perf(fts): defer decoding for underfilled conjunctions

[BubbleCal]

Before a competitive floor exists, AND queries still decoded frequencies and prepared bounds while looking for intersections. This PR keeps that work lazy, particularly when the final intersection has fewer than k matches.

• Split DocID and frequency decoding for full posting blocks and tails, retaining the existing encoded format and combined decoding entry points.
• Advance and intersect DocIDs before decoding frequencies; initialize score bounds when a positive competitive floor makes them useful.
• Avoid loading document lengths for partitions whose dictionaries cannot satisfy all required tokens.
• Use SIMD catch-up for the existing classic 4/5-clause path, with unsigned comparisons covering the full u32 DocID range and a binary-search fallback without AVX2.

Tests cover empty/underfilled intersections, delayed frequency and bound activation, block/tail transitions, required-token misses, and scalar/SIMD boundary behavior. Code and its regression tests stay together in this PR.

No isolated main A/B measurement is claimed for this layer. The later bulk-intersection measurements belong to #9030.

Validation

• Local inverted-index suite: 530 passed.
• Required all-workspace Clippy: passed.
• CI: pending.

Stack, 1/4: this PR → #9032 → #9033 → #9030. Base: main.

Merge in stack order; retarget/restack the remaining PRs after their parent merges.

[lance-gatekeeper]

⚠️ Gate recommendation: approve with a non-blocking risk.

The lazy, block-granular decoder addresses the real underfilled-AND cost without changing the posting format, and the current coverage preserves classic/bulk, phrase, tail, score, and full-u32 behavior. The residual risk is evaluation: this layer has no isolated base-to-head benchmark, while the linked #9030 measurements cover a later stacked increment, so net latency and possible regressions outside underfilled conjunctions remain unquantified. No change is requested for this PR.