fix: preserve scalar enum and const constraints in MCP schemas

[liangzhechen655]

MCP tool parameters with scalar enum or const values lose their choices during schema conversion. The generated input model accepts values outside the advertised choices, and the model-facing schema omits the restrictions.

Represent scalar choices with Literal, intersect them with the declared JSON type, and validate that type before literal matching. This keeps null out of a string-only enum, rejects strings in integer enums, and distinguishes booleans from numbers. Nullable type arrays retain null when explicitly allowed. Definitions with no compatible scalar choices raise a clear error instead of becoming unrestricted fields.

Referenced choices use the resolver already merged in #304; this PR's remaining source diff only adds scalar constraints to that implementation.

Validation on Windows / Python 3.13:

• All 11 original regressions failed on the original base. All 10 additional type-intersection regressions failed on the previous PR head.
• Full core suite: 421 passed, 3 credential-gated integration tests skipped, 93% total coverage.
• Repository-wide Black and Flake8 checks pass.
• GitHub's Code Quality & Tests check passed on 6dbfbe4.
• No live provider integration run is claimed.

[Eigenwise]

Source review of 73963771fbfcd18a45b8bf61d0f0c3f8fdb56ee8: schema_transformer.py:103-108 returns a Literal before applying the declared field type. A required string field with enum: ["brief", null] now includes null, and an integer field with enum: [1, "two"] includes a string. Preserve the intersection of the declared type and choices, and test both typed mixed-enum cases in validation and the emitted schema.

The reference-resolution change overlaps #304. Retain one implementation of that branch when reconciling the two. This correctness finding is source-derived; I haven't run this head's tests locally.

The earlier complexity-only rework request is withdrawn.

[Eigenwise]

Rechecked 6dbfbe4d22838c5e0126014a5676297f7e88cf41. The earlier string/null and integer/string intersections are repaired, with validation and emitted-schema regressions. Normal CI passed 421 tests with 3 MiniMax skips; formatting and lint passed.

One scalar-choice issue remains at schema_transformer.py:41-55: for type: ["boolean", "integer"], enum: [true], input 1 passes the type guard and Literal[True] converts it to True. Conversely, enum: [1] accepts True and returns 1. The existing Pydantic 2.12.4/core 2.41.5 dependency confirms that literal matching behavior; the complete candidate example is source-derived, not locally executed.

Check JSON scalar choice identity before literal matching, and add boolean/numeric union and untyped enum/const regressions. Preserve ordinary numeric equality such as 1 and 1.0. No broader schema redesign requested.