
corrects Task references to the SDK type (not an InspectorTask
wrapper), corrects log hook wiring to useMessageLog, and strikes
all remaining v2-only hooks with explicit "no v1.5 analog"
annotations. grep "likely" specification/v2_ux_interfaces.md now
returns zero results.
Phase 0.4 — Local-redeclaration inventory:
- specification/v2_ux_interfaces_phase_0_4_inventory.md enumerates
every ad hoc local type (JsonSchema, LogLevel, TaskStatus,
PromptItem, ResourceItem, ToolListItemProps, RootEntry, KeyValuePair,
inline ConnectionStatus / transport unions) that will be replaced
in Phases 1–4, including the file it lives in, every site that
re-imports it, and the SDK / wrapper type that replaces it. Intended
for the Phase 0 PR description and as a running checklist during
the refactor.
Build state: npm run build / lint / format:check all pass in
clients/web.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
cliffhall
Sam Morrow